Skip to content
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
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/kairyou--agent-tools/badge.svg)](/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
  1. {
  2. "name": "agent-tools",
  3. "version": "0.27.0",
  4. "description": "Reusable Agent Skills from agent-tools",
  5. "author": {
  6. "name": "kairyou"
  7. },
  8. "skills": [
  9. "./skills/workflow/at-commit",
  10. "./skills/workflow/at-daily-log",
  11. "./skills/workflow/at-review",
  12. "./skills/workflow/at-self-eval",
  13. "./skills/workflow/at-simplify",
  14. "./skills/systems/at-zentao"
  15. ],
  16. "license": "MIT"
  17. }
README.md · README · 270 lines
  1. # Agent Tools
  2. Reusable Agent Skills for compatible coding agents, plus per-agent runtime capabilities for statusline, provider usage, vision, and session logging.
  3. Requires Node.js >= 22.
  4. [中文](README.zh-CN.md)
  5. ## Skills
  6. ### Install
  7. ```bash
  8. # List available skills
  9. npx -y skills@latest add kairyou/agent-tools --list
  10. # Install globally (pass one or more names after --skill)
  11. npx -y skills@latest add kairyou/agent-tools --skill <name...> -g -y
  12. ```
  13. The Skills installer automatically detects and installs to the Skill directories
  14. of most supported agents.
  15. ### at-commit
  16. Generate a Conventional Commits message from staged changes and wait for user confirmation before committing.
  17. ```bash
  18. npx -y skills@latest add kairyou/agent-tools --skill at-commit -g -y
  19. ```
  20. Usage:
  21. - `/at-commit [<language>]` — language for the commit description (Conventional Commits tokens stay in English)
  22. ### at-review
  23. Review local changes or a hosted PR/MR for correctness bugs, regressions, convention violations, and high-value cleanup findings.
  24. ```bash
  25. npx -y skills@latest add kairyou/agent-tools --skill at-review -g -y
  26. ```
  27. Usage:
  28. - `/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
  29. ### at-simplify
  30. Refactor changes to reduce duplication, lower complexity, and improve code quality.
  31. ```bash
  32. npx -y skills@latest add kairyou/agent-tools --skill at-simplify -g -y
  33. ```
  34. Usage:
  35. - `/at-simplify [<pr|branch|path>]`
  36. ### at-zentao
  37. 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.
  38. ```bash
  39. npx -y skills@latest add kairyou/agent-tools --skill at-zentao -g -y
  40. ```
  41. Usage:
  42. - `/at-zentao bugs` — list bugs assigned to you (the configured account); pick one or several (several = batch mode)
  43. - `/at-zentao tasks` — same, for tasks
  44. - `/at-zentao bug <id>` — work a specific bug
  45. - `/at-zentao task <id> [request]` — work a task, start/pause/resume it, or log hours with a natural-language request
  46. - `/at-zentao story <id>` — read requirement scope and acceptance context without writing back
  47. Configure `~/.agent-tools/config.jsonc`:
  48. ```jsonc
  49. {
  50. "zentao": {
  51. "url": "https://zentao.example.com",
  52. "account": "user",
  53. "password": "your-password",
  54. // "password": { "env": "ZENTAO_PASSWORD" }, // Or read the password from an environment variable.
  55. // Optional. Without this, labels follow the item or user's language.
  56. // "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."
  57. }
  58. }
  59. ```
  60. ## Capabilities
  61. Runtime capabilities, installed per agent:
  62. ```bash
  63. npx -y @kairyou/agent-tools@latest <capability> -a <agent...>
  64. # npx -y github:kairyou/agent-tools <capability> -a <agent...> # Or the latest code from GitHub (needs Git)
  65. ```
  66. `--dry-run` previews, `--uninstall` removes the capability from the agent, and
  67. re-running the install command updates. Updates to `config.jsonc` add missing
  68. defaults while preserving your values and comments.
  69. | Runtime capability | Supported agents |
  70. | --- | --- |
  71. | `statusline` | Claude Code |
  72. | `usage` | Claude Code, Codex, OpenCode, Pi |
  73. | `vision` | Claude Code, Codex, OpenCode, Pi, ZCode, DeepSeek Harness |
  74. | `log` | Claude Code, Codex, OpenCode, Pi |
  75. ### Statusline
  76. ```bash
  77. npx -y @kairyou/agent-tools@latest statusline -a claude
  78. ```
  79. The installer writes `statusLine` to `~/.claude/settings.json`. Example output:
  80. ```text
  81. # Claude subscription:
  82. ⎇ main | Opus 4.8 | 5h 7% ⟳ 2h54m | w 41% ⟳ 3d1h
  83. # API relay:
  84. ⎇ main | Opus 4.8 | balance $362 | today $61.7 | 30d $566
  85. ```
  86. `5h` / `w`: Claude's rolling 5-hour / 7-day usage windows; `⟳`: time until reset.
  87. Set visible fields and order via `statusline.fields` in `~/.agent-tools/config.jsonc`;
  88. add `"outputSpeed"` for estimated output speed (e.g. `38.2 tok/s`).
  89. For supported relay gateways and usage configuration, see [Provider usage](#provider-usage).
  90. ### Provider usage
  91. Shows API relay / gateway balance and quota inside the agent. Supports Sub2API,
  92. One API (including OneHub and DoneHub), New API, Claude Code Hub, OpenRouter, and
  93. Command Code; compatibility depends on the gateway version and enabled usage
  94. endpoints.
  95. ```bash
  96. npx -y @kairyou/agent-tools@latest usage -a claude codex opencode pi
  97. ```
  98. - **Claude Code** — `/at-usage` shows usage in chat; installing `statusline` also adds it to the status line.
  99. Set `statusline.showProviderUsage` to `false` to hide relay gateway usage from the status line.
  100. - **Codex** — run `/hooks` once after installation to approve it. The Codex CLI
  101. displays usage automatically; clients that hide hook output can use `$at-usage`.
  102. - **OpenCode** — usage refreshes when the session goes idle and appears as a
  103. toast; `/at-usage` shows it on demand. Restart opencode after installing or updating.
  104. - **Pi** — displays usage in the footer. Restart Pi or run `/reload` after installing or updating.
  105. The endpoint and key come from the agent's current model or existing configuration;
  106. official endpoints are skipped. If it reports
  107. `Provider usage is unavailable.`, set `PROVIDER_USAGE_BASE_URL` and
  108. `PROVIDER_USAGE_API_KEY` to override the endpoint and key. Configure
  109. `providerUsage` in `~/.agent-tools/config.jsonc` only when needed:
  110. ```jsonc
  111. {
  112. "providerUsage": {
  113. // auto | sub2api | openai-compatible | one-api | one-hub |
  114. // done-hub | new-api | claude-code-hub | openrouter | commandcode | <custom-route-id>
  115. "preset": "auto", // auto-detect, or select one protocol listed above
  116. "days": 30, // how many recent days of spend to count
  117. "outputSpeed": false, // true: show estimated output speed (tok/s)
  118. "debug": false // true: log probes to ~/.agent-tools/logs/usage-debug.log
  119. }
  120. }
  121. ```
  122. Output examples:
  123. ```text
  124. # Plan limits:
  125. D $0.0/$100 | W $0.0/$300 ⟳ 3d1h | Exp 07-08
  126. # Multi-window limits:
  127. 5h $2.1/$10.0 | D $8.0/$20.0 | T $19.0/$100 | Exp 08-31
  128. # Balance and usage:
  129. balance $15.0 | used $5.0/$20.0 | ⟳ 3d1h
  130. # Wallet and recent spend:
  131. balance $362 | today $61.7 | 30d $566
  132. ```
  133. Fields: `5h/D/W/M/T` are five-hour/daily/weekly/monthly/total spend against
  134. limits; `⟳` is the time until a known limit reset; `Exp` is the plan expiry;
  135. `balance` is wallet credit; `used` is consumed credit; `today` and `30d` are
  136. today's and the last 30 days' API spend. Reset countdowns require gateway timing data.
  137. #### Custom gateway routes
  138. Gateways not covered by the built-in probes can use a custom route. See
  139. [Custom gateway routes](docs/en/custom-gateway-routes.md).
  140. ### Vision (cross-model image understanding)
  141. 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.
  142. #### Install
  143. ```bash
  144. npx -y @kairyou/agent-tools@latest vision -a claude codex opencode pi zcode dsh
  145. ```
  146. Uninstalling keeps your vision provider config by default.
  147. #### Configure
  148. Configure `vision` in `~/.agent-tools/config.jsonc`:
  149. ```jsonc
  150. {
  151. "vision": {
  152. "provider": "openai-compatible", // or "anthropic-compatible"
  153. "baseUrl": "https://gateway.example.com/v1", // anthropic-compatible: gateway root, /v1/messages is appended
  154. "model": "internal-vlm",
  155. "apiKey": { "env": "OPENAI_API_KEY" } // read from the OPENAI_API_KEY environment variable
  156. // , "timeoutMs": 30000, "maxImageBytes": 20971520, "maxOutputTokens": 8192
  157. // , "maxConcurrentRequests": 2, "maxRequestsPerMinute": 30
  158. }
  159. }
  160. ```
  161. `apiKey` accepts a key string or an environment variable reference as above. Omit it for gateways that require no key.
  162. #### Use
  163. Pass a local image path or URL in your message. If the main model cannot accept
  164. pasted images, save the image first and pass its file path instead.
  165. To diagnose the provider setup or test recognition quality manually:
  166. ```bash
  167. npx -y @kairyou/agent-tools@latest inspect-image <path|url> -q "What are the navbar background color and height?"
  168. ```
  169. ## More tools and documentation
  170. - [Work utilities](docs/en/extras.md) — Work reports, session logs, and self-evaluations.
  171. - [Output speed](docs/en/output-speed.md)
  172. - [Repository structure](docs/en/repository-structure.md)
  173. ## FAQ
  174. ### Why does installing skills report PromptScript as unsupported?
  175. `PromptScript does not support global skill installation` applies only to
  176. PromptScript; installation for other agents is unaffected. See [`skills` issue #1352](https://github.com/vercel-labs/skills/issues/1352).
  177. ### How do I install skills without GitHub access?
  178. In Bash, install from the npm package (swap `at-commit` for the skills you want):
  179. ```bash
  180. cd "$(mktemp -d)" && tar -xf "$(npm pack @kairyou/agent-tools --silent)" && npx -y skills@latest add ./package --skill at-commit -g -y
  181. ```
  182. ## Acknowledgements
  183. - `at-commit` draws on commit-message generation ideas from
  184. [OpenCommit](https://github.com/di-sukharev/opencommit) and
  185. [GitLens](https://github.com/gitkraken/vscode-gitlens), reimplemented for an
  186. Agent Skill workflow.
  187. - `at-review` and `at-simplify` are installable Agent Skills derived and
  188. adapted from Claude Code's built-in `code-review` and `simplify` workflow
  189. prompts.
  190. 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 in

Free to use. If it’s helped, pass it on.