orchestkit
The Complete AI Development Toolkit - 115 skills, 36 agents, 47 commands, 163 hooks for full-stack development
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
Its scripts were only partly scanned.
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/yonatangross/orchestkit 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/yonatangross/orchestkit'
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/yonatangross-orchestkit)HTML
<a href="/listings/yonatangross-orchestkit"><img src="/api/listings/yonatangross-orchestkit/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.
Pick the host you actually use. Claude Code is the full plugin (skills + agents + hooks). Cursor gets the same `ork` plugin minus Claude hook scripts. skills.sh is skills only — start with the 12 below, not the whole catalog.
Host support matrix
Measured 2026-09-08 on pi 0.85, Codex CLI and cursor-agent. Details, commands and the lane model: [OrchestKit on pi, Codex and Cursor](https://orchestkit.dev/docs/guides/orchestkit-on-pi-codex-cursor). Antigravity measured 2026-09-18 on agy 1.2.6; full evidence in `docs/audits/agy-host-support-2026-09-18.md`.
| Host | Skills | Agents | Hooks | Install | Needs | |---|---|---|---|---|---| | Claude Code | 115 | 36 | 163 | plugin (CLI) | Claude Code 2.1.277 or newer | | Cursor | 115 | 36 | not yet (#4004) | plugin (Settings) | | | Codex | 9 | 4 roles | not yet (#4004) | ork-codex pack | | | Devin | 82 | ? | ? | plugin (git) | | | OpenCode | 12 | ? | ? | skills.sh | | | Muse Code | 12 | ? | ? | .agents/skills | | | Pi | 82 | ? | not yet (#4004) | pi manifest | | | Antigravity | 12 | ? | ? | .agents/skills | |
`?` means not measured yet, never zero. `not yet` means a tracked issue will bring it.
How each host wires the rest (measured, see the dates above):
| Surface | Claude Code | Cursor | Codex | pi | Devin | Antigravity | |---|---|---|---|---|---|---| | Rules | repo convention | 14, plugin `rules` key | `AGENTS.md` | none | `AGENTS.md`, always on | `AGENTS.md`, per-directory | | Commands | `/ork:<skill>` | 36 wrappers | `$ork-<skill>` | `/skill:<name>` | `/ork:<skill>` | `/<skill-name>`; `ork:<skill>` via plugin install | | MCP config | `.mcp.json` | `.cursor/mcp.json` | plugin `mcp.json` | `.pi/mcp.json` | `mcp.json` / `.mcp.json` | `~/.gemini/config/mcp_config.json` or plugin `mcp_config.json`; repo `.mcp.json` not read | | Status | shipped | shipped | shipped | shipped | skills only, GH-4146 | skills only, measured agy 1.2.6 |
Claude Code
/plugin marketplace add yonatangross/orchestkit /plugin install ork
Then `/ork:setup`. The wizard scans the repo, recommends skills, and writes MCP config.
CLI equivalent: `claude plugin marketplace add yonatangross/orchestkit && claude plugin install ork@orchestkit`.
Channels: `ork` is the stable channel, pinned to the latest release. `ork-alpha` is the same plugin tracking `main`, in the same marketplace (`claude plugin install ork-alpha@orchestkit`); use it only if you want changes before they are released.
Cursor
Settings → Plugins / marketplaces → add `yonatangross/orchestkit` → enable **ork** → **open a new chat**. Same plugin Claude Code installs, not a five-skill fork. See [Install → Cursor](#cursor).
skills.sh (Cursor, Codex, OpenCode, …)
Starter 12 from measured installs plus the ork skills we retain (full why table under [Install](#install)):
npx skills add yonatangross/orchestkit -s devops-deployment -s responsive-patterns -s architecture-decision-record -s ui-components -s rag-retrieval -s agent-orchestration -s brainstorm -s expect -s auto -s review-pr -s fix-issue -s commit
Full catalog: `npx skills add yonatangross/orchestkit` (hundreds of SKILL.md files; do not treat that as unique users). Live install totals stay on the skills.sh badge above.
---
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 128 lines
- {
- "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
- "name": "orchestkit",
- "version": "10.14.0",
- "description": "The Complete AI Development Toolkit - 115 skills, 36 agents, 47 commands, 163 hooks for full-stack development",
- "owner": {
- "name": "Yonatan Gross",
- "email": "yonaigross@gmail.com"
- },
- "metadata": {
- "description": "AI-assisted development plugin with built-in best practices, security patterns, quality gates, and multi-agent orchestration for Claude Code.",
- "pluginRoot": "./plugins"
- },
- "plugins": [
- {
- "name": "ork",
- "version": "10.14.0",
- "description": "Complete AI development toolkit covering AI/LLM, backend, frontend, security, and testing patterns, with specialized agents, commands, and lifecycle hooks.",
- "author": {
- "name": "Yonatan Gross",
- "email": "yonaigross@gmail.com"
- },
- "category": "development",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/yonatangross/orchestkit.git",
- "path": "plugins/ork",
- "ref": "v10.14.0"
- }
- },
- {
- "name": "ork-alpha",
- "version": "10.14.0",
- "description": "Prerelease channel for OrchestKit. Tracks main, so it carries alpha and beta builds ahead of the stable ork plugin. Install only if you want unreleased changes.",
- "author": {
- "name": "Yonatan Gross",
- "email": "yonaigross@gmail.com"
- },
- "category": "development",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/yonatangross/orchestkit.git",
- "path": "plugins/ork",
- "ref": "main"
- }
- },
- {
- "name": "ork-extras",
- "version": "10.14.0",
- "description": "Opt-in reference skills split out of ork: library patterns (LangGraph, RAG, MCP, Vite, Zustand, Storybook and more) and engineering domain guides (accessibility, distributed systems, DDD, release management). Skills only, no agents or hooks. Install next to ork; invoke as /ork-extras:<skill>.",
- "author": {
- "name": "Yonatan Gross",
- "email": "yonaigross@gmail.com"
- },
- "category": "development",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/yonatangross/orchestkit.git",
- "path": "plugins/ork-extras",
- "ref": "v10.14.0"
- }
- },
- {
- "name": "promote-lights",
- "description": "Mod (function hooks): CI lights above the prompt while a promote PR is open, or for any PR with /lights watch owner/repo#N; /lights [off|refresh|watch]. Requires Claude Code 2.1.266+. On 2.1.266 to 2.1.286 set CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1; on 2.1.287+ Mods are public.",
- "version": "0.0.15",
- "author": {
- "name": "Yonatan Gross",
- "email": "yonaigross@gmail.com"
- },
- "category": "development",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/yonatangross/orchestkit.git",
- "path": "mods/promote-lights",
- "ref": "main"
- }
- },
- {
- "name": "secrets-veil",
- "description": "Mod (function hooks): masks secret values in tool results before the model reads them. Requires Claude Code 2.1.266+. On 2.1.266 to 2.1.286 set CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1; on 2.1.287+ Mods are public.",
- "version": "0.0.11",
- "author": {
- "name": "Yonatan Gross",
- "email": "yonaigross@gmail.com"
- },
- "category": "security",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/yonatangross/orchestkit.git",
- "path": "mods/secrets-veil",
- "ref": "main"
- }
- },
- {
- "name": "memory-lens",
- "description": "Mod (function hooks): recalls the few memories related to each prompt you send (not notifications, peers, schedules or slash commands, and never on file tool calls); /memory-lens for stats, reload and show. Requires Claude Code 2.1.266+. On 2.1.266 to 2.1.286 set CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1; on 2.1.287+ Mods are public.",
- "version": "0.1.1",
- "author": {
- "name": "Yonatan Gross",
- "email": "yonaigross@gmail.com"
- },
- "category": "development",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/yonatangross/orchestkit.git",
- "path": "mods/memory-lens",
- "ref": "main"
- }
- },
- {
- "name": "prompt-enhancer",
- "description": "Beta mod (function hooks, experimental): a band above the prompt rewrites your draft with the session haiku model into a short, stack-aware prompt (typo fixes, your real subagents, skills and MCP servers, one Done when line, no questions); you edit the rewrite, then Send or Undo. The catalog prefix is prompt-cached. Each Enhance click costs model usage on your account (1024 token cap). Requires Claude Code 2.1.300+.",
- "version": "0.2.0",
- "author": {
- "name": "Yonatan Gross",
- "email": "yonaigross@gmail.com"
- },
- "category": "development",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/yonatangross/orchestkit.git",
- "path": "mods/prompt-enhancer",
- "ref": "main"
- }
- }
- ]
- }
README.md · README · 797 lines
- <!-- markdownlint-disable MD033 MD041 -->
- <div align="center">
- <img src="docs/banner.png" alt="OrchestKit - Stop explaining your stack. Start shipping." width="100%" />
- **<!--ork:skills-->115<!--/ork--> skills · <!--ork:agents-->36<!--/ork--> agents · <!--ork:hooks-->163<!--/ork--> hooks**
- [](https://claude.ai/claude-code)
- [](./LICENSE)
- [](https://github.com/yonatangross/orchestkit)
- [](https://platform.yonyon.ai/circle?ref=readme)
- [](https://deepwiki.com/yonatangross/orchestkit)
- [](https://mcptoplist.com/server/io.github.yonatangross%2Forchestkit)
- [](https://www.skills.sh/yonatangross/orchestkit)
- [](https://vercel.com/open-source-program)
- </div>
- ## Start here
- OrchestKit is free and open source (MIT, no account): skills and agents for Claude Code, Cursor, Codex and five more coding agents, plus hooks in Claude Code, for review, testing, security and memory. [Where it runs](https://orchestkit.dev/docs/compatibility).
- ```bash
- claude plugin marketplace add yonatangross/orchestkit && claude plugin install ork@orchestkit
- ```
- [Docs](https://orchestkit.dev/docs) · [What's new in v10](https://orchestkit.dev/docs/whats-new-v10) · [yonyon.ai](https://yonyon.ai)
- <!-- X account link: add it here when the account exists. -->
- ---
- <p align="center">
- <a href="https://orchestkit.dev/"><strong>Explore the Docs →</strong></a> ·
- <a href="https://yonyon.ai/go/orchestkit?utm_campaign=readme"><strong>OrchestKit Community →</strong></a><br>
- <sub>Skill browser, demo gallery, setup wizard</sub>
- </p>
- ---
- ## Contents
- - [Quick Start](#quick-start)
- - [Why OrchestKit?](#why-orchestkit)
- - [What You Get](#what-you-get)
- - [Key Commands](#key-commands)
- - [Configuration](#configuration)
- - [What OrchestKit observes](#what-orchestkit-observes)
- - [Install](#install)
- - [FAQ](#faq)
- - [Development](#development)
- - [What's New](#whats-new)
- - [Community](#community)
- ## Quick Start
- Pick the host you actually use. Claude Code is the full plugin (skills + agents + hooks). Cursor gets the same `ork` plugin minus Claude hook scripts. skills.sh is skills only — start with the 12 below, not the whole catalog.
- #### Host support matrix
- Measured 2026-09-08 on pi 0.85, Codex CLI and cursor-agent. Details, commands and the lane model: [OrchestKit on pi, Codex and Cursor](https://orchestkit.dev/docs/guides/orchestkit-on-pi-codex-cursor). Antigravity measured 2026-09-18 on agy 1.2.6; full evidence in `docs/audits/agy-host-support-2026-09-18.md`.
- <!-- compat-table:start (generated by scripts/stamp-compat-table.js) -->
- | Host | Skills | Agents | Hooks | Install | Needs |
- |---|---|---|---|---|---|
- | Claude Code | 115 | 36 | 163 | plugin (CLI) | Claude Code 2.1.277 or newer |
- | Cursor | 115 | 36 | not yet (#4004) | plugin (Settings) | |
- | Codex | 9 | 4 roles | not yet (#4004) | ork-codex pack | |
- | Devin | 82 | ? | ? | plugin (git) | |
- | OpenCode | 12 | ? | ? | skills.sh | |
- | Muse Code | 12 | ? | ? | .agents/skills | |
- | Pi | 82 | ? | not yet (#4004) | pi manifest | |
- | Antigravity | 12 | ? | ? | .agents/skills | |
- `?` means not measured yet, never zero. `not yet` means a tracked issue will bring it.
- <!-- compat-table:end -->
- How each host wires the rest (measured, see the dates above):
- | Surface | Claude Code | Cursor | Codex | pi | Devin | Antigravity |
- |---|---|---|---|---|---|---|
- | Rules | repo convention | 14, plugin `rules` key | `AGENTS.md` | none | `AGENTS.md`, always on | `AGENTS.md`, per-directory |
- | Commands | `/ork:<skill>` | 36 wrappers | `$ork-<skill>` | `/skill:<name>` | `/ork:<skill>` | `/<skill-name>`; `ork:<skill>` via plugin install |
- | MCP config | `.mcp.json` | `.cursor/mcp.json` | plugin `mcp.json` | `.pi/mcp.json` | `mcp.json` / `.mcp.json` | `~/.gemini/config/mcp_config.json` or plugin `mcp_config.json`; repo `.mcp.json` not read |
- | Status | shipped | shipped | shipped | shipped | skills only, GH-4146 | skills only, measured agy 1.2.6 |
- ### Claude Code
- ```bash
- /plugin marketplace add yonatangross/orchestkit
- /plugin install ork
- ```
- Then `/ork:setup`. The wizard scans the repo, recommends skills, and writes MCP config.
- CLI equivalent: `claude plugin marketplace add yonatangross/orchestkit && claude plugin install ork@orchestkit`.
- Channels: `ork` is the stable channel, pinned to the latest release. `ork-alpha` is the same plugin tracking `main`, in the same marketplace (`claude plugin install ork-alpha@orchestkit`); use it only if you want changes before they are released.
- ### Cursor
- Settings → Plugins / marketplaces → add `yonatangross/orchestkit` → enable **ork** → **open a new chat**. Same plugin Claude Code installs, not a five-skill fork. See [Install → Cursor](#cursor).
- ### skills.sh (Cursor, Codex, OpenCode, …)
- Starter 12 from measured installs plus the ork skills we retain (full why table under [Install](#install)):
- ```bash
- npx skills add yonatangross/orchestkit -s devops-deployment -s responsive-patterns -s architecture-decision-record -s ui-components -s rag-retrieval -s agent-orchestration -s brainstorm -s expect -s auto -s review-pr -s fix-issue -s commit
- ```
- Full catalog: `npx skills add yonatangross/orchestkit` (hundreds of SKILL.md files; do not treat that as unique users). Live install totals stay on the skills.sh badge above.
- ---
- ## Why OrchestKit?
- Every Claude Code session starts from zero. You explain your stack, patterns, preferences—again and again.
- OrchestKit gives Claude **persistent knowledge** of production patterns that work automatically:
- | Without | With OrchestKit |
- |---------|-----------------|
- | "Use FastAPI with async SQLAlchemy 2.0..." | "Create an API endpoint" → Done right |
- | "Remember cursor pagination, not offset..." | Agents know your patterns |
- | "Don't commit to main branch..." | Hooks block bad commits |
- | "Run tests before committing..." | `/ork:commit` runs tests for you |
- ---
- ## What You Get
- **One unified plugin, everything included.**
- | Component | Details |
- |-----------|---------|
- | **<!--ork:skills-->115<!--/ork--> Skills** | RAG patterns, FastAPI, React 19, testing, security, database design, ML integration — loaded on-demand, zero overhead |
- | **<!--ork:agents-->36<!--/ork--> Agents** | Specialized personas (backend-architect, frontend-dev, security-auditor) — route tasks to the right expert |
- | **<!--ork:hooks-->163<!--/ork--> Hooks** | Pre-commit checks, git protection, quality gates, browser safety — ship with confidence |
- All available in a single `/plugin install ork`. Skills load on-demand. Hooks work automatically.
- **[Browse everything in the Docs →](https://orchestkit.dev/docs/skills/overview)**
- ---
- ## Key Commands
- ```bash
- /ork:auto # Front door: describe a goal, it routes to the right skill
- /ork:setup # Personalized onboarding wizard
- /ork:implement # Full-stack implementation with parallel agents
- /ork:expect # Diff-aware AI browser testing
- /ork:review-pr # PR review with parallel agents
- /ork:verify # Multi-agent validation
- /ork:commit # Conventional commit with pre-checks
- /ork:explore # Analyze unfamiliar codebase
- /ork:remember # Save to persistent memory
- /ork:doctor # Health check
- ```
- ---
- ## Configuration
- `/ork:setup` detects your stack, recommends MCP servers, and writes the configuration for you.
- ### Recommended MCP Servers
- | Server | Purpose | Required? |
- |--------|---------|-----------|
- | Context7 | Up-to-date library docs | **Prerequisite** (22 of 36 agents grant its tools) |
- | Memory | Knowledge graph persistence | Recommended |
- | Sequential Thinking | Structured reasoning for subagents | Recommended |
- | Tavily | Web search and extraction | Optional |
- Set `"alwaysLoad": true` on the first three in your `.mcp.json`. It skips the per-skill tool probe and shaves ~150ms off cold starts.
- **Context7 is a prerequisite, and ork does not ship it.** 22 agents grant
- `mcp__context7__*` in their frontmatter, but `.mcp.json` is user-owned and project-scoped,
- so the grant refers to a server you add. Skip it and those agents answer from training
- data with no error raised. The recommended entry is the hosted HTTP server, which costs
- no local process:
- ```json
- "context7": {
- "type": "http",
- "url": "https://mcp.context7.com/mcp"
- }
- ```
- Free tier: 1,000 requests, public repos, no account. Context7 Pro ($10 per seat per
- month) raises that to 5,000 per seat and parses private repos; add
- `"headers": { "Authorization": "Bearer ${CONTEXT7_API_KEY}" }` and export the `ctx7sk-`
- key. Add the header only once the variable is exported: with it unset the unexpanded
- literal is sent as the token and every query fails, and it does **not** fall back to the
- anonymous free tier, so the keyless entry above is strictly better than a header with no
- key behind it. The legacy stdio transport (`npx -y @upstash/context7-mcp@4.0.2`) is the fallback
- when the hosted endpoint is unreachable, but it spawns one child process per Claude Code
- session, so the fan-out scales with how many sessions you keep open.
- **Optional companion for web-platform questions:** Chrome's [Modern Web Guidance](https://github.com/GoogleChrome/modern-web-guidance) (Apache-2.0) is a separate tool that checks a site against current web-platform guidance; pin a version when you run it, for example `npx modern-web-guidance@1.0.0`.
- ### Customizing skills
- Skills install as files on your disk, but **don't hand-edit the installed copy** — it gets overwritten on update and silently diverges from the canonical playbook. The supported ways to extend (user-level skills, project skills, upstream PRs, or disabling a bundled skill) are in [docs/extending-skills.md](docs/extending-skills.md).
- ---
- ## What OrchestKit observes
- OrchestKit is a quality-gate plugin, so its hooks are the product rather than an
- add-on. This section states plainly what they see, where it goes, and how to turn
- each piece off.
- **Scope: broad and intentional.** OrchestKit registers <!--ork:hooks-->163<!--/ork--> hooks across <!--ork:events-->32<!--/ork-->
- lifecycle events, including `SessionStart`, `UserPromptSubmit`, `PreToolUse`,
- `PostToolUse`, and `Stop`. They are **not** gated to a particular framework or
- project type, because the gates they enforce (secret-write blocking, protected-file
- guards, git safety, file-size limits, agent status protocol) apply to any codebase.
- If you only want gates on some projects, enable the plugin per-project rather than
- globally.
- **Where data goes: a local file on your own disk.**
- | What | Destination | Notes |
- |---|---|---|
- | Lifecycle events (session end, PR merged, goal converged, chain phase) | `~/.local/state/orchestkit/events.jsonl` | Written unconditionally, rotated at 10 MB. `ORK_EVENTS_LOG` redirects the path (used by the test suite) |
- | Hook metrics: event name, tool name, payload size, duration | same local file | Size-capped metrics only |
- | Hook telemetry log: event, tool name, session id, branch, timestamp, and tool inputs and outputs | `telemetry/events.jsonl` in the plugin data folder (or `.claude/telemetry/` in the project) | Secrets redacted, every string cut to 500 characters. Rotated at 10 MB at session end; rotated files deleted after 7 days |
- | Prompt text | **Not recorded** in either log | Hooks read it to make an allow/deny decision, then discard it |
- | Remote sync | **Off** | No endpoint is compiled in; see below |
- There is deliberately **no global kill switch** for the local write, because the
- gates depend on that state (the git-safety and chain-staleness hooks read their
- own prior events). To stop it entirely, disable the plugin. Individual noisy hooks
- have their own opt-outs: `ORK_DISABLE_DEBT_TRACKER`, `ORK_DISABLE_WORKTREE_VERIFIER`,
- `ORK_DISABLE_COORDINATION_METRICS`, `ORK_NO_NOTIFY`, `ORK_NO_STALE_SWEEP`, and
- `ORCHESTKIT_SKIP_SLOW_HOOKS` among others.
- **Network access from the hooks themselves is opt-in and unset by default.** The
- only remote host compiled into the shipped hook bundles is `api.typesafe.ai`,
- used solely by the two opt-in TypeSafe settings below (`grep -o 'https\?://[A-Za-z0-9.-]*' plugins/ork/hooks/dist/*.mjs`
- also lists `github.com`, which appears only in printed links). By default some
- hooks run CLIs you already have, which use your own credentials and network:
- - `claude -p --model haiku` on the first prompt of a session, to title and color
- it. It sends the git branch name and the first 600 characters of that prompt
- to Anthropic through your own Claude Code login, with no tools, MCP servers or
- hooks in the child. `ORK_SESSION_IDENTITY=0` turns it off.
- - `gh issue view <n>` when a subagent starts on a branch named like
- `issue/<n>-...` or `fix/<n>-...`, to add the issue title and body as context.
- - `gh pr view` and `gh pr list` when a Bash command runs `gh pr merge` with
- `--delete-branch`, to warn before deleting a branch that open PRs are based on.
- Any other outbound call happens only if you configure a destination yourself,
- via one of:
- - `ORCHESTKIT_HOOK_URL` + `ORCHESTKIT_HOOK_TOKEN` (or the plugin's `webhookUrl` and
- `hookToken` options), which enable `hooks/bin/telemetry-sync.mjs`. It POSTs
- your local JSONL to *your own* endpoint. A `SessionEnd` hook runs it in the
- background; without a URL and token it exits at once and sends nothing. The
- same two settings enable the webhook forwarder, which streams hook events,
- HMAC signed, to that endpoint.
- - `telemetry.sinks` entries in `~/.claude/settings.local.json` or in the plugin
- data folder's `settings.local.json` (user scope only, never read from a
- project), each an `https:` URL you choose.
- - `ORK_HQ_TELEMETRY_URL`, which points the telemetry HTTP sink at *your own* collector.
- - `ORK_HQ_TELEMETRY_USE_HQ_API=1` together with `HQ_API_URL`, the same sink aimed
- at a self-hosted HQ API.
- - `ORK_SESSION_CATEGORY_PROVIDER=jev` (or `shadow`) together with the TypeSafe
- key variable `ORK_TYPESAFE_API_KEY`, a second classifier for the session work
- category. The session-identity hook already asks a local `claude -p --model haiku`
- process for a title and a category; with both variables set it also asks
- TypeSafe's Jev model (`api.typesafe.ai`, model pinned to `jev-1.13.0`) one typed
- Choice over the same eight categories and the same criteria text. This is the
- one exception to the "no hardcoded host" note above, and it is dormant unless
- both variables are set. What leaves your machine: the git branch name and the
- first 600 characters of the session's first prompt, sent to a third-party
- processor under its own data policy. What changes in `jev` mode: when Jev
- answers at confidence 0.8 or above, its category decides the session color
- (held out on 150 sessions, that band is 93.5% correct);
- below 0.8, or on any error, haiku's category decides as before. The title and
- emoji always come from haiku. In `shadow` mode nothing you see changes; Jev is
- only logged beside haiku. To turn it on locally, in the shell that launches
- `claude`: `export ORK_TYPESAFE_API_KEY="$(<your secret manager> ...)"` and
- `export ORK_SESSION_CATEGORY_PROVIDER=jev`. Both outcomes are logged once per
- session in the hook log, as
- `category jev: haiku=<cat> jev=<cat> agree=<bool> confidence=<n> decided_by=jev|haiku threshold=0.8 latency_ms=<n>`,
- and as `session-identity.shadow.json` with the same fields (labels, decision,
- timing; never prompt text) next to the raw answer `session-identity.jev.json`
- in the session data directory. Cost of opting in: the first prompt of a session
- waits for the call to settle, 1.1 to 1.7 s measured from a fresh hook process
- (the eval's 320 ms was a warm connection), 3 s at most before it gives up.
- - `ORK_ROUTE_JEV=shadow` (or `steer`) together with `ORK_TYPESAFE_API_KEY`, the
- Jev routing seam for `/ork:auto` (#4233). Off by default. When set, every
- build-shaped prompt (the same test the once-per-session executor reminder
- uses: an imperative build or fix verb, 40 characters or more, no explicit
- `/plugin:skill`) is sent to the same TypeSafe endpoint and model as one typed
- Choice over nineteen route classes plus four side judgments (needs a worktree,
- needs a browser, mutation risk, needs the operator). What leaves your machine:
- the first 1,500 characters of the prompt after a redactor has replaced
- secrets, emails, Israeli phone numbers, nine digit ids, `op://` references and
- the names of directories under `clients/` with `[SECRET]`, `[EMAIL]`,
- `[PHONE]` and `[CLIENT]`, plus the repository basename. The serialized request
- is scanned again before it leaves; anything that survives redaction refuses
- the call. In `shadow` mode nothing you see changes; the verdict is logged. In
- `steer` mode, at confidence `ORK_ROUTE_JEV_FLOOR` (default 0.5) or above, the
- one-line executor reminder names the executor the class maps to
- (`route: dev_fix -> /ork:fix-issue (conf 0.83)`); the model still reads the
- `/ork:auto` table and says whether it agrees. Fallbacks are fail open: no key,
- timeout, non-2xx, malformed answer, below the floor, or the daily token budget
- (`ORK_ROUTE_JEV_DAILY_TOKENS`, default 2,000,000) spent all mean the existing
- path runs untouched; a 402 or 429 switches the seam off for 24 hours. One log
- line per prompt,
- `route jev: intent=<class> conf=<n> top3=<a:p,b:p,c:p> worktree=<n> browser=<n> mutation=<n> operator=<n> floor=<n> decided_by=jev|table|off|budget|egress latency_ms=<n> input_tokens=<n> redacted=<n>`,
- and one record per prompt in `jev-route.jsonl` next to
- `session-identity.jev.json` (labels, timings and a sha256 of the redacted
- text; never prompt text). Offline replay: `node scripts/eval/route-check.mjs --jev`
- and `node scripts/eval/jev-route-score.mjs`. The vendor's agent skill is a
- peer plugin installed from its own marketplace, never a copied directory:
- `claude plugin marketplace add typesafe-ai/skills` then
- `claude plugin install typesafe@typesafe-ai`; `/ork:doctor` reports the
- installed version against the marketplace and prints the update commands.
- The sink returns early when the URL or the token is missing, and
- `telemetry-sync.mjs` prints `No ORCHESTKIT_HOOK_URL or TOKEN configured. Nothing
- to sync.` then exits 0. There is no analytics ping, no crash reporter, and no
- feature-flag fetch.
- **What OrchestKit never reads.** No OS keychain lookups, no `~/.aws/credentials`,
- no SSH private keys, no browser cookie or login stores, no clipboard. The one
- place secret-shaped paths appear in the source is
- `plugins/ork/hooks/dist/pretool.mjs`, where `id_rsa`, `.pem`, `.env`, and
- `credentials.json` form a **blocklist** that stops Claude writing to them. That
- code denies access; it does not read those files.
- **Third-party MCP servers are recommendations, not bundled dependencies.** The
- plugin ships no `.mcp.json` and declares no `mcpServers`. The table under
- [Configuration](#configuration) is advisory, and `/ork:setup` asks before writing
- anything.
- ---
- ## Install
- ```bash
- /plugin install ork
- ```
- No tiering. No version confusion. Just one powerful plugin.
- Not on Claude Code? Pull a **starter 12** into any agent (Cursor, Codex, OpenCode, …) via [skills.sh](https://www.skills.sh/yonatangross/orchestkit) — do not install the whole firehose on day one. Picked from measured skills.sh installs on our listing plus the ork skills we actually retain:
- | skill | why |
- |---|---|
- | `devops-deployment` | most-installed cloud skill on our listing |
- | `responsive-patterns` | most-installed design skill on our listing |
- | `architecture-decision-record` | writing-bucket install leader |
- | `ui-components` | design install co-leader |
- | `rag-retrieval` | SE install leader |
- | `agent-orchestration` | agent-workflow install leader |
- | `brainstorm` | our most-retained ork skill |
- | `expect` | browser verification we run day to day |
- | `auto` | front-door router we actually invoke |
- | `review-pr` | ship-loop review we use |
- | `fix-issue` | debug loop we use |
- | `commit` | ship-loop commit (has a with/without receipt) |
- ```bash
- npx skills add yonatangross/orchestkit -s devops-deployment -s responsive-patterns -s architecture-decision-record -s ui-components -s rag-retrieval -s agent-orchestration -s brainstorm -s expect -s auto -s review-pr -s fix-issue -s commit
- ```
- All skills: `npx skills add yonatangross/orchestkit`. Live install totals stay on the [skills.sh badge](https://www.skills.sh/yonatangross/orchestkit) above, not hard-coded here.
- ### Cursor
- Cursor loads [Agent Plugins](https://agent-plugins.org) and Cursor plugins.
- This repo already ships the Agent Plugins manifest at `plugins/ork/plugin.json`.
- Add the GitHub repo as a Cursor marketplace (Settings → `yonatangross/orchestkit`),
- enable **`ork`**, then **open a new chat**. That is the same plugin Claude Code
- installs, not a five-skill fork.
- It also ships 14 rules under the plugin's `rules` key, generated from
- `src/rules/` and `src/shared/rules/`. They are agent-fetched, so a rule costs
- context only when its description matches the task.
- Claude hook scripts are not registered for Cursor: they depend on
- `${CLAUDE_PLUGIN_ROOT}` (orchestkit#293, closed). Cursor enforcement for HQ
- repos stays in the consuming project's `.cursor/hooks.json`.
- "Include third-party Plugins" can leak SKILL.md from `~/.claude/plugins`. That
- is not an install. Proof is the `ork` plugin id plus the full skill catalog.
- ### Codex
- Codex uses its own plugin format, skill picker, and standalone role
- configuration. Add OrchestKit's Codex marketplace, then install the small
- portable workflow pack:
- ```bash
- codex plugin marketplace add yonatangross/orchestkit --ref main --sparse .agents/plugins --sparse plugins/ork-codex
- codex plugin add ork-codex@orchestkit-codex
- ```
- Restart Codex after installation. Invoke a workflow explicitly with
- `$ork-brainstorm`, `$ork-explore`, `$ork-implement`, `$ork-assess`, `$ork-verify`,
- or `$ork-review-pr`; their narrow descriptions also let Codex select the relevant
- workflow automatically.
- The plugin intentionally ships roles as templates because Codex loads custom
- roles from `~/.codex/agents/`, not from a plugin manifest. From an OrchestKit
- checkout, run this one-time, non-overwriting install:
- ```bash
- plugins/ork-codex/scripts/install-codex-roles.sh ~/.codex/agents
- ```
- It installs `ork_explorer`, `ork_implementer`, `ork_reviewer`, and
- `ork_verifier`; restart Codex before spawning them.
- #### Unattended runs: the `ork-mech` profile
- For mechanical work (renames, bumps, codemods, sweeps that end in a diff),
- install the shipped profile and run `codex exec` against it:
- ```bash
- plugins/ork-codex/scripts/install-codex-profile.sh ~/.codex
- codex exec --profile ork-mech "<task>" </dev/null
- ```
- The profile is a FILE, not a snippet you paste into `config.toml`. Measured on
- codex-cli 0.153.4: `--profile <name>` layers `$CODEX_HOME/<name>.config.toml`
- over the base config, and a legacy `[profiles.<name>]` table left inside
- `config.toml` makes the same flag a hard config-load error. The installer
- refuses to run next to that table, and refuses to overwrite a profile you
- already have.
- What it sets, as `codex exec` prints it in its own header:
- ```
- approval: never
- sandbox: workspace-write [workdir, /tmp, $TMPDIR] (network access enabled)
- reasoning effort: high
- ```
- It deliberately does not pin a model (pass `-m`) and does not use
- `--dangerously-bypass-approvals-and-sandbox`, which drops the sandbox entirely.
- Two contracts a TOML file cannot express, so they stay on the command line:
- - **`</dev/null`.** `codex exec` reads stdin even when a prompt argument is
- given. An inherited open pipe blocks the run with `Reading additional input
- from stdin...` and no timeout.
- - **`--add-dir` inside a git worktree.** The writable roots are
- `[workdir, /tmp, $TMPDIR]`. A linked worktree's git common dir sits outside
- the workdir, so the first commit dies on `index.lock`. Add it:
- ```bash
- codex exec --profile ork-mech \
- --add-dir "$(git rev-parse --path-format=absolute --git-common-dir)" \
- "<task>" </dev/null
- ```
- #### Keeping the install current
- `ref main` in the marketplace source is a cached snapshot, not a tracker. On the
- 2026-09-08 audit machine `codex plugin list` showed `10.0.0-beta.5` while main
- was three releases ahead. After an OrchestKit release, update and check:
- ```bash
- codex plugin update
- codex plugin list | grep ork-codex # installed version
- jq -r .version plugins/ork-codex/.codex-plugin/plugin.json # what main ships
- ```
- #### Documentation lookup (context7)
- The plugin ships a [context7](https://context7.com) MCP server in its own
- manifest (`mcpServers` in `.codex-plugin/plugin.json`, defined in `mcp.json`),
- so installing the plugin registers it. Confirm with `codex mcp get context7`.
- It is scoped to the only two tools context7 exposes, `resolve-library-id` and
- `query-docs`, and it uses the hosted HTTP transport rather than an `npx` stdio
- child, so it costs no extra process per Codex session.
- Export a key before starting Codex. The plugin references the variable name
- and never stores the value, so no token is written to `~/.codex/config.toml`:
- ```bash
- export CONTEXT7_API_KEY_CODEX="<your-context7-api-key>"
- ```
- Put that in your shell profile so every Codex session inherits it. Get the
- key from your own context7 account and keep the value out of the repository.
- If you store it in a secret manager, substitute your own vault and item names
- (with the 1Password CLI the reference is `op://<vault>/<item>/credential`), and
- cache the resolved value instead of re-reading the vault in every shell: each
- raw read is a separate unlock prompt.
- Two behaviors worth knowing:
- - A server you already define yourself under `[mcp_servers.context7]` in
- `~/.codex/config.toml` **wins**, and the plugin's definition is ignored
- entirely (including its tool scoping). That is intentional: your own
- configuration is never overridden. Remove your entry if you want the
- plugin's.
- - Without a valid key the server still connects and still lists its tools.
- Only a real call fails, with `Invalid API key`. A successful connection is
- therefore not proof of authentication.
- ### pi
- pi (0.85) reads the same SKILL.md format, and the repo now carries a `pi`
- manifest, so the package installs directly:
- ```bash
- pi install git:github.com/yonatangross/orchestkit
- ```
- That registers every skill. Add `-l` to write `.pi/settings.json` in the
- project instead of your user settings. Pointing pi at a checkout still works
- and needs no install (`pi --skill ./plugins/ork/skills`).
- The 29 skills marked `disable-model-invocation` stay reachable only as
- `/skill:<name>`. Two measured caveats: `--no-builtin-tools` hides every skill
- (pi lists skills only when a file-reading tool is enabled), and `pi -p` blocks
- on an open stdin, so headless runs need `</dev/null`.
- MCP servers for pi come from `.pi/mcp.json`, then `.mcp.json`, then
- `~/.config/mcp/mcp.json`. Copy the shipped template to get the recommended
- servers with a read-only `includeTools` allowlist per server:
- ```bash
- cp .pi/mcp.json.example .pi/mcp.json
- ```
- Full detail and the tracking epic:
- [OrchestKit on pi, Codex and Cursor](https://orchestkit.dev/docs/guides/orchestkit-on-pi-codex-cursor).
- ### Devin
- ```bash
- devin plugins install yonatangross/orchestkit
- ```
- Devin checks a plugin root for a manifest in this order: `.devin-plugin/plugin.json`,
- then `.claude-plugin/plugin.json`, then root `plugin.json`
- ([plugins reference](https://docs.devin.ai/cli/extensibility/plugins/overview)).
- The repo root only had the last one, the [Agent Plugins](https://agent-plugins.org)
- manifest, which fixes skills at a root `skills/` directory this repo does not have,
- so a bare install used to list 0 of 107 skills, 0 hooks, and only the `AGENTS.md`
- rule (GH-4146). A root level `.devin-plugin/plugin.json` now maps `skills` to
- `./plugins/ork/skills`, the same built tree Claude Code and Cursor already read.
- `devin plugins info ork` lists 76 of 107 skills after that change (measured on
- Devin CLI 3000.10.27). The other 31, `auto`, `verify`, `help`, `brainstorm`, and
- similar router or workflow skills, declare a `triggers:` frontmatter key shaped
- as an object (`keywords`, `examples`, `anti-triggers`). Devin's own `triggers`
- field expects a flat `[user, model]` list, and the shape mismatch drops the
- whole skill instead of warning. Renaming that key touches three other readers
- (`scripts/eval/eval-coverage.sh`, `tests/skills/triggering/test-trigger-keywords.sh`,
- and the `SKILL_ONLY` allowlist in `tests/plugins/test-command-frontmatter-passthrough.sh`),
- so it stays tracked on GH-4146 instead of folded into this fix. Installing the
- subpath directly, `devin plugins install yonatangross/orchestkit#plugins/ork`,
- reaches the same 76 skills plus the plugin's 36 custom subagents, which neither
- path surfaces through `devin plugins info`. That subpath is what this repo's own
- `.claude-plugin/marketplace.json` already points Claude Code at.
- OrchestKit's plugin hooks work under Claude Code only today; none of the <!--ork:hooks-->163<!--/ork-->
- fire under Devin. Two reasons. Location: OrchestKit ships hooks at
- `plugins/ork/hooks/hooks.json`, while Devin's own plugin format reads a bare
- `hooks.json` at the plugin root instead. Shape and tool names: OrchestKit's
- file matches Claude Code tool names such as `Bash` and `Write|Edit` and
- expands `${CLAUDE_PLUGIN_ROOT}` in command args, both Claude Code specific.
- Devin's own
- [hooks.v1.json](https://docs.devin.ai/cli/extensibility/hooks/overview) format
- matches its own tool names instead, `exec`, `write`, `edit` and friends (see
- [lifecycle hooks](https://docs.devin.ai/cli/extensibility/hooks/lifecycle-hooks)),
- inside the same `{matcher, hooks:[{type, command}]}` event map shape.
- `devin plugins info` confirms `Hooks (none)` even once skills resolve.
- `PreToolUse` and `PostToolUse` read the closest to what OrchestKit's own
- pretool and posttool hooks already do, and are the first candidates for a
- future Devin hook manifest once the tool name mapping is written deliberately
- instead of guessed.
- Pin a release instead of tracking `main`: release-please tags every release as
- `v10.0.0-beta.N`. The single argument `devin plugins install <source>` command
- has no ref pinning syntax of its own; pin through a `requiredPlugins` entry
- (in this repo's own `.devin/config.json`, or a personal, org, or enterprise
- manifest) instead:
- ```json
- {
- "requiredPlugins": [
- { "source": "github", "repo": "yonatangross/orchestkit", "ref": "v10.0.0-beta.30" }
- ]
- }
- ```
- ### Antigravity
- ```bash
- npx skills add yonatangross/orchestkit -s devops-deployment -s responsive-patterns -s architecture-decision-record -s ui-components -s rag-retrieval -s agent-orchestration -s brainstorm -s expect -s auto -s review-pr -s fix-issue -s commit
- ```
- Antigravity (`agy`, Google's agentic CLI) reads Agent Skills from a workspace
- `.agents/skills` directory, so the shared skills.sh line above is the install
- path and Antigravity is already in that installer's universal target list
- (measured on agy 1.2.6; full evidence in
- `docs/audits/agy-host-support-2026-09-18.md`). Verify from the repo root with
- `agy -p "/skills" --add-dir "$PWD"`: print mode only registers a workspace from
- an absolute `--add-dir`, while the interactive TUI takes the launch directory
- as the workspace and needs no flag.
- Two honest gaps. `npx skills add -g` lands in `~/.agents/skills`, which agy
- does not read; user scope lives at `~/.gemini/config/skills` (or
- `~/.gemini/skills`). And none of ork's <!--ork:hooks-->163<!--/ork--> hooks port: agy's `hooks.json` uses
- its own event names and payload shape, and `agy plugin validate plugins/ork`
- reports hooks skipped because ork keeps them at `hooks/hooks.json`, not the
- plugin-root `hooks.json` agy looks for.
- A fuller install exists but needs a local checkout:
- `agy plugin validate <checkout>/plugins/ork` reports `skills: 108 processed`,
- `agents: 36 processed`, and `agy plugin install <checkout>/plugins/ork` copies
- them into `~/.gemini/config/plugins/ork/` namespaced `ork:<name>`, which matches
- the `/ork:<skill>` spelling. Plugin-bundled `mcp_config.json` also works
- (marker-verified end to end), but a repo-level `.mcp.json` is never read.
- ---
- ## FAQ
- <details>
- <summary><strong>Plugin not found?</strong></summary>
- ```bash
- /plugin list
- /plugin uninstall ork && /plugin install ork
- ```
- </details>
- <details>
- <summary><strong>Hooks not firing?</strong></summary>
- Run `/ork:doctor` to diagnose.
- </details>
- <details>
- <summary><strong>Claude Code version?</strong></summary>
- Requires **≥2.1.277** (supported floor; Opus 5 as the default Opus, Opus 5.5 from 2.1.280, `xhigh` effort, dynamic workflows, `sandbox.network.strictAllowlist`, native binary, hardened `Bash(rm:*)`/`Bash(find:*)` rules). Check with `claude --version`.
- Raising this floor is a breaking change and ships as a major release. See [STABILITY.md](STABILITY.md) for the full contract, and `shared/cc-support.json` for the authoritative window.
- </details>
- <details>
- <summary><strong>Superpowers vs OrchestKit?</strong></summary>
- Complementary, not a rival listing. Superpowers (official Anthropic marketplace) is process: how the agent works a task. OrchestKit is production patterns plus lifecycle hooks. Honest split: [docs](https://orchestkit.dev/docs/getting-started/superpowers) · [yonyon.ai](https://yonyon.ai/compare/orchestkit-superpowers).
- </details>
- ---
- ## Development
- ```bash
- npm run build # Build plugins from src/
- npm test # Run all tests
- ```
- Edit `src/` and `manifests/`, never `plugins/` (generated).
- See [CONTRIBUTING.md](./CONTRIBUTING.md) for details.
- ---
- ## What's New
- <!--ork:whats-new-->
- <!-- AUTO-GENERATED from CHANGELOG.md by scripts/stamp-whats-new.mjs — do not hand-edit between the ork:whats-new markers. -->
- <!-- Regenerated on `npm run build`; CI (`--check`) fails if this is stale. Full history: [CHANGELOG.md](CHANGELOG.md). -->
- **[v10.14.0](https://github.com/yonatangross/orchestkit/compare/v10.13.0...v10.14.0)** · 2026-11-17
- - **cli:** orchestkit install finds the coding agents on this machine (#5267)
- - **codex:** add ork-commit and ork-create-pr to the Codex pack (#5261)
- - **fix-issue:** safety-fact proof ladder and review-pr proof criterion (#5273)
- - **hooks:** record a fixed error_class on PostToolUseFailure telemetry (#5248)
- - **review-pr:** proven-by-a-run tier in review-fanout (#5274)
- - …and 27 more (see [CHANGELOG.md](CHANGELOG.md))
- **[v10.13.0](https://github.com/yonatangross/orchestkit/compare/v10.12.0...v10.13.0)** · 2026-11-15
- - **ci:** scheduled whole-tree npm audit with a cannot-audit item (#5230)
- - **plugins:** move 26 reference skills to the opt-in ork-extras plugin (#5220)
- - **ci:** make the nightly health report prove its Claude call (#5221)
- - **ci:** the npm audit gate judges the change, not the tree (#5233)
- - **disk-cleanup:** ask before images, keep new snapshots, pin apply (#5213)
- - …and 11 more (see [CHANGELOG.md](CHANGELOG.md))
- **[v10.12.0](https://github.com/yonatangross/orchestkit/compare/v10.11.0...v10.12.0)** · 2026-11-12
- - **hooks:** ship 2 hook processes per tool call, not 3 (#5214)
- - **skills:** add /ork:disk-cleanup (#5211)
- - **cursor:** commands run skill scripts only from the installed plugin (#5216)
- - **docs:** hook pages say when the shipped plugin skips an event (#5215)
- - **docs:** try Chromium before apt, so the mirror is not on every build (#5212)
- - …and 5 more (see [CHANGELOG.md](CHANGELOG.md))
- **[v10.11.0](https://github.com/yonatangross/orchestkit/compare/v10.10.8...v10.11.0)** · 2026-11-10
- - **cc:** adopt Claude Code 2.1.310 through 2.1.322 (#5181)
- - **demo-producer:** add code-drawn mode, storyboard renders the film (#5185)
- - **docs-site:** count page views cookieless before consent (#5180)
- - **docs-site:** make the consent banner easier to notice (#5179)
- - **agents:** raise builder maxTurns above documented workload (#5192)
- - …and 11 more (see [CHANGELOG.md](CHANGELOG.md))
- **[v10.10.8](https://github.com/yonatangross/orchestkit/compare/v10.10.7...v10.10.8)** · 2026-11-09
- - **release:** fetch mcp-publisher through the authenticated API (#5162)
- **[v10.10.7](https://github.com/yonatangross/orchestkit/compare/v10.10.6...v10.10.7)** · 2026-11-09
- - **ci-sentinel:** match the skill to the locked-down dispatch (#5156)
- - **ci-sentinel:** say every failed check, and pin the playbook copy (#5159)
- - **deps-dev:** bump @biomejs/biome (#5153)
- - **deps-dev:** bump @sanity/client (#5154)
- - **deps:** bump @anthropic-ai/sdk (#5151)
- - …and 4 more (see [CHANGELOG.md](CHANGELOG.md))
- **[v10.10.6](https://github.com/yonatangross/orchestkit/compare/v10.10.5...v10.10.6)** · 2026-11-09
- - **ci-sentinel:** refresh drifted skill text (#5147)
- - **ci:** remove the ci-sentinel ceiling that could never fire (#5141), closes [#5138](https://github.com/yonatangross/orchestkit/issues/5138)
- - **ci:** tell claude-triage the repo so it stops running out of turns (#5143), closes [#5142](https://github.com/yonatangross/orchestkit/issues/5142)
- - **docs:** serve the server card media type when a client asks (#5125)
- - **secrets-veil:** keep image URLs on named media hosts readable (#5146)
- - …and 4 more (see [CHANGELOG.md](CHANGELOG.md))
- **[v10.10.5](https://github.com/yonatangross/orchestkit/compare/v10.10.4...v10.10.5)** · 2026-11-08
- - Codex hook paths and docs MCP query validation (#5119)
- - **hooks:** state machine audit bundle (#5117)
- - **skills:** bill long Haiku 5.5 prompts on the higher rate card (#5124)
- - **skills:** send the event name from fork skill body loaders (#5122)
- - **skills:** skill quality round 5, pass the fitness checklist (#5104)
- _See [CHANGELOG.md](CHANGELOG.md) for the full release history._
- <!--/ork-->
- ---
- ## Community
- Join the **Building with AI** community for AI dev tips, OrchestKit support, and connecting with other builders:
- | Room | Who it's for | Link |
- |------|--------------|------|
- | **Building with AI** | The umbrella community. One join, every room below. | [Join](https://platform.yonyon.ai/circle?ref=readme) |
- | **Builders** | For people already building | [Join](https://yonyon.ai/go/builders?utm_campaign=readme) |
- | **OrchestKit** | For OrchestKit users | [Join](https://yonyon.ai/go/orchestkit?utm_campaign=readme) |
- | **AI for Business** | For people leading AI adoption | [Join](https://yonyon.ai/go/business?utm_campaign=readme) |
- Names and audiences match what [yonyon.ai](https://yonyon.ai/en) renders, so the two surfaces cannot drift. Every link resolves through `yonyon.ai/go/*`, so a rotated invite never needs a README change and no raw invite is published here.
- ---
- ## OrchestKit family
- - **[Tower](https://github.com/yonatangross/tower)**: a macOS menu bar app for people who run several AI coding subscriptions: usage per account, room left, when to switch. Also an MCP server (`tower mcp`).
- ---
- ## Who builds this
- OrchestKit is built and maintained by **[Yonatan Gross](https://github.com/yonatangross)** — [Yonyon AI](https://yonyon.ai/en), an AI consulting practice. It is the toolkit extracted from real client work, not a side project: the patterns here are the ones that survived shipping.
- It stays MIT and free. Nothing is gated, and none of the below changes that.
- **Working out where AI actually fits in your business?** The [**AI readiness audit**](https://platform.yonyon.ai/ai-audit) is a free assessment that maps your workflows and returns a prioritized report — the same diagnostic that opens a consulting engagement.
- **Want the toolkit running properly in your team?** Setup, configuration, and a working agent loop tailored to your stack is something I do as a fixed-scope engagement. Start a [discussion](https://github.com/yonatangross/orchestkit/discussions) or reach out through the [community](https://yonyon.ai/go/business?utm_campaign=readme).
- Security policy and reporting: [SECURITY.md](SECURITY.md).
- ---
- <div align="center">
- **[Docs](https://orchestkit.dev/)** · **[Issues](https://github.com/yonatangross/orchestkit/issues)** · **[Discussions](https://github.com/yonatangross/orchestkit/discussions)** · **[Community](https://platform.yonyon.ai/circle?ref=readme)**
- MIT License · [@yonatangross](https://github.com/yonatangross)
- </div>
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.