stbr
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 12 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/solanabr/ai-kit with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/solanabr/ai-kit'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/solanabr--ai-kit)HTML
<a href="/listings/solanabr--ai-kit"><img src="/api/listings/solanabr--ai-kit/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
After installation, configure the MCP servers from inside Claude Code in your project:
/setup-mcp
This guides you through the Helius API key and offers the [optional MCP servers](docs/configuration.md#optional-mcp-servers) — including the ones that sign transactions or reach a production database, with what each exposes before you attach it. Beyond the standard plugins above, Anthropic's marketplace has more worth adding and some that collide with the firewall: [which ones, and what each costs per session](docs/configuration.md#optional-plugins).
**We recommend [varlock](https://varlock.dev) for the keys themselves.** The install also writes `.env.schema`, a varlock schema with every key's name, type, purpose and whether it is secret, but no values, so it is safe to commit and safe for the agent to read. `varlock load` validates `.env` against it, and `varlock run --inject vars -- claude` starts Claude Code with the values, which can come from 1Password or another secret manager instead of a plaintext `.env`. Nothing changes if you skip it: `.env.example`, `.env` and `/setup-mcp` work as before. [Setup, what it does not hide from the agent, the preview credential proxy, and the safe-ai-skill policy line older installs need](docs/configuration.md#secrets-with-varlock).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 37 lines
- {
- "$schema": "https://code.claude.com/schemas/marketplace.json",
- "name": "stbr",
- "owner": {
- "name": "SuperteamBR",
- "url": "https://github.com/solanabr"
- },
- "metadata": {
- "description": "Solana AI Kit — Claude Code configuration for Solana development: specialized agents, workflow commands, go-to-market skills, MCP servers, and hooks.",
- "version": "2.4.0"
- },
- "plugins": [
- {
- "name": "solana-ai-kit",
- "source": "./plugin",
- "description": "Core Solana dev kit: specialized agents, workflow commands, skills, MCP servers, and dev hooks. Installs the safe-ai-skill security firewall as a dependency. (Full install via install.sh adds the project CLAUDE.md, the permissions/sandbox policy, and the ext/ skill packs: core by default, extensions on demand.)",
- "category": "Development",
- "homepage": "https://github.com/solanabr/ai-kit",
- "license": "MIT",
- "keywords": ["solana", "anchor", "rust", "web3", "defi", "blockchain", "agents", "mcp"]
- },
- {
- "name": "safe-ai-skill",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/solanabr/safe-ai-skill.git",
- "path": "plugins/safe-ai-skill",
- "ref": "main",
- "sha": "8920686ba919faa9804c6d41297bfa8bcdaed527"
- },
- "description": "Security firewall and supply-chain verifier (hooks): gates mainnet, value-moving and authority actions and secret reads, and pins installed skills and MCPs at session start. Core part of the kit: solana-ai-kit depends on it.",
- "category": "Security",
- "homepage": "https://github.com/solanabr/safe-ai-skill",
- "license": "MIT"
- }
- ]
- }
README.md · README · 217 lines · 3 findings marked
- <p align="center"><img src=".github/assets/solana-ai-kit-banner.png" alt="Solana AI Kit — Skill, MCP & config aggregator for Claude Code, Codex + any agentic setup" width="100%" /></p>
- # Solana AI Kit
- [](https://github.com/solanabr/ai-kit/actions/workflows/ci.yml)
- 
- 
- 
- 
- [](https://ai.superteam.codes)
- **Claude Code, set up to ship on Solana.** Not programs alone — the whole lifecycle: validating the idea, building the program and the app around it, shipping it, and the launch and growth work that follows. One command installs 15 specialized agents, 54 workflow commands, skill packs pinned — and scanned — at a commit from the ecosystem's own repositories, 4 MCP servers for on-chain data, live docs and context compression, and a firewall that gates mainnet deploys, secret reads and destructive commands. Almost none of it loads until a task needs it.
- ```bash
- curl -fsSL https://aikit.superteam.codes | bash
- Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
- Line 15 on GitHub
- ```
- Run it from your project's root — it installs into the current directory. Everything this README links out to lives in [`docs/`](docs/), which stays in this repository and is never copied into yours.
- Browse every agent, command and skill pack at **[ai.superteam.codes](https://ai.superteam.codes)**. Each page is also plain Markdown at the same path plus `.md`, for agents, indexed at [`/llms.txt`](https://ai.superteam.codes/llms.txt).
- ## What This Is
- A complete `.claude/` configuration that turns Claude into a Solana building partner across that whole lifecycle, not program code alone:
- - **15 specialized agents** for different tasks (architecture, Anchor, Pinocchio, DeFi, tokens, frontend, mobile, backend, DevOps, QA, docs, games, Unity, learning, research) — [full table](docs/agents-and-commands.md#agents)
- - **54 workflow commands** for building, testing, deploying, profiling, migrating, committing, and writing the PR, plus an agent workflow with a command per step from intake to merge: `/crew` chains the steps and stops at your gates, `/parallel` fans any task out to agents in file-owned lanes, and `/adversarial` puts a task's key claims to an adversary — [full table](docs/agents-and-commands.md#commands), [how it chains](docs/agents-and-commands.md#how-the-agent-workflow-chains)
- - **4 MCP servers** on by default for on-chain data (Helius), Solana docs (solana-dev), library docs (Context7) and context optimization (context-mode), plus opt-in browser automation (Playwright) and local-validator / mainnet-fork control (Surfpool)
- - **Four firewall tiers** (Off / Relaxed / Medium / High, default Relaxed) gating file access, destructive commands, egress and `context-mode`'s code executor — pick one with `/firewall`, see [Firewall tiers](#firewall-tiers)
- - **The [safe-ai-skill](https://github.com/solanabr/safe-ai-skill) security firewall** (core, installed with the kit): hooks that gate mainnet, value-moving and authority actions, in Bash and in MCP tools, hold transfers to spend caps, block secret reads, and pin installed skills and MCPs at session start — [details](#security-firewall-safe-ai-skill)
- - **Four standard plugins**, two steps at the end of the install: [memsearch](#persistent-memory-memsearch) for memory that outlives a session, and [`rust-analyzer-lsp`, `typescript-lsp`, `csharp-lsp`](#code-intelligence-language-server-plugins) so the agent reads your code through a compiler
- - **Pinned skill packs** from Solana Foundation, Colosseum, Jupiter, Metaplex, MagicBlock, Helius, Alchemy, SendAI, Solana Mobile and more — four installed by default (three into `ext/`, plus Anthropic's own `frontend-design` and `webapp-testing` top-level), the rest on demand ([skill-packs.md](docs/skill-packs.md)). One extension reports usage: `solana-new`'s SKILL.md files open with a telemetry block that appends each skill run to `~/.superstack/telemetry.jsonl` and, once its own setup script has written a Convex endpoint into `~/.superstack/config.json`, POSTs the skill name, version, OS and timestamp there. The kit reads that pack's references and does not run those blocks; `{"telemetryTier":"off"}` in that config file turns both off
- - **Agent teams** (opt-in, experimental) for multi-step workflows (architect → engineer → QA)
- - **Progressive skill loading** that only loads context when needed (saves tokens)
- - **A small always-on CLAUDE.md** carrying only the house rules and workflow a strong model would not infer; everything else is on demand
- ## Installer (recommended)
- The installer copies the kit into a project: `.claude/` (agents, commands, skills, a `settings.json` with the permissions, sandbox and hooks, and a `security.json` naming the [firewall tier](#firewall-tiers) those rules came from), `CLAUDE.md`, `.mcp.json` and `.env`, then installs the kit's security plugin, [safe-ai-skill](#security-firewall-safe-ai-skill), with the `claude` CLI. It downloads the kit's latest release tag from GitHub into a temporary directory, which it deletes when done. It installs into the current directory, so go to your project's root first (replace `your-project` with its path):
- ```bash
- cd your-project
- ```
- ```bash
- curl -fsSL https://aikit.superteam.codes | bash
- Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
- Line 46 on GitHub
- ```
- `aikit.superteam.codes` and `aikit.superteam.codes/install.sh` both redirect to [`install.sh` on `main`](https://raw.githubusercontent.com/solanabr/ai-kit/main/install.sh).
- **Verify before you run it.** Same installer, with a review step: download it, read it, then run the copy you read. To check it against a release's published SHA-256 instead, see [verify a release installer](docs/install.md#verify-a-release-installer).
- ```bash
- curl -fsSL https://aikit.superteam.codes/install.sh -o /tmp/solana-ai-kit-install.sh
- ```
- ```bash
- less /tmp/solana-ai-kit-install.sh
- ```
- ```bash
- bash /tmp/solana-ai-kit-install.sh
- ```
- When the installer finishes, start Claude Code in the project:
- ```bash
- claude
- ```
- Two things finish the install from inside Claude Code, and both are part of a standard setup rather than extras: **[memsearch](#persistent-memory-memsearch)**, so the project's decisions survive the end of a session, and **[the language server plugins](#code-intelligence-language-server-plugins)**, so the agent reads your code through a compiler instead of grep.
- ```text
- /plugin marketplace add zilliztech/memsearch
- /plugin install memsearch
- /plugin install rust-analyzer-lsp@claude-plugins-official
- /plugin install typescript-lsp@claude-plugins-official
- /plugin install csharp-lsp@claude-plugins-official
- ```
- Take the LSP lines for the languages you actually write — Rust for programs, TypeScript for the client, C# for the Unity/PSG1 track — and install each language server first, since Claude Code offers the plugin once the binary is on your `PATH`. memsearch needs a restart.
- Then `/setup-mcp` for the Helius API key. Everything past that point is genuinely optional: the [opt-in MCP servers](docs/configuration.md#optional-mcp-servers) and the [optional plugins](docs/configuration.md#optional-plugins).
- ### Other ways to install
- Codex, opencode and anything else that reads `AGENTS.md` and `.agents/skills/` instead of Claude Code's files:
- ```bash
- curl -fsSL https://aikit.superteam.codes | bash -s -- --agents
- Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
- Line 90 on GitHub
- ```
- | Route | Use it when |
- |-------|-------------|
- | [From a clone](docs/install.md#from-a-clone) | You want to pin a release, or read every file before it reaches your project |
- | [`--agents`](docs/install.md#codex-opencode-and-other-agents) | Your tool reads `AGENTS.md` and `.agents/skills/` — see [what each harness enforces](docs/other-agents.md) |
- | [No install](docs/install.md#no-install-read-the-kit-from-aikitsuperteamcodes) | You want the skills in any agent without adding files to your project |
- | [Claude Code plugin](docs/plugin.md) | Not recommended — read that page before you use it |
- | [GitHub template](docs/install.md#using-as-a-github-template) | You are starting a new repository from the kit rather than adding it to one |
- Already installed? `/update` inside Claude Code pulls the latest release ([details, and the shell form](docs/install.md#updating)). Working in a fork or clone of this repo? Its top-level `CLAUDE.md` is for maintaining the kit itself; `/cleanup` swaps in `CLAUDE-solana.md`.
- ### Config is gitignored by default
- To keep your project clean, the installer adds `.claude/`, `.mcp.json`, `.gitmodules` and `.safe-ai-skill/` to `.gitignore` — the kit reads as ignorable infrastructure, not your app code (the `ext/` skill packs are ignored too; `bash .claude/bin/update.sh` re-fetches the core packs and the project's extensions). An `--agents` install ignores `.agents/`, `.mcp.json` and `.gitmodules` the same way. Neither ignores the instruction file, `CLAUDE.md` or `AGENTS.md`, because [Grok Build skips an instruction file that `.gitignore` lists](docs/other-agents.md), and `/update` takes it out of the block an older install wrote. `CLAUDE.local.md`, for private notes, stays ignored.
- Want the config tracked in git (team setup, reproducible config)? Run `/commit-claude-config` — it un-ignores those files and commits them with the instruction file (or edit `.gitignore` by hand). If your project already commits `.claude/` or its own `.gitmodules`, the new ignore lines are a no-op — git keeps tracking files it already tracks.
- ### MCP setup
- After installation, configure the MCP servers from inside Claude Code in your project:
- ```text
- /setup-mcp
- ```
- This guides you through the Helius API key and offers the [optional MCP servers](docs/configuration.md#optional-mcp-servers) — including the ones that sign transactions or reach a production database, with what each exposes before you attach it. Beyond the standard plugins above, Anthropic's marketplace has more worth adding and some that collide with the firewall: [which ones, and what each costs per session](docs/configuration.md#optional-plugins).
- **We recommend [varlock](https://varlock.dev) for the keys themselves.** The install also writes `.env.schema`, a varlock schema with every key's name, type, purpose and whether it is secret, but no values, so it is safe to commit and safe for the agent to read. `varlock load` validates `.env` against it, and `varlock run --inject vars -- claude` starts Claude Code with the values, which can come from 1Password or another secret manager instead of a plaintext `.env`. Nothing changes if you skip it: `.env.example`, `.env` and `/setup-mcp` work as before. [Setup, what it does not hide from the agent, the preview credential proxy, and the safe-ai-skill policy line older installs need](docs/configuration.md#secrets-with-varlock).
- ### Persistent memory: memsearch
- Of everything in the standard install, this is the one that changes how the kit feels day to day. A Solana project accumulates context that is expensive to rediscover: which program ID is live on which cluster, the account layout you settled on and the reason you rejected the other one, the approach that failed, the protocol quirk that cost you an afternoon. Without persistent memory every session starts cold — the agent re-derives it, re-asks you, or quietly re-makes a decision you already threw out.
- [memsearch](docs/configuration.md#persistent-memory-memsearch) gives it semantic recall over markdown you own, so the store can grow without the always-on context budget growing with it. That is the opposite trade from putting more in `CLAUDE.md`, which every session and every subagent pays for whether it is relevant or not. Markdown stays the source of truth, so your memory stays diffable, reviewable and portable.
- Nothing leaves your machine: a local Milvus Lite store and an ONNX `bge-m3` embedder on CPU, no key and no account. Setup costs a ~558 MB model download on first launch and one restart; per session it costs four hooks and ~400 tokens of skill descriptions, plus the recent-memory preview its `SessionStart` hook injects — [the measured breakdown](docs/configuration.md#standard-plugins).
- ```text
- /plugin marketplace add zilliztech/memsearch
- /plugin install memsearch
- ```
- It is a plugin, not an MCP server. `memsearch-mcp` was never published to npm, so an `.mcp.json` entry for it silently never starts — `/doctor` flags that entry if an older install still carries one, and `/update` removes it. Its recall skill runs at Off and Relaxed, the default; at Medium and High its set-up line meets the `bash -c` deny and recall stops ([why](docs/configuration.md#persistent-memory-memsearch)).
- ### Code intelligence: language server plugins
- The other half of the standard install. Without a language server the agent navigates your code by reading files and matching text; with one it asks the compiler — go-to-definition, find-all-references, the real type of a value, the diagnostics your editor shows. On a Solana project that is three servers for three languages: Rust for the programs, TypeScript for the client and frontend, C# for the Unity/PSG1 track.
- ```text
- /plugin install rust-analyzer-lsp@claude-plugins-official
- /plugin install typescript-lsp@claude-plugins-official
- /plugin install csharp-lsp@claude-plugins-official
- ```
- **Install the language server itself first** — `rustup component add rust-analyzer`, `npm i -g typescript typescript-language-server`, and a C# server such as `csharp-ls` — and Claude Code then offers the matching plugin once the binary is on your `PATH`. Install only the ones whose language you write.
- These are the cheapest additions in the kit: no hook, nothing registered in the session listing, so the standing context cost is about zero and an idle one is free. Skip a language and you simply skip its plugin.
- ## Security firewall: safe-ai-skill
- [safe-ai-skill](https://github.com/solanabr/safe-ai-skill) is a core part of the kit. It is a Claude Code plugin whose hooks gate mainnet, value-moving and authority actions, hold transfers to per-transaction and daily spend caps, block reads of keypairs and credential stores, and pin installed skills and MCPs at session start. Its gates also cover MCP tools, such as Helius's `heliusWrite` transfers, which the kit's own hooks do not see. The kit's `stbr` marketplace lists it next to the kit plugin, pinned to safe-ai-skill **1.3.4** (commit `8920686b`); a plugin release reaches you only when the kit moves that pin, and `/update` then moves an installed plugin to it.
- - **Plugin install:** `solana-ai-kit@stbr` depends on `safe-ai-skill@stbr`, so installing the kit installs it.
- - **Full install:** `.claude/settings.json` enables `safe-ai-skill@stbr`, but Claude Code installs a plugin from an external source only when each user runs the install, so `install.sh` runs `claude plugin install safe-ai-skill@stbr --scope project` for you, registering the `stbr` marketplace first when needed. `--no-safe-ai-skill` skips it, and so does a missing `claude` CLI or a platform with no engine build; the closing message then prints the command. Someone who clones a project that commits the kit config runs that command once. When `SOLANA_AI_KIT_UPSTREAM` points at a fork, the fork's marketplace is the one registered as `stbr` on that machine. `/doctor` reports whether it is installed.
- - **`--agents` install (Codex, opencode):** the hooks are Claude Code only. Vet add-ons with the CLI instead: `npx @stbr/safe-ai-skill add skill|mcp <source>`.
- Its engine ships prebuilt for macOS and Linux on x64 and arm64, and for 64-bit Windows under Git Bash. On any other platform it fails open with a notice and Solana CLI calls still ask; the installer skips it there. To turn it off for yourself in a full install, set `"safe-ai-skill@stbr": false` under `enabledPlugins` in `.claude/settings.local.json`.
- **Part of the firewall lives only in this plugin.** No kit layer stands in for these rules, so they hold only while safe-ai-skill is installed and enabled, and turning it off drops them: the Read tool on project keypairs, shell history, `~/.ssh` and key containers, on-chain gating at Off, spend caps, value-moving calls on MCP servers other than `context-mode`, the `curl … | sh` deny, the session-start supply-chain check and the pasted-key prompt guard. Without the kit's sandbox (Off, or a plugin install) the plugin is a pattern layer, which a script written in one call and run in the next, a path built at runtime or a subprocess reading a credential file walks past. Which layer enforces each rule: [docs/firewall.md](docs/firewall.md#who-enforces-what).
- **Project policy.** The full install writes `.safe-ai-skill/policy.yaml`, which safe-ai-skill merges over its default policy; a project policy can only tighten. It sets two keys. `supply_chain.exec_install_scripts: deny` denies download-and-run (`curl … | sh`) from a host outside safe-ai-skill's installer list instead of asking; the Anza installer still runs. `secrets.deny_read_globs` adds shell history, `~/.ssh`, the macOS keychain files and key containers (`.kdbx`, `.ppk`, `.p12`, `.pfx`, `.jks`, `.keystore`) to the reads it denies. The project's `.env` follows the [firewall tier](#firewall-tiers): safe-ai-skill lets the agent read it at Off, Relaxed and Medium and denies it at High, and the env templates, the [varlock schema](docs/configuration.md#secrets-with-varlock) among them, stay readable. Add `env_read: deny` under `secrets` to deny the project's `.env` at every tier. `install.sh` writes the file, and `/update` adds it when missing and refreshes it while it is still an unedited copy the kit shipped. Once you edit it, it is yours and `/update` leaves it alone. The firewall denies the agent edits to it at every tier — unlike `.claude/settings.json`, which only [High](#firewall-tiers) protects: this file is a third-party security tool's policy rather than part of the installation you customize. It is gitignored with the rest of the kit config; run `/commit-claude-config` so teammates who clone the repo get it too.
- safe-ai-skill checks each `ext/` pack on its own and never moves one. From Relaxed it denies a pack in place when its files changed since it pinned them, or a check finds a BLOCK, until you run `safe-ai-skill verify approve <pack>` in your own terminal; the agent can't. At High it also denies a pack with a HIGH heuristic finding until you trust or approve it. `/update` names the packs it changed, with the command that approves each.
- ## Firewall tiers
- One tier is in force per project. `.claude/security.json` names it; `/firewall` (or `/firewall <tier>`) switches it and rewrites the kit-owned rules in `.claude/settings.json` to match. The default is **Relaxed**. A switch takes effect in the **next** session: permission and sandbox rules are read once at session start, so the session you are in keeps the rules it started with, whether the change was a tightening or a loosening.
- The hooks also gate `context-mode`'s MCP tools at every tier, and Medium and High refuse its code executor and arbitrary-path reader outright — a local MCP server runs outside the OS sandbox, so the two stricter tiers cannot keep their read and egress promises while it is callable. Those two tiers also refuse Playwright's `browser_run_code_unsafe` and `browser_network_request`, and High alone refuses the opt-in Cloudflare server's `execute` and Playwright's `browser_evaluate` — keeping Cloudflare's read-only `docs` and `search`, and Playwright's `browser_navigate`, `browser_snapshot`, clicking and typing, at every tier. [Details](docs/firewall.md#what-the-tiers-do-not-do).
- **High is also the only tier that stops the agent editing the kit's own configuration** — `.claude/settings.json`, `.claude/security.json`, `.mcp.json` and the user-scope equivalents under `~/.claude/`. Off, Relaxed and Medium allow it, on the view that customizing your own installation is your call. **The guard hooks are the exception and are denied at every tier**, Off included: `.claude/hooks/` holds the mainnet, secrets and on-chain gates as executable scripts, and `/firewall` already changes every tier knob without touching them, so customizing never means editing a guard. So below High you own your `.claude/` *configuration*, not the guards. A nested `claude` started with a policy-weakening flag (`--dangerously-skip-permissions`, `--settings`, `--permission-mode` and the like), an organization's managed settings and `safe-ai-skill`'s policy are also denied at every tier. [Details](docs/firewall.md#what-the-tiers-do-not-do).
- | Tier | Readable | Writable | On-chain and destructive | Use it for |
- |------|----------|----------|--------------------------|------------|
- | **Off** | Everything your user account can read. The sandbox is off. | Everything. | The kit asks about no on-chain write here: its on-chain, egress and fetch-and-execute hooks stop early at Off, and only safe-ai-skill, while enabled, still asks on mainnet. Irreversible actions are still refused — `--final`, `program-v4 finalize`, `spl-token authorize --disable`, `anchor idl erase-authority`, and `solana-keygen new --force` over your default wallet. The deny rules apply here too, the git transport overrides, `gh issue delete`, `gh repo delete`, `git config alias.<name>`, `git --config-env`, `git --exec-path=`, `git reflog delete` and `git reflog drop` included, and so do the guards' every-tier refusals: a recursive `rm` aimed at a root, home or project directory, `kill -1`, a shell's `-c`, and the `Read` and `Grep` tools on `gh`'s host file. | A machine you have already isolated — a container or throwaway VM — or a session where you supply your own policy in `~/.claude/settings.json`. |
- | **Relaxed** (default) | Leaves open: your Solana config dir apart from the default wallet (so `solana config get` keeps working), the project's `.env`, and `gh`'s host file `~/.config/gh/hosts.yml`, so `gh` can start inside the sandbox (the Read and Grep tools are still refused it). Denies the never-allowed set, which no tier opens: the default wallet `~/.config/solana/id.json` (so signing with it fails inside the sandbox), SSH and GPG keys, cloud, registry and git-host tokens (`~/.aws`, `~/.npmrc`, `~/.git-credentials`, `~/.netrc`, `~/.cargo/credentials*`, `~/.docker/config.json` and the like), keychains, keyrings and password managers, browser profiles and wallet extension stores, and shell and REPL history — plus writes to shell startup files, `~/.cargo/config.toml` and `~/.gitconfig`. | The repo, the platform temp dir, the toolchain caches (`~/.cargo`, `~/.rustup`, `~/.avm`, the Solana caches) and the project's `.env`. The sandbox refuses a shell write anywhere else. | On-chain writes stop for your approval on every cluster except a local validator, naming the cluster it resolved. `--final`, program close, `spl-token authorize --disable`, `solana-keygen new --force` over your default wallet, a recursive `rm` aimed at a root, home or project directory, and `kill -1` are refused outright. `npm`/`cargo publish` ask. Force push, `gh pr merge`, git history rewrites and `git branch -D` are allowed — this is your own repo — and so are stopping a stuck process and removing containers, images and volumes. | **Local development.** Your own machine and your own repo, where the toolchain should just work. Also the tier to run headless — see [docs/firewall.md](docs/firewall.md#what-the-tiers-do-not-do). |
- | **Medium** | Relaxed's denials, plus the Solana config dir's `*.json` (the wallet files; `cli/config.yml` stays readable), session transcript `*.jsonl`, and the `gh` host file Relaxed leaves open. | The repo and the toolchain carve-outs; the sandbox refuses a shell write anywhere else, as at Relaxed. The project's `.env` becomes **write-deny** — nothing in a Solana build legitimately rewrites it, and an ask there is walked around by `python3 -c`, `perl -pi` or `sed -i`. On Linux and WSL2 the sandbox cannot back that up, so an inline interpreter such as `python3 -c` still writes it there ([details](docs/firewall.md#what-the-tiers-do-not-do)). | As Relaxed, plus `npm`/`cargo publish`, `gh api`, `kill -9`, `pkill`, `killall`, `docker rm`, `docker rmi`, `docker system prune`, `docker volume rm` and `docker compose down -v` denied, and force push, `gh pr merge` and writes to a local validator ask. A skill whose set-up line runs `bash -c` is stopped, memsearch's recall among them. `context-mode`'s code executor and Playwright's `browser_run_code_unsafe` and `browser_network_request` are refused by name. | Reading code you did not write — audits, dependency triage, a repo you cloned to look at. Interactive sessions only. |
- | **High** | Only the working directory and the toolchain roots the build needs. `permissions.blockReadsOutsideWorkingDirectories` is on and the sandbox denies `~/` with a narrow `allowRead` carve-out for `~/.cargo`, `~/.rustup` and the Solana caches. The project's `.env` becomes read-deny, for a sandboxed build too: `npm run build`, `next dev` or `vitest` cannot load it. | The repo plus those toolchain roots (cargo needs *write* to the registry cache or the build dies); everything else outside the repo is denied. The project's `.env` takes a shell append, which is how `/setup-mcp` fills it, but not the Edit and Write tools: a read deny covers them too. A repository's `.git/config` and `.git/hooks/` are denied to the file tools, as Claude Code's own sandbox already denies them to shell writes at every sandboxed tier. | Mainnet writes are denied outright rather than asked, and so are force push and `gh pr merge`. The recoverable history rewrites ask: `git rebase`, `git commit --amend`, `git stash drop`/`clear`, `git branch -d`/`-D`/`-f`, `git tag -d` and `git filter-branch`/`filter-repo`. Starting a workflow and retrying a command outside the sandbox ask too, as permission rules that still prompt in bypass mode. | A repo you actively distrust, or a session on a machine that holds production credentials. Interactive sessions only. |
- | **Maintainer** (kit repo only) | As Relaxed. | As Relaxed, plus the guard hooks in `.claude/hooks/` and `.safe-ai-skill/` to the file tools, and `git submodule` runs outside the sandbox so the packs under `.claude/skills/ext/` can be initialized. | As Relaxed: mainnet writes stop for your approval, and `--final`, `program-v4 finalize`, `spl-token authorize --disable`, `anchor idl erase-authority` and `solana-keygen new --force` over your default wallet are refused. | **Working on the solana-ai-kit repository itself, and nothing else.** It also lets `claude mcp add` run; `claude -p`, `claude plugin validate` and `claude --version` run at every tier. A nested `claude` with a policy-weakening flag is refused here as at Relaxed, so an agent cannot start one with no policy. `firewall.sh` refuses it in any other project, `/update` never re-applies it, `/doctor` reports it as a failure and `validate.sh` refuses it as the committed default. [Details](docs/firewall.md#the-maintainer-tier). |
- Which gate stops what, how a tier is generated, and — at length — **what the tiers do not do**: [docs/firewall.md](docs/firewall.md). Short version: High and Medium are interactive-only, an allowlist is not something the kit can enforce, an MCP server runs outside the sandbox so only the hooks reach it (and at Medium and High `context-mode`'s executor and Playwright's two arbitrary primitives are refused outright, at High Cloudflare's `execute` and Playwright's `browser_evaluate` too), what Relaxed leaves readable is readable by every process the agent runs, not only by the tool it is for — `gh`'s host file included, which only Claude Code's Read and Grep tools are refused — at Off and Relaxed a skill's set-up line may run `bash -c`, and the tier is not immune to the agent. safe-ai-skill, when on, also refuses `.env` and its variants to the file tools and `cat`-style reads at every tier; `grep`, `awk` and inline interpreters pass it.
- ## Full documentation
- [`docs/`](docs/) is the kit's full spec. It is not copied into your project.
- | Document | What it covers |
- |----------|----------------|
- | [install.md](docs/install.md) | Every install route in full, pinning a release, `--agents`, the no-install route, GitHub template, updating |
- | [firewall.md](docs/firewall.md) | Permission and safety gates, tier generation, and the limits of all of it |
- | [agents-and-commands.md](docs/agents-and-commands.md) | All 15 agents with their models, all 54 commands and how the agent workflow chains, agent teams, and the [report pages](docs/agents-and-commands.md#how-the-agent-workflow-chains): the local HTML pages `/report` and `/decide` write to `.claude/reports/` with `.claude/bin/report-page.sh` |
- | [skill-packs.md](docs/skill-packs.md) | The pinned `ext/` packs, core vs extension, the opt-in add-on registry |
- | [other-agents.md](docs/other-agents.md) | Codex, Grok Build, Cursor, Gemini CLI, opencode: what each one actually enforces |
- | [configuration.md](docs/configuration.md) | MCP servers including the opt-in ones, secrets with varlock, the standard plugins and the optional ones with what each costs per session, and the settings the kit leaves to you |
- | [decisions.md](docs/decisions.md) | The decision record, the hooks that hand the decisions in force to every agent, the check on what the kit's agents report back, and the guard that keeps the record your main session's |
- | [plugin.md](docs/plugin.md) | The plugin route and why it is not recommended |
- | [design.md](docs/design.md) | Why the always-on context is small, and the 2026 stack |
- | [repo-structure.md](docs/repo-structure.md) | Repository layout, DX scripts, the GitHub Action, branch and review workflow |
- [QUICK-START.md](QUICK-START.md) is the two-minute version with usage examples per task. [FIREWALL-SPEC.md](FIREWALL-SPEC.md) is the verified spec behind the tiers.
- ## License
- MIT - See [LICENSE](LICENSE)
- ## Disclaimer
- **No warranty, and no liability.** This software is provided "as is", without warranty of any kind, express or implied, including without limitation the warranties of merchantability, fitness for a particular purpose and non-infringement. To the fullest extent permitted by applicable law, Superteam Brazil, its members and the contributors to this repository accept no liability for any claim, loss or damage — direct, indirect, incidental, special, consequential or exemplary, including loss of funds, keys, data, profits or goodwill — arising from or in connection with this software or its use, whether in contract, tort, negligence or otherwise, and whether or not advised of the possibility of such damage. You install and run it on your own systems, against your own keys, accounts and funds, and every action it helps you take remains your decision and your responsibility. Review what it does before you run it, especially anything that touches mainnet or moves value.
- **What this repository contains, and what it does not.** This is a configuration layer and an index. It contains Superteam Brazil's own work — the agents, commands, skills, rules, hooks and settings written here — together with references to third-party projects. Those third-party projects are identified by their canonical repository URL and a recorded commit, and they are retrieved directly from their own publishers at install time, by the same public mechanisms any user would use unaided: `git submodule`, `git clone`, `npx`, or a first-party plugin marketplace. Third-party code is not rehosted, mirrored, bundled, modified or redistributed by this repository, and none of it is served from here. Removing a reference removes nothing but the reference.
- **Ownership, attribution and independence.** Every referenced project remains the property of its own authors and is governed exclusively by the terms its authors attach to it, which travel with the project when it is retrieved. Nothing here asserts ownership of, or claims credit for, any third-party work, and no part of the wider stack is presented as this project's own. Inclusion is not endorsement in either direction: no affiliation with, sponsorship by, or approval from any referenced project, protocol, company or foundation is claimed or implied. Product names, trademarks and logos belong to their respective owners and appear only to identify the software they refer to, as nominative reference.
- **No charge.** This repository is distributed free of charge. Nothing in it is sold, rented, licensed for a fee or placed behind a paywall, no payment is solicited or accepted for access to it, and no revenue is derived from the third-party projects it references.
- **Maintainer requests.** If you maintain a project referenced here and would like the reference amended, attributed differently, or removed, open an issue in this repository and it will be actioned.
.claude/settings.json · Bundled script · 955 lines · 17 findings marked
- {
- "sandbox": {
- "enabled": true,
- "excludedCommands": [
- "surfpool *",
- "anchor test*",
- "git push *",
- "git pull *",
- "git fetch *",
- "gh pr *",
- "gh run *",
- "gh issue *"
- ],
- "network": {
- "allowLocalBinding": true,
- "deniedDomains": [
- "requestbin.com",
- Dismissed after review: Mentions a known data-relay/testing domain (requestbin.com) without linking or sending anything to it
- Line 17 on GitHub
- "*.requestbin.com",
- Dismissed after review: Mentions a known data-relay/testing domain (requestbin.com) without linking or sending anything to it
- Line 18 on GitHub
- "pipedream.net",
- "*.pipedream.net",
- "webhook.site",
- Dismissed after review: Mentions a known data-relay/testing domain (webhook.site) without linking or sending anything to it
- Line 21 on GitHub
- "*.webhook.site",
- Dismissed after review: Mentions a known data-relay/testing domain (webhook.site) without linking or sending anything to it
- Line 22 on GitHub
- "requestcatcher.com",
- "*.requestcatcher.com",
- "beeceptor.com",
- Dismissed after review: Mentions a known data-relay/testing domain (beeceptor.com) without linking or sending anything to it
- Line 25 on GitHub
- "*.beeceptor.com",
- Dismissed after review: Mentions a known data-relay/testing domain (beeceptor.com) without linking or sending anything to it
- Line 26 on GitHub
- "hookb.in",
- "*.hookb.in",
- "typedwebhook.tools",
- "burpcollaborator.net",
- Dismissed after review: Mentions a known data-relay/testing domain (burpcollaborator.net) without linking or sending anything to it
- Line 30 on GitHub
- "*.burpcollaborator.net",
- Dismissed after review: Mentions a known data-relay/testing domain (burpcollaborator.net) without linking or sending anything to it
- Line 31 on GitHub
- "oast.fun",
- Dismissed after review: Mentions a known data-relay/testing domain (oast.fun) without linking or sending anything to it
- Line 32 on GitHub
- "*.oast.fun",
- Dismissed after review: Mentions a known data-relay/testing domain (oast.fun) without linking or sending anything to it
- Line 33 on GitHub
- "oastify.com",
- Warning: Mentions a known data-relay/testing domain (oastify.com) without linking or sending anything to it
- Line 34 on GitHub
- "*.oastify.com",
- Warning: Mentions a known data-relay/testing domain (oastify.com) without linking or sending anything to it
- Line 35 on GitHub
- "interact.sh",
- "*.interact.sh",
- "dnslog.cn",
- Warning: Mentions a known data-relay/testing domain (dnslog.cn) without linking or sending anything to it
- Line 38 on GitHub
- "*.dnslog.cn",
- Warning: Mentions a known data-relay/testing domain (dnslog.cn) without linking or sending anything to it
- Line 39 on GitHub
- "canarytokens.com",
- "*.canarytokens.com",
- "ngrok.io",
- "*.ngrok.io",
- "ngrok.app",
- "*.ngrok.app",
- "ngrok-free.app",
- "*.ngrok-free.app",
- "trycloudflare.com",
- "*.trycloudflare.com",
- "loca.lt",
- "*.loca.lt",
- "localtunnel.me",
- "*.localtunnel.me",
- "serveo.net",
- "*.serveo.net",
- "tunnelmole.net",
- "*.tunnelmole.net",
- "pagekite.me",
- "*.pagekite.me",
- "pastebin.com",
- "*.pastebin.com",
- "paste.ee",
- "hastebin.com",
- "dpaste.com",
- "dpaste.org",
- "glot.io",
- "ix.io",
- "sprunge.us",
- "termbin.com",
- "0x0.st",
- "x0.at",
- "envs.sh",
- "transfer.sh",
- "file.io",
- "oshi.at",
- "bashupload.com",
- "keep.sh",
- "temp.sh",
- "gofile.io",
- "*.gofile.io",
- "anonfiles.com",
- "catbox.moe",
- "*.catbox.moe",
- "uguu.se",
- "tmpfiles.org",
- "*.tmpfiles.org"
- ]
- },
- "filesystem": {
- "denyRead": [
- "~/.ssh",
- "~/.gnupg",
- "~/.aws",
- "~/.config/solana/id.json",
- "~/.claude/.credentials.json",
- "~/Library/Keychains",
- "/Library/Keychains",
- "~/.local/share/keyrings",
- "~/.gnome2/keyrings",
- "~/.password-store",
- "~/.config/1Password",
- "~/.config/Bitwarden",
- "~/.config/keepassxc",
- "~/Library/Application Support/Google/Chrome",
- "~/Library/Application Support/BraveSoftware/Brave-Browser",
- "~/Library/Application Support/Microsoft Edge",
- "~/Library/Application Support/Firefox",
- "~/Library/Application Support/Chromium",
- "~/Library/Application Support/Vivaldi",
- "~/Library/Application Support/Arc",
- "~/Library/Application Support/com.operasoftware.Opera",
- "~/.config/google-chrome",
- "~/.config/BraveSoftware/Brave-Browser",
- "~/.config/microsoft-edge",
- "~/.mozilla/firefox",
- "~/.config/chromium",
- "~/.config/vivaldi",
- "~/.config/opera",
- "~/AppData/Local/Google/Chrome/User Data",
- "~/AppData/Local/BraveSoftware/Brave-Browser/User Data",
- "~/AppData/Local/Microsoft/Edge/User Data",
- "~/AppData/Roaming/Mozilla/Firefox",
- "~/AppData/Local/Chromium/User Data",
- "~/AppData/Local/Vivaldi/User Data",
- "~/AppData/Roaming/Opera Software",
- "~/.zsh_history",
- "~/.zhistory",
- "~/.bash_history",
- "~/.local/share/fish/fish_history",
- "~/.config/fish/fish_history",
- "~/.python_history",
- "~/.node_repl_history",
- "~/.psql_history",
- "~/.sqlite_history",
- "~/.lesshst"
- ],
- "denyWrite": [
- "~/.ssh",
- "~/.gnupg",
- "~/.aws",
- "~/.config/solana/id.json",
- "~/.claude/.credentials.json",
- "~/Library/Keychains",
- "/Library/Keychains",
- "~/.local/share/keyrings",
- "~/.gnome2/keyrings",
- "~/.password-store",
- "~/.config/1Password",
- "~/.config/Bitwarden",
- "~/.config/keepassxc",
- "~/.netrc",
- "~/.git-credentials",
- "~/.npmrc",
- "~/.cargo/credentials",
- "~/.cargo/credentials.toml",
- "~/.docker/config.json",
- "~/.config/gh/hosts.yml",
- "~/.kube/config",
- "~/.pypirc",
- "~/.gem/credentials",
- "~/Library/Application Support/Google/Chrome",
- "~/Library/Application Support/BraveSoftware/Brave-Browser",
- "~/Library/Application Support/Microsoft Edge",
- "~/Library/Application Support/Firefox",
- "~/Library/Application Support/Chromium",
- "~/Library/Application Support/Vivaldi",
- "~/Library/Application Support/Arc",
- "~/Library/Application Support/com.operasoftware.Opera",
- "~/.config/google-chrome",
- "~/.config/BraveSoftware/Brave-Browser",
- "~/.config/microsoft-edge",
- "~/.mozilla/firefox",
- "~/.config/chromium",
- "~/.config/vivaldi",
- "~/.config/opera",
- "~/AppData/Local/Google/Chrome/User Data",
- "~/AppData/Local/BraveSoftware/Brave-Browser/User Data",
- "~/AppData/Local/Microsoft/Edge/User Data",
- "~/AppData/Roaming/Mozilla/Firefox",
- "~/AppData/Local/Chromium/User Data",
- "~/AppData/Local/Vivaldi/User Data",
- "~/AppData/Roaming/Opera Software",
- "~/.cargo/config.toml",
- "~/.cargo/config",
- "~/.gitconfig",
- "~/.config/git/config",
- "~/.zshenv",
- "~/.zshrc",
- "~/.zprofile",
- "~/.zlogin",
- "~/.bashrc",
- "~/.bash_profile",
- "~/.profile",
- "~/.config/fish/config.fish",
- "~/.config/fish/conf.d",
- "~/Library/LaunchAgents",
- "/Library/LaunchAgents",
- "/Library/LaunchDaemons",
- "~/.config/autostart",
- "~/.zsh_history",
- "~/.zhistory",
- "~/.bash_history",
- "~/.local/share/fish/fish_history",
- "~/.config/fish/fish_history",
- "~/.python_history",
- "~/.node_repl_history",
- "~/.psql_history",
- "~/.sqlite_history",
- "~/.lesshst",
- "~/.claude/settings.json",
- "~/.claude/settings.local.json",
- "/Library/Application Support/ClaudeCode/managed-settings.json"
- ],
- "allowWrite": [
- ".",
- "/tmp",
- "/private/tmp",
- "/var/folders",
- "~/.cargo",
- "~/.rustup",
- "~/.cache",
- "~/.cache/solana",
- "~/.local/share/solana",
- "~/.avm",
- "~/.npm",
- "~/.anchor",
- "~/.config/solana",
- "~/Library/Caches",
- ".git"
- ]
- }
- },
- "extraKnownMarketplaces": {
- "stbr": {
- "source": {
- "source": "git",
- "url": "https://github.com/solanabr/ai-kit.git"
- }
- }
- },
- "enabledPlugins": {
- "safe-ai-skill@stbr": true
- },
- "attribution": {
- "commit": "",
- "pr": ""
- },
- "permissions": {
- "allow": [
- "Bash(git -c core.fsmonitor=false status *)",
- "Bash(git -c core.fsmonitor=false diff *)",
- "Bash(git -c core.fsmonitor=false log *)",
- "Bash(git -c core.fsmonitor=false show *)",
- "Bash(git -c core.fsmonitor=false add *)",
- "Bash(git -c core.fsmonitor=false commit *)",
- "Bash(git -c core.fsmonitor=false push *)",
- "Bash(git -c core.fsmonitor=false pull *)",
- "Bash(git -c core.fsmonitor=false fetch *)",
- "Bash(git -c core.fsmonitor=false branch *)",
- "Bash(git -c core.fsmonitor=false checkout *)",
- "Bash(git -c core.fsmonitor=false switch *)",
- "Bash(git -c core.fsmonitor=false merge *)",
- "Bash(git -c core.fsmonitor=false rebase *)",
- "Bash(git -c core.fsmonitor=false stash *)",
- "Bash(git -c core.fsmonitor=false tag *)",
- "Bash(git -c core.fsmonitor=false remote *)",
- "Bash(git -c core.fsmonitor=false submodule *)",
- "Bash(git -c core.fsmonitor=false blame *)",
- "Bash(git -c core.fsmonitor=false cherry-pick *)",
- "Bash(git -c core.hooksPath=/dev/null status *)",
- "Bash(git -c core.hooksPath=/dev/null diff *)",
- "Bash(git -c core.hooksPath=/dev/null log *)",
- "Bash(git -c core.hooksPath=/dev/null show *)",
- "Bash(git -c core.hooksPath=/dev/null add *)",
- "Bash(git -c core.hooksPath=/dev/null commit *)",
- "Bash(git -c core.hooksPath=/dev/null push *)",
- "Bash(git -c core.hooksPath=/dev/null pull *)",
- "Bash(git -c core.hooksPath=/dev/null fetch *)",
- "Bash(git -c core.hooksPath=/dev/null branch *)",
- "Bash(git -c core.hooksPath=/dev/null checkout *)",
- "Bash(git -c core.hooksPath=/dev/null switch *)",
- "Bash(git -c core.hooksPath=/dev/null merge *)",
- "Bash(git -c core.hooksPath=/dev/null rebase *)",
- "Bash(git -c core.hooksPath=/dev/null stash *)",
- "Bash(git -c core.hooksPath=/dev/null tag *)",
- "Bash(git -c core.hooksPath=/dev/null remote *)",
- "Bash(git -c core.hooksPath=/dev/null submodule *)",
- "Bash(git -c core.hooksPath=/dev/null blame *)",
- "Bash(git -c core.hooksPath=/dev/null cherry-pick *)",
- "Bash(anchor *)",
- "Bash(cargo build*)",
- "Bash(cargo test*)",
- "Bash(cargo clippy *)",
- "Bash(cargo fmt *)",
- "Bash(cargo audit *)",
- "Bash(cargo install *)",
- "Bash(cargo geiger *)",
- "Bash(cargo check *)",
- "Bash(cargo doc *)",
- "Bash(cargo run *)",
- "Bash(cargo add *)",
- "Bash(cargo remove *)",
- "Bash(cargo update *)",
- "Bash(cargo clean *)",
- "Bash(cargo bench *)",
- "Bash(cargo fix *)",
- "Bash(cargo tree *)",
- "Bash(cargo metadata *)",
- "Bash(rustup *)",
- "Bash(rustfmt *)",
- "Bash(trident *)",
- "Bash(solana config *)",
- "Bash(solana address *)",
- "Bash(solana balance *)",
- "Bash(solana airdrop *)",
- "Bash(solana program show *)",
- "Bash(solana program dump *)",
- "Bash(solana logs *)",
- "Bash(solana account *)",
- "Bash(solana cluster-version *)",
- "Bash(solana epoch-info *)",
- "Bash(solana slot *)",
- "Bash(solana rent *)",
- "Bash(solana decode *)",
- "Bash(solana transaction-history *)",
- "Bash(solana confirm *)",
- "Bash(solana-keygen *)",
- "Bash(solana-test-validator *)",
- "Bash(surfpool *)",
- "Bash(npm *)",
- "Bash(yarn *)",
- "Bash(pnpm *)",
- "Bash(bun *)",
- "Bash(npx *)",
- "Bash(node *)",
- "Bash(tsx *)",
- "Bash(tsc *)",
- "Bash(next *)",
- "Bash(vite *)",
- "Bash(vitest *)",
- "Bash(prettier *)",
- "Bash(eslint *)",
- "Bash(create-solana-dapp *)",
- "Bash(git status *)",
- "Bash(git diff *)",
- "Bash(git log *)",
- "Bash(git show *)",
- "Bash(git add *)",
- "Bash(git commit *)",
- "Bash(git push *)",
- "Bash(git pull *)",
- "Bash(git fetch *)",
- "Bash(git branch *)",
- "Bash(git checkout *)",
- "Bash(git switch *)",
- "Bash(git merge *)",
- "Bash(git rebase *)",
- "Bash(git stash *)",
- "Bash(git tag *)",
- "Bash(git remote *)",
- "Bash(git submodule *)",
- "Bash(git blame *)",
- "Bash(git cherry-pick *)",
- "Bash(gh *)",
- "Bash(ls *)",
- "Bash(cat *)",
- "Bash(head *)",
- "Bash(tail *)",
- "Bash(grep *)",
- "Bash(rg *)",
- "Bash(find *)",
- "Bash(fd *)",
- "Bash(mkdir *)",
- "Bash(touch *)",
- "Bash(echo *)",
- "Bash(printf *)",
- "Bash(pwd)",
- "Bash(cd *)",
- "Bash(cp *)",
- "Bash(mv *)",
- "Bash(wc *)",
- "Bash(sort *)",
- "Bash(uniq *)",
- "Bash(diff *)",
- "Bash(tree *)",
- "Bash(which *)",
- "Bash(command -v *)",
- "Bash(type *)",
- "Bash(export *)",
- "Bash(date *)",
- "Bash(basename *)",
- "Bash(dirname *)",
- "Bash(realpath *)",
- "Bash(readlink *)",
- "Bash(xargs grep *)",
- "Bash(xargs rg *)",
- "Bash(xargs wc *)",
- "Bash(xargs ls *)",
- "Bash(xargs -0 grep *)",
- "Bash(sed *)",
- "Bash(awk *)",
- "Bash(cut *)",
- "Bash(tr *)",
- "Bash(tee *)",
- "Bash(jq *)",
- "Bash(curl *)",
- "Bash(wget *)",
- "Bash(tar *)",
- "Bash(unzip *)",
- "Bash(du *)",
- "Bash(df *)",
- "Bash(file *)",
- "Bash(stat *)",
- "Bash(sha256sum *)",
- "Bash(md5sum *)",
- "Bash(base64 *)",
- "Bash(openssl *)",
- "Bash(docker build *)",
- "Bash(docker run *)",
- "Bash(docker compose *)",
- "Bash(docker ps *)",
- "Bash(docker logs *)",
- "Bash(docker images *)",
- "Bash(docker stop *)",
- "Bash(docker inspect *)",
- "Bash(unity-editor *)",
- "Bash(dotnet *)",
- "Bash(nuget *)",
- "Bash(python *)",
- "Bash(python3 *)",
- "Bash(pip *)",
- "Bash(pip3 *)",
- "Bash(avm *)",
- "Bash(solana-verify *)",
- "Bash(mollusk *)",
- "Bash(litesvm *)",
- "Bash(spl-token *)",
- "Bash(just *)",
- "Bash(make *)",
- "Bash(cmake *)",
- "Bash(wasm-pack *)",
- "Bash(cross *)",
- "Bash(cargo-generate *)",
- "Bash(solana-install *)",
- "Bash(bash .claude/bin/skills.sh list)",
- "Bash(bash .claude/bin/skills.sh add *)",
- "Bash(bash .claude/bin/decisions.sh *)",
- "Bash(bash .claude/bin/report-page.sh *)",
- "Read(*)",
- "Edit(*)",
- "Write(*)",
- "Glob(*)",
- "Grep(*)",
- "Agent(*)",
- "WebFetch(*)",
- "WebSearch(*)"
- ],
- "deny": [
- "Bash(git -c core.fsmonitor=false clean *)",
- "Bash(git -c core.fsmonitor=false clean)",
- "Bash(git -c core.fsmonitor=false restore *)",
- "Bash(git -c core.fsmonitor=false restore)",
- "Bash(git -c core.fsmonitor=false checkout -- *)",
- "Bash(git -c core.fsmonitor=false checkout --)",
- "Bash(git -c core.fsmonitor=false reset *--ha*)",
- "Bash(git -c core.fsmonitor=false reset --ha*)",
- "Bash(git -c core.fsmonitor=false gc *--prune*)",
- "Bash(git -c core.fsmonitor=false gc --prune*)",
- "Bash(git -c core.fsmonitor=false prune *)",
- "Bash(git -c core.fsmonitor=false prune)",
- "Bash(git -c core.fsmonitor=false reflog expire *)",
- "Bash(git -c core.fsmonitor=false reflog expire)",
- "Bash(git -c core.fsmonitor=false reflog delete *)",
- "Bash(git -c core.fsmonitor=false reflog delete)",
- "Bash(git -c core.fsmonitor=false reflog drop *)",
- "Bash(git -c core.fsmonitor=false reflog drop)",
- "Bash(git -c core.fsmonitor=false push *--mirror*)",
- "Bash(git -c core.fsmonitor=false push --mirror*)",
- "Bash(git -c core.fsmonitor=false push *--receive-pack*)",
- "Bash(git -c core.fsmonitor=false push --receive-pack*)",
- "Bash(git -c core.fsmonitor=false push *--exec*)",
- "Bash(git -c core.fsmonitor=false push --exec*)",
- "Bash(git -c core.fsmonitor=false pull *--upload-pack*)",
- "Bash(git -c core.fsmonitor=false pull --upload-pack*)",
- "Bash(git -c core.fsmonitor=false fetch *--upload-pack*)",
- "Bash(git -c core.fsmonitor=false fetch --upload-pack*)",
- "Bash(git -c core.fsmonitor=false clone *--upload-pack*)",
- "Bash(git -c core.fsmonitor=false clone --upload-pack*)",
- "Bash(git -c core.fsmonitor=false ls-remote *--upload-pack*)",
- "Bash(git -c core.fsmonitor=false ls-remote --upload-pack*)",
- "Bash(git -c core.fsmonitor=false --config-env*)",
- "Bash(git -c core.fsmonitor=false --exec-path=*)",
- "Bash(git -c core.fsmonitor=false config *alias.*)",
- "Bash(git -c core.fsmonitor=false config alias.*)",
- "Bash(git -c core.hooksPath=/dev/null clean *)",
- "Bash(git -c core.hooksPath=/dev/null clean)",
- "Bash(git -c core.hooksPath=/dev/null restore *)",
- "Bash(git -c core.hooksPath=/dev/null restore)",
- "Bash(git -c core.hooksPath=/dev/null checkout -- *)",
- "Bash(git -c core.hooksPath=/dev/null checkout --)",
- "Bash(git -c core.hooksPath=/dev/null reset *--ha*)",
- "Bash(git -c core.hooksPath=/dev/null reset --ha*)",
- "Bash(git -c core.hooksPath=/dev/null gc *--prune*)",
- "Bash(git -c core.hooksPath=/dev/null gc --prune*)",
- "Bash(git -c core.hooksPath=/dev/null prune *)",
- "Bash(git -c core.hooksPath=/dev/null prune)",
- "Bash(git -c core.hooksPath=/dev/null reflog expire *)",
- "Bash(git -c core.hooksPath=/dev/null reflog expire)",
- "Bash(git -c core.hooksPath=/dev/null reflog delete *)",
- "Bash(git -c core.hooksPath=/dev/null reflog delete)",
- "Bash(git -c core.hooksPath=/dev/null reflog drop *)",
- "Bash(git -c core.hooksPath=/dev/null reflog drop)",
- "Bash(git -c core.hooksPath=/dev/null push *--mirror*)",
- "Bash(git -c core.hooksPath=/dev/null push --mirror*)",
- "Bash(git -c core.hooksPath=/dev/null push *--receive-pack*)",
- "Bash(git -c core.hooksPath=/dev/null push --receive-pack*)",
- "Bash(git -c core.hooksPath=/dev/null push *--exec*)",
- "Bash(git -c core.hooksPath=/dev/null push --exec*)",
- "Bash(git -c core.hooksPath=/dev/null pull *--upload-pack*)",
- "Bash(git -c core.hooksPath=/dev/null pull --upload-pack*)",
- "Bash(git -c core.hooksPath=/dev/null fetch *--upload-pack*)",
- "Bash(git -c core.hooksPath=/dev/null fetch --upload-pack*)",
- "Bash(git -c core.hooksPath=/dev/null clone *--upload-pack*)",
- "Bash(git -c core.hooksPath=/dev/null clone --upload-pack*)",
- "Bash(git -c core.hooksPath=/dev/null ls-remote *--upload-pack*)",
- "Bash(git -c core.hooksPath=/dev/null ls-remote --upload-pack*)",
- "Bash(git -c core.hooksPath=/dev/null --config-env*)",
- "Bash(git -c core.hooksPath=/dev/null --exec-path=*)",
- "Bash(git -c core.hooksPath=/dev/null config *alias.*)",
- "Bash(git -c core.hooksPath=/dev/null config alias.*)",
- "Edit(/.claude/hooks/**)",
- "Edit(~/.claude/hooks/**)",
- "Bash(claude *--dangerously-skip-permissions*)",
- "Bash(claude *--permission-mode*)",
- "Bash(claude *--permission-prompt-tool*)",
- "Bash(claude *--settings*)",
- "Bash(claude *--setting-sources*)",
- "Bash(claude *--allowedTools*)",
- "Bash(claude *--allowed-tools*)",
- "Bash(claude *--add-dir*)",
- "Bash(claude *--mcp-config*)",
- "Bash(claude *--plugin-dir*)",
- "Bash(claude *--plugin-url*)",
- "Bash(claude mcp add*)",
- "Bash(claude setup-token*)",
- "Edit(//**/managed-settings.json)",
- "Edit(/.safe-ai-skill/**)",
- "Read(~/.ssh)",
- "Read(~/.ssh/**)",
- "Read(~/.gnupg)",
- "Read(~/.gnupg/**)",
- "Read(~/.aws)",
- "Read(~/.aws/**)",
- "Read(~/.config/solana/id.json)",
- "Read(~/.npmrc)",
- "Read(~/.git-credentials)",
- "Read(~/.netrc)",
- "Read(~/.kube/config)",
- "Read(~/.cargo/credentials)",
- "Read(~/.cargo/credentials.toml)",
- "Read(~/.docker/config.json)",
- "Read(~/.pypirc)",
- "Read(~/.gem/credentials)",
- "Read(~/.claude/.credentials.json)",
- "Read(~/.local/share/keyrings)",
- "Read(~/.local/share/keyrings/**)",
- "Read(~/.gnome2/keyrings)",
- "Read(~/.gnome2/keyrings/**)",
- "Read(~/.password-store)",
- "Read(~/.password-store/**)",
- "Read(~/.config/1Password)",
- "Read(~/.config/1Password/**)",
- "Read(~/Library/Application Support/Bitwarden)",
- "Read(~/Library/Application Support/Bitwarden/**)",
- "Read(~/.config/Bitwarden)",
- "Read(~/.config/Bitwarden/**)",
- "Read(~/.config/keepassxc)",
- "Read(~/.config/keepassxc/**)",
- "Read(~/Library/Application Support/Google/Chrome)",
- "Read(~/Library/Application Support/Google/Chrome/**)",
- "Read(~/Library/Application Support/BraveSoftware/Brave-Browser)",
- "Read(~/Library/Application Support/BraveSoftware/Brave-Browser/**)",
- "Read(~/Library/Application Support/Microsoft Edge)",
- "Read(~/Library/Application Support/Microsoft Edge/**)",
- "Read(~/Library/Application Support/Firefox)",
- "Read(~/Library/Application Support/Firefox/**)",
- "Read(~/Library/Application Support/Chromium)",
- "Read(~/Library/Application Support/Chromium/**)",
- "Read(~/Library/Application Support/Vivaldi)",
- "Read(~/Library/Application Support/Vivaldi/**)",
- "Read(~/Library/Application Support/Arc)",
- "Read(~/Library/Application Support/Arc/**)",
- "Read(~/Library/Application Support/com.operasoftware.Opera)",
- "Read(~/Library/Application Support/com.operasoftware.Opera/**)",
- "Read(~/.config/google-chrome)",
- "Read(~/.config/google-chrome/**)",
- "Read(~/.config/BraveSoftware/Brave-Browser)",
- "Read(~/.config/BraveSoftware/Brave-Browser/**)",
- "Read(~/.config/microsoft-edge)",
- "Read(~/.config/microsoft-edge/**)",
- "Read(~/.mozilla/firefox)",
- "Read(~/.mozilla/firefox/**)",
- "Read(~/.config/chromium)",
- "Read(~/.config/chromium/**)",
- "Read(~/.config/vivaldi)",
- "Read(~/.config/vivaldi/**)",
- "Read(~/.config/opera)",
- "Read(~/.config/opera/**)",
- "Read(~/AppData/Local/Google/Chrome/User Data)",
- "Read(~/AppData/Local/Google/Chrome/User Data/**)",
- "Read(~/AppData/Local/BraveSoftware/Brave-Browser/User Data)",
- "Read(~/AppData/Local/BraveSoftware/Brave-Browser/User Data/**)",
- "Read(~/AppData/Local/Microsoft/Edge/User Data)",
- "Read(~/AppData/Local/Microsoft/Edge/User Data/**)",
- "Read(~/AppData/Roaming/Mozilla/Firefox)",
- "Read(~/AppData/Roaming/Mozilla/Firefox/**)",
- "Read(~/AppData/Local/Chromium/User Data)",
- "Read(~/AppData/Local/Chromium/User Data/**)",
- "Read(~/AppData/Local/Vivaldi/User Data)",
- "Read(~/AppData/Local/Vivaldi/User Data/**)",
- "Read(~/AppData/Roaming/Opera Software)",
- "Read(~/AppData/Roaming/Opera Software/**)",
- "Read(~/**/Local Extension Settings)",
- "Read(~/**/Local Extension Settings/**)",
- "Edit(~/.cargo/config.toml)",
- "Edit(~/.cargo/config)",
- "Edit(**/.cargo/config.toml)",
- "Edit(~/.gitconfig)",
- "Edit(~/.config/git/config)",
- "Edit(~/.zshenv)",
- "Edit(~/.zshrc)",
- "Edit(~/.zprofile)",
- "Edit(~/.zlogin)",
- "Edit(~/.bashrc)",
- "Edit(~/.bash_profile)",
- "Edit(~/.profile)",
- "Edit(~/.config/fish/config.fish)",
- "Edit(~/.config/fish/conf.d/**)",
- "Edit(~/Library/LaunchAgents)",
- "Edit(~/Library/LaunchAgents/**)",
- "Edit(//Library/LaunchAgents)",
- "Edit(//Library/LaunchAgents/**)",
- "Edit(//Library/LaunchDaemons)",
- "Edit(//Library/LaunchDaemons/**)",
- "Edit(~/.config/autostart)",
- "Edit(~/.config/autostart/**)",
- "Read(~/.zsh_history)",
- "Read(~/.zhistory)",
- "Read(~/.bash_history)",
- "Read(~/.local/share/fish/fish_history)",
- "Read(~/.config/fish/fish_history)",
- "Read(~/.python_history)",
- "Read(~/.node_repl_history)",
- "Read(~/.psql_history)",
- "Read(~/.sqlite_history)",
- "Read(~/.lesshst)",
- "Bash(cat *id.json)",
- "Bash(cat *keypair*.json)",
- "Bash(cat keypair*.json)",
- "Bash(cat *keypair.json)",
- "Bash(cat ~/.ssh/*)",
- "Bash(cat ~/.config/solana/*.json)",
- "Bash(cat ~/.aws/*)",
- "Bash(cat ~/.gnupg/*)",
- "Bash(cat *.pem)",
- "Bash(cat ~/.config/gh/hosts.yml)",
- "Bash(cat ~/.npmrc)",
- "Bash(cat ~/.git-credentials)",
- "Bash(cat ~/.netrc)",
- "Bash(cat ~/.cargo/credentials*)",
- "Bash(cat ~/.claude/.credentials.json)",
- "Bash(less *id.json)",
- "Bash(xxd *id.json)",
- "Bash(gh auth token *)",
- "Bash(env *)",
- "Bash(sh -c *)",
- "Bash(bash -lc *)",
- "Bash(zsh -c *)",
- "Bash(dash -c *)",
- "Bash(ksh -c *)",
- "Bash(git --config-env*)",
- "Bash(git --exec-path=*)",
- "Bash(git config *alias.*)",
- "Bash(git config alias.*)",
- "Bash(flock *)",
- "Bash(watch *)",
- "Bash(setsid *)",
- "Bash(ionice *)",
- "Bash(devbox run *)",
- "Bash(direnv exec *)",
- "Bash(mise exec *)",
- "Bash(docker exec *)",
- "Bash(security *)",
- "Bash(/usr/bin/security *)",
- "Bash(crontab*)",
- "Bash(launchctl *)",
- "Bash(defaults *)",
- "Bash(gh alias *)",
- "Bash(sudo *)",
- "Bash(rm -rf /)",
- Warning: Runs `rm -rf` against a root or home-directory path
- Line 734 on GitHub
- "Bash(rm -rf ~)",
- Warning: Runs `rm -rf` against a root or home-directory path
- Line 735 on GitHub
- "Bash(rm -rf ~/)",
- Warning: Runs `rm -rf` against a root or home-directory path
- Line 736 on GitHub
- "Bash(rm -rf .)",
- "Bash(rm -rf ..)",
- "Bash(rm -rf .git)",
- "Bash(rm -rf .git/*)",
- "Bash(rm -rf /\\* *)",
- "Bash(rm -rf ~/\\* *)",
- "Bash(rm -rf \\* *)",
- "Bash(rm -rf .\\* *)",
- "Bash(chmod 777 *)",
- "Bash(chmod -R 777 *)",
- "Bash(chown *)",
- "Bash(mkfs*)",
- "Bash(dd *)",
- "Bash(shutdown *)",
- "Bash(reboot *)",
- "Bash(git clean *)",
- "Bash(git restore *)",
- "Bash(git checkout -- *)",
- "Bash(git reset *--ha*)",
- "Bash(git reset --ha*)",
- "Bash(git gc *--prune*)",
- "Bash(git gc --prune*)",
- "Bash(git prune *)",
- "Bash(git reflog expire *)",
- "Bash(git reflog delete *)",
- "Bash(git reflog drop *)",
- "Bash(git push *--mirror*)",
- "Bash(git push --mirror*)",
- "Bash(git -C * clean *)",
- "Bash(git -C * clean)",
- "Bash(git -C * restore *)",
- "Bash(git -C * restore)",
- "Bash(git -C * checkout -- *)",
- "Bash(git -C * checkout --)",
- "Bash(git -C * reset *--ha*)",
- "Bash(git -C * reset --ha*)",
- "Bash(git -C * gc *--prune*)",
- "Bash(git -C * gc --prune*)",
- "Bash(git -C * prune *)",
- "Bash(git -C * prune)",
- "Bash(git -C * reflog expire *)",
- "Bash(git -C * reflog expire)",
- "Bash(git -C * reflog delete *)",
- "Bash(git -C * reflog delete)",
- "Bash(git -C * reflog drop *)",
- "Bash(git -C * reflog drop)",
- "Bash(git -C * push *--mirror*)",
- "Bash(git -C * push --mirror*)",
- "Bash(git -C * push *--receive-pack*)",
- "Bash(git -C * push --receive-pack*)",
- "Bash(git -C * push *--exec*)",
- "Bash(git -C * push --exec*)",
- "Bash(git -C * pull *--upload-pack*)",
- "Bash(git -C * pull --upload-pack*)",
- "Bash(git -C * fetch *--upload-pack*)",
- "Bash(git -C * fetch --upload-pack*)",
- "Bash(git -C * clone *--upload-pack*)",
- "Bash(git -C * clone --upload-pack*)",
- "Bash(git -C * ls-remote *--upload-pack*)",
- "Bash(git -C * ls-remote --upload-pack*)",
- "Bash(git -C * --config-env*)",
- "Bash(git -C * --exec-path=*)",
- "Bash(git -C * config *alias.*)",
- "Bash(git -C * config alias.*)",
- "Bash(git push *--receive-pack*)",
- "Bash(git push --receive-pack*)",
- "Bash(git push *--exec*)",
- "Bash(git push --exec*)",
- "Bash(git pull *--upload-pack*)",
- "Bash(git pull --upload-pack*)",
- "Bash(git fetch *--upload-pack*)",
- "Bash(git fetch --upload-pack*)",
- "Bash(git clone *--upload-pack*)",
- "Bash(git clone --upload-pack*)",
- "Bash(git ls-remote *--upload-pack*)",
- "Bash(git ls-remote --upload-pack*)",
- "Bash(gh issue delete *)",
- "Bash(gh repo delete *)",
- "Bash(gh repo delete)",
- "Bash(solana program deploy *--final*)",
- "Bash(solana program deploy --final*)",
- "Bash(solana program set-upgrade-authority *--final*)",
- "Bash(solana program set-upgrade-authority --final*)",
- "Bash(anchor * --final*)",
- "Bash(anchor --final*)",
- "Bash(solana program close *--bypass-warning*)",
- "Bash(solana program close --bypass-warning*)",
- "Bash(solana program-v4 finalize *)",
- "Bash(spl-token authorize *--disable*)",
- "Bash(spl-token authorize --disable*)",
- "Bash(solana transfer *)",
- "Bash(solana close-vote-account *)",
- "Bash(solana authorize-nonce-account *)",
- "Bash(solana withdraw-from-nonce-account *)",
- "Bash(spl-token burn *)",
- "Bash(spl-token close *)",
- "Bash(solana config set *-k*)",
- "Bash(solana config set -k*)",
- "Bash(solana -* program deploy *--final*)",
- "Bash(solana -* program deploy --final*)",
- "Bash(solana -* program set-upgrade-authority *--final*)",
- "Bash(solana -* program set-upgrade-authority --final*)",
- "Bash(solana -* program close *--bypass-warning*)",
- "Bash(solana -* program close --bypass-warning*)",
- "Bash(solana -* program-v4 finalize *)",
- "Bash(solana -* program-v4 finalize)",
- "Bash(spl-token -* authorize *--disable*)",
- "Bash(spl-token -* authorize --disable*)",
- "Bash(solana -* transfer *)",
- "Bash(solana -* transfer)",
- "Bash(solana -* close-vote-account *)",
- "Bash(solana -* close-vote-account)",
- "Bash(solana -* authorize-nonce-account *)",
- "Bash(solana -* authorize-nonce-account)",
- "Bash(solana -* withdraw-from-nonce-account *)",
- "Bash(solana -* withdraw-from-nonce-account)",
- "Bash(spl-token -* burn *)",
- "Bash(spl-token -* burn)",
- "Bash(spl-token -* close *)",
- "Bash(spl-token -* close)",
- "Bash(solana -* config set *-k*)",
- "Bash(solana -* config set -k*)",
- "Bash(gh secret set *)",
- "Bash(gh variable set *)"
- ]
- },
- "hooks": {
- "SessionStart": [
- {
- "hooks": [
- {
- "type": "command",
- "command": "INPUT=$(cat)\nV=$(awk 'NF{print $NF; exit}' \"${CLAUDE_PROJECT_DIR:-.}/.claude/VERSION\" 2>/dev/null)\n[ -n \"$V\" ] || V=dev\nif command -v solana >/dev/null 2>&1; then\n RPC=$(solana config get json_rpc_url 2>/dev/null | awk '{print $NF}' | sed -E 's#^([a-z]+://[^/?]+).*#\\1#')\n WALLET=$(solana address 2>/dev/null) || WALLET='none configured'\n CTX=\"Solana CLI: RPC ${RPC:-unknown}, wallet ${WALLET:-none configured}.\"\n LINE=\"🔗 ${RPC:-unknown} 👛 ${WALLET:-none configured}\"\nelse\n CTX='Solana CLI not found on PATH.'\n LINE=$CTX\nfi\nSEC=\"${CLAUDE_PROJECT_DIR:-.}/.claude/security.json\"\nif [ -r \"$SEC\" ]; then\n TIERS=$(awk '\n /\"enforced\"/ { inenf = 1 }\n /\"tier\"[[:space:]]*:/ {\n t = $0; sub(/.*\"tier\"[^\"]*\"/, \"\", t); sub(/\".*/, \"\", t)\n if (inenf) { if (e == \"\") e = t } else if (d == \"\") d = t\n }\n END { print d \"|\" e }' \"$SEC\" 2>/dev/null)\n DT=${TIERS%%|*}; ET=${TIERS#*|}\n if [ -n \"$DT\" ] && [ \"$DT\" = \"$ET\" ]; then\n CTX=\"$CTX Firewall tier: $DT.\"\n elif [ -n \"$DT\" ]; then\n CTX=\"$CTX Firewall tier: $DT declared but ${ET:-none} enforced — the rules are stale; the user should run /firewall $DT and restart.\"\n fi\nfi\ncase $INPUT in *'\"startup\"'*) ;; *) printf '%s\\n' \"$CTX\"; exit 0 ;; esac\ncommand -v jq >/dev/null 2>&1 || { printf '%s\\n' \"$CTX\"; exit 0; }\nBANNER=$(printf '%s\\n' \\\n '' ' _____ ____ __ ___ _ _____' \\\n ' / ___// __ \\/ / / | / | / / |' \\\n ' \\__ \\/ / / / / / /| | / |/ / /| |' \\\n ' ___/ / /_/ / /___/ ___ |/ /| / ___ |' \\\n '/____/\\____/_____/_/ |_/_/ |_/_/ |_|' '' \\\n ' ▄▀█ █ █▄▀ █ ▀█▀' \\\n ' █▀█ █ █ █ █ █' '' \\\n \" v$V — by @SuperteamBR 🇧🇷\" '' \"$LINE\")\njq -n --arg b \"$BANNER\" --arg c \"$CTX\" '{systemMessage: $b, hookSpecificOutput: {hookEventName: \"SessionStart\", additionalContext: $c}}'",
- "timeout": 15
- }
- ]
- },
- {
- "hooks": [
- {
- "type": "command",
- "command": "H=\"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/decisions-inject.sh\"; [ -r \"$H\" ] && sh \"$H\"; exit 0",
- "timeout": 10
- }
- ]
- }
- ],
- "PreToolUse": [
- {
- "matcher": "Bash|mcp__context-mode__.*",
- "hooks": [
- {
- "type": "command",
- "command": "H=\"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/onchain-guard.sh\"; [ -r \"$H\" ] && exec sh \"$H\"; exit 0",
- "timeout": 10
- }
- ]
- },
- {
- "matcher": "Bash|mcp__context-mode__.*",
- "hooks": [
- {
- "type": "command",
- "command": "H=\"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/egress-guard.sh\"; [ -r \"$H\" ] && exec sh \"$H\"; exit 0",
- "timeout": 10
- }
- ]
- },
- {
- "matcher": "Bash|Write|Edit|MultiEdit|NotebookEdit|mcp__context-mode__.*",
- "hooks": [
- {
- "type": "command",
- "command": "H=\"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/decisions-guard.sh\"; [ -r \"$H\" ] && exec sh \"$H\"; exit 0",
- "timeout": 10
- }
- ]
- },
- {
- "hooks": [
- {
- "type": "command",
- "command": "H=\"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/decisions-push.sh\"; [ -r \"$H\" ] && sh \"$H\"; exit 0",
- "timeout": 5
- }
- ]
- }
- ],
- "SubagentStart": [
- {
- "hooks": [
- {
- "type": "command",
- "command": "H=\"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/decisions-inject.sh\"; [ -r \"$H\" ] && sh \"$H\"; exit 0",
- "timeout": 10
- }
- ]
- }
- ],
- "SubagentStop": [
- {
- "matcher": "^(solana-ai-kit:)?(anchor-engineer|defi-engineer|devops-engineer|game-architect|mobile-engineer|pinocchio-engineer|rust-backend-engineer|solana-architect|solana-frontend-engineer|solana-guide|solana-qa-engineer|solana-researcher|tech-docs-writer|token-engineer|unity-engineer)$",
- "hooks": [
- {
- "type": "command",
- "command": "H=\"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/decisions-report-check.sh\"; [ -r \"$H\" ] && sh \"$H\"; exit 0",
- "timeout": 10
- }
- ]
- }
- ]
- }
- }
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.