Back to search
agent-tools
SkillWorks with CodexGitHub
Reusable Agent Skills from agent-tools
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/kairyou--agent-tools)HTML
<a href="/listings/kairyou--agent-tools"><img src="/api/listings/kairyou--agent-tools/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
# List available skills npx -y skills@latest add kairyou/agent-tools --list # Install globally (pass one or more names after --skill) npx -y skills@latest add kairyou/agent-tools --skill <name...> -g -y
The Skills installer automatically detects and installs to the Skill directories of most supported agents.
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/plugin.json · Manifest · 17 lines
- {
- "name": "agent-tools",
- "version": "0.27.0",
- "description": "Reusable Agent Skills from agent-tools",
- "author": {
- "name": "kairyou"
- },
- "skills": [
- "./skills/workflow/at-commit",
- "./skills/workflow/at-daily-log",
- "./skills/workflow/at-review",
- "./skills/workflow/at-self-eval",
- "./skills/workflow/at-simplify",
- "./skills/systems/at-zentao"
- ],
- "license": "MIT"
- }
README.md · README · 270 lines
- # Agent Tools
- Reusable Agent Skills for compatible coding agents, plus per-agent runtime capabilities for statusline, provider usage, vision, and session logging.
- Requires Node.js >= 22.
- [中文](README.zh-CN.md)
- ## Skills
- ### Install
- ```bash
- # List available skills
- npx -y skills@latest add kairyou/agent-tools --list
- # Install globally (pass one or more names after --skill)
- npx -y skills@latest add kairyou/agent-tools --skill <name...> -g -y
- ```
- The Skills installer automatically detects and installs to the Skill directories
- of most supported agents.
- ### at-commit
- Generate a Conventional Commits message from staged changes and wait for user confirmation before committing.
- ```bash
- npx -y skills@latest add kairyou/agent-tools --skill at-commit -g -y
- ```
- Usage:
- - `/at-commit [<language>]` — language for the commit description (Conventional Commits tokens stay in English)
- ### at-review
- Review local changes or a hosted PR/MR for correctness bugs, regressions, convention violations, and high-value cleanup findings.
- ```bash
- npx -y skills@latest add kairyou/agent-tools --skill at-review -g -y
- ```
- Usage:
- - `/at-review [--fix] [<pr-or-mr-url|branch|path>]` — reports review findings; private hosted targets require locally available read access, and `--fix` applies fixes only to a matching working tree
- ### at-simplify
- Refactor changes to reduce duplication, lower complexity, and improve code quality.
- ```bash
- npx -y skills@latest add kairyou/agent-tools --skill at-simplify -g -y
- ```
- Usage:
- - `/at-simplify [<pr|branch|path>]`
- ### at-zentao
- Work ZenTao (禅道) bugs/tasks end to end, manage task status and hours, or read linked story context; asks before committing and before writing back.
- ```bash
- npx -y skills@latest add kairyou/agent-tools --skill at-zentao -g -y
- ```
- Usage:
- - `/at-zentao bugs` — list bugs assigned to you (the configured account); pick one or several (several = batch mode)
- - `/at-zentao tasks` — same, for tasks
- - `/at-zentao bug <id>` — work a specific bug
- - `/at-zentao task <id> [request]` — work a task, start/pause/resume it, or log hours with a natural-language request
- - `/at-zentao story <id>` — read requirement scope and acceptance context without writing back
- Configure `~/.agent-tools/config.jsonc`:
- ```jsonc
- {
- "zentao": {
- "url": "https://zentao.example.com",
- "account": "user",
- "password": "your-password",
- // "password": { "env": "ZENTAO_PASSWORD" }, // Or read the password from an environment variable.
- // Optional. Without this, labels follow the item or user's language.
- // "commentPrompt": "For fixed Bugs, write in English using this format:\nCause: ...\nFix: ...\nScope: ...\nTest suggestions: ...\nCommit: <hash>\nKeep each field brief. Omit Scope and Test suggestions when there is nothing useful to add. Use a real commit hash."
- }
- }
- ```
- ## Capabilities
- Runtime capabilities, installed per agent:
- ```bash
- npx -y @kairyou/agent-tools@latest <capability> -a <agent...>
- # npx -y github:kairyou/agent-tools <capability> -a <agent...> # Or the latest code from GitHub (needs Git)
- ```
- `--dry-run` previews, `--uninstall` removes the capability from the agent, and
- re-running the install command updates. Updates to `config.jsonc` add missing
- defaults while preserving your values and comments.
- | Runtime capability | Supported agents |
- | --- | --- |
- | `statusline` | Claude Code |
- | `usage` | Claude Code, Codex, OpenCode, Pi |
- | `vision` | Claude Code, Codex, OpenCode, Pi, ZCode, DeepSeek Harness |
- | `log` | Claude Code, Codex, OpenCode, Pi |
- ### Statusline
- ```bash
- npx -y @kairyou/agent-tools@latest statusline -a claude
- ```
- The installer writes `statusLine` to `~/.claude/settings.json`. Example output:
- ```text
- # Claude subscription:
- ⎇ main | Opus 4.8 | 5h 7% ⟳ 2h54m | w 41% ⟳ 3d1h
- # API relay:
- ⎇ main | Opus 4.8 | balance $362 | today $61.7 | 30d $566
- ```
- `5h` / `w`: Claude's rolling 5-hour / 7-day usage windows; `⟳`: time until reset.
- Set visible fields and order via `statusline.fields` in `~/.agent-tools/config.jsonc`;
- add `"outputSpeed"` for estimated output speed (e.g. `38.2 tok/s`).
- For supported relay gateways and usage configuration, see [Provider usage](#provider-usage).
- ### Provider usage
- Shows API relay / gateway balance and quota inside the agent. Supports Sub2API,
- One API (including OneHub and DoneHub), New API, Claude Code Hub, OpenRouter, and
- Command Code; compatibility depends on the gateway version and enabled usage
- endpoints.
- ```bash
- npx -y @kairyou/agent-tools@latest usage -a claude codex opencode pi
- ```
- - **Claude Code** — `/at-usage` shows usage in chat; installing `statusline` also adds it to the status line.
- Set `statusline.showProviderUsage` to `false` to hide relay gateway usage from the status line.
- - **Codex** — run `/hooks` once after installation to approve it. The Codex CLI
- displays usage automatically; clients that hide hook output can use `$at-usage`.
- - **OpenCode** — usage refreshes when the session goes idle and appears as a
- toast; `/at-usage` shows it on demand. Restart opencode after installing or updating.
- - **Pi** — displays usage in the footer. Restart Pi or run `/reload` after installing or updating.
- The endpoint and key come from the agent's current model or existing configuration;
- official endpoints are skipped. If it reports
- `Provider usage is unavailable.`, set `PROVIDER_USAGE_BASE_URL` and
- `PROVIDER_USAGE_API_KEY` to override the endpoint and key. Configure
- `providerUsage` in `~/.agent-tools/config.jsonc` only when needed:
- ```jsonc
- {
- "providerUsage": {
- // auto | sub2api | openai-compatible | one-api | one-hub |
- // done-hub | new-api | claude-code-hub | openrouter | commandcode | <custom-route-id>
- "preset": "auto", // auto-detect, or select one protocol listed above
- "days": 30, // how many recent days of spend to count
- "outputSpeed": false, // true: show estimated output speed (tok/s)
- "debug": false // true: log probes to ~/.agent-tools/logs/usage-debug.log
- }
- }
- ```
- Output examples:
- ```text
- # Plan limits:
- D $0.0/$100 | W $0.0/$300 ⟳ 3d1h | Exp 07-08
- # Multi-window limits:
- 5h $2.1/$10.0 | D $8.0/$20.0 | T $19.0/$100 | Exp 08-31
- # Balance and usage:
- balance $15.0 | used $5.0/$20.0 | ⟳ 3d1h
- # Wallet and recent spend:
- balance $362 | today $61.7 | 30d $566
- ```
- Fields: `5h/D/W/M/T` are five-hour/daily/weekly/monthly/total spend against
- limits; `⟳` is the time until a known limit reset; `Exp` is the plan expiry;
- `balance` is wallet credit; `used` is consumed credit; `today` and `30d` are
- today's and the last 30 days' API spend. Reset countdowns require gateway timing data.
- #### Custom gateway routes
- Gateways not covered by the built-in probes can use a custom route. See
- [Custom gateway routes](docs/en/custom-gateway-routes.md).
- ### Vision (cross-model image understanding)
- Lets a main model that cannot see images use a multimodal model to analyze error screenshots, implement UI from design mockups, and inspect bug-report screenshots.
- #### Install
- ```bash
- npx -y @kairyou/agent-tools@latest vision -a claude codex opencode pi zcode dsh
- ```
- Uninstalling keeps your vision provider config by default.
- #### Configure
- Configure `vision` in `~/.agent-tools/config.jsonc`:
- ```jsonc
- {
- "vision": {
- "provider": "openai-compatible", // or "anthropic-compatible"
- "baseUrl": "https://gateway.example.com/v1", // anthropic-compatible: gateway root, /v1/messages is appended
- "model": "internal-vlm",
- "apiKey": { "env": "OPENAI_API_KEY" } // read from the OPENAI_API_KEY environment variable
- // , "timeoutMs": 30000, "maxImageBytes": 20971520, "maxOutputTokens": 8192
- // , "maxConcurrentRequests": 2, "maxRequestsPerMinute": 30
- }
- }
- ```
- `apiKey` accepts a key string or an environment variable reference as above. Omit it for gateways that require no key.
- #### Use
- Pass a local image path or URL in your message. If the main model cannot accept
- pasted images, save the image first and pass its file path instead.
- To diagnose the provider setup or test recognition quality manually:
- ```bash
- npx -y @kairyou/agent-tools@latest inspect-image <path|url> -q "What are the navbar background color and height?"
- ```
- ## More tools and documentation
- - [Work utilities](docs/en/extras.md) — Work reports, session logs, and self-evaluations.
- - [Output speed](docs/en/output-speed.md)
- - [Repository structure](docs/en/repository-structure.md)
- ## FAQ
- ### Why does installing skills report PromptScript as unsupported?
- `PromptScript does not support global skill installation` applies only to
- PromptScript; installation for other agents is unaffected. See [`skills` issue #1352](https://github.com/vercel-labs/skills/issues/1352).
- ### How do I install skills without GitHub access?
- In Bash, install from the npm package (swap `at-commit` for the skills you want):
- ```bash
- cd "$(mktemp -d)" && tar -xf "$(npm pack @kairyou/agent-tools --silent)" && npx -y skills@latest add ./package --skill at-commit -g -y
- ```
- ## Acknowledgements
- - `at-commit` draws on commit-message generation ideas from
- [OpenCommit](https://github.com/di-sukharev/opencommit) and
- [GitLens](https://github.com/gitkraken/vscode-gitlens), reimplemented for an
- Agent Skill workflow.
- - `at-review` and `at-simplify` are installable Agent Skills derived and
- adapted from Claude Code's built-in `code-review` and `simplify` workflow
- prompts.
- The [sync workflow](tools/claude-skill-sync/README.md) describes how upstream prompts are tracked.
Version history
v0.27.011/18/2026
v0.26.011/11/2026
v0.24.010/28/2026
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.