- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add hyhmrright/brooks-lint --skill brooks-harness -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add hyhmrright/brooks-lint --skill brooks-harness -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add hyhmrright/brooks-lint --skill brooks-harness -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add hyhmrright/brooks-lint --skill brooks-harness -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/hyhmrright/brooks-lint/tree/HEAD/.agents/skills/brooks-harness來自發布者
This skill orchestrates work on the brooks-lint repo itself. It runs a sequential
subagent pipeline: each stage is a dedicated agent defined in .codex/agents/.
Use the available Codex collaboration tools with the matching agent role; inherit
the parent model and permissions. If custom roles are not loaded, pass the role's
developer_instructions from its TOML file to a standard subagent. Stages run
sequentially. Every editing agent must preserve other contributors' changes and
own only the files assigned by the orchestrator.
[orchestrator]
Phase 0 context check
Phase 1 classify request → select stages
Phase 2 run selected stages in order, with a QA loop-back:
skill-author → eval-curator → consistency-qa ─(FAIL)→ back to author
│ PASS
▼
trigger-boundary-auditor (only if a description changed)
▼
release-manager (only if release requested)
Phase 3 report + collect feedback
Determine the run mode before doing anything:
_workspace/brooks-harness/ exists + maintainer asks to redo part of a prior run →
partial re-run: invoke only the affected stage(s), reusing prior notes._workspace/brooks-harness/ exists + a fresh request → new run: move the old
folder to _workspace/brooks-harness_prev/, start clean._workspace/brooks-harness/ → initial run: create it.Run notes and the QA report live under _workspace/brooks-harness/. The real
artifacts are the repo files themselves — agents edit skills/, evals/, manifests
directly; _workspace/ only holds the run's notes and the PASS/FAIL verdict for audit.
Pick the minimal set of stages. The QA stage is never skipped — every change is gated.
Spawn each selected stage as a subagent in order using Codex collaboration tools. Pass each agent (a) the task
contract and (b) the previous stage's summary. Agents write their summaries to
_workspace/brooks-harness/; read them between stages.
new-skill scaffold. Returns the list of files touched + convention-relevant
choices (new risk codes, new Step numbers, changed description trigger phrases).skill-author reported new/changed risk codes or modes, adds
the paired happy-path + false-positive scenarios and runs npm run evals.npm run validate + npm test +
npm run evals, then the cross-document sync checks (manifests, all version-bearing text files,
CHANGELOG, AGENTS/GEMINI book count, eval count). Writes a PASS/FAIL verdict.
On FAIL: loop back to the agent named in the verdict (author or eval-curator),
fix, then re-run QA. Repeat once; if it still fails, stop and report to the
maintainer.description field changed. It
read-only audits the six shipped skills' trigger surfaces for false-triggering and
routing collisions. Surface its findings; if it flags a real collision, loop back to
skill-author.release skill.Report: stages run, files changed, QA verdict, trigger-audit findings (if any), and the release URL (if any). Then offer the maintainer a feedback opening: "Anything to adjust in the result, the agent roles, or the pipeline order?" Record accepted changes in the AGENTS.md harness change-log table.
general-purpose (it runs npm scripts); the
trigger-boundary-auditor is read-only..agents/skills/.--no-verify, --force, history rewrites) require explicit
maintainer authorization — release-manager stops and asks.Normal flow — "add a brooks-security skill": Phase 1 selects author+eval+QA+audit.
skill-author runs new-skill brooks-security, creates SKILL.md (with a sibling-carving
"Do NOT trigger for:" clause) + guide; eval-curator adds an S-code happy-path + a
false-positive scenario; consistency-qa runs the gate → PASS; trigger-boundary-auditor
confirms no collision with brooks-review/audit. Report lists files + PASS.
Error flow — QA FAIL on book-count drift: maintainer adds a thirteenth book but
edits only source-coverage.md. consistency-qa's cross-doc check finds README still
says "twelve" → FAIL, attributed to skill-author. Orchestrator loops back; skill-author
updates README/AGENTS/GEMINI wording; QA re-runs → PASS. No release was requested, so
the pipeline ends at Phase 3.
>
---name: brooks-harnessdescription: >---# .agents/skills/brooks-harness/SKILL.md常見問題
從發布者下載 .agents/skills/brooks-harness/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/hyhmrright/brooks-lint。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。