Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ccdawn/codex-skills/briefbound-development-cleanupnpx skills add CCDawn/codex-skills --skill briefbound-development-cleanupgit clone --depth 1 https://github.com/CCDawn/codex-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-development-cleanup)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-development-cleanup"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-development-cleanup.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.01625 |
| Opus 5 | $0.00036 | $0.00813 |
| Sonnet 5 | $0.00014 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00162 |
Grade A, and why
briefbound-development-cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefbound Development Cleanup
目标
保护未合并工作和证据,清掉可证明噪音并收尾 branch、worktree 与 claim。
无法证明“可重建、已吸收、无 owner”就保留;清理不扩大范围。
Briefbound task contract
- Context Boundary: 真实根目录、实现范围、验证、Git target/base/head、working tree、残留、task-owned PID/listener、worktree、claim 和清理授权。
- Output Contract:
CLEAN / NOOP / DEFERRED_INTEGRATION / BLOCKED、已删除项、保留项、延后条件、清理后证据和 Route Out。 - Allowed Action: 先只读审计;只删除已证明属于本轮且可重建的本地残留,只停止已证明由本任务启动或依赖的精确进程树。删除本地 branch/worktree 需用户明确清理、项目长期策略,或同一任务“完成开发到 PR”许可且已验证 PR 合并。远程分支、push、合并、发布和无法归属的文件或进程不自动处理。
- Success Evidence: 清理后 Git、worktree 和 registry 符合预期;源码、用户改动、未合并提交和必要证据仍在。
- Stop Condition: 根目录或 integration target 不明、工作区 dirty 且归属不清、process owner 或 data root 不明、branch 未吸收、worktree 被占用、claim 仍 active、路径安全无法证明、删除需要远程或 force 动作。
- Route Out: 当前开发 owner、
briefbound-autonomous-collaboration-loop、briefbound-thread-coordination、briefbound-pr-review、briefbound-router或 BLOCKED。
统一调用契约
- 只处理 Briefbound task contract 范围;不匹配时回
briefbound-router或更具体 owner,复合任务不吞其他 owner。 - 用户可见内容默认中文,完成只报状态、产出、证据和剩余风险;代码、命令、路径、错误原文、API/协议、skill 名和枚举保留原样;Route Out 仅以 Briefbound task contract 为准,末行写
下一步建议: <一个具体动作>。
进入时机
- 只有当前任务已知创建了临时产物、任务专用缓存、scratch 文件、后台进程/listener、claim、feature branch/worktree,或用户明确要求清理时,才做静默清理检查并加载本 skill。
- 没有已知候选时直接收口,不扫描全仓寻找可能的噪音,也不输出
NOOP。 - 合并前清理开发残留,但保留仍用于 PR/合并的 branch/worktree,状态为
DEFERRED_INTEGRATION;合并后再次收尾这些 Git 资源。 - 纯规划、只读审查、研究归档或未验证开发不进入删除阶段。
- 由
briefbound-autonomous-collaboration-loop调用时,沿用其本轮安全本地清理授权;已证明被本地main吸收的任务 branch/worktree 和已完成 claim 不再逐项询问。
Post-PR Closeout Gate
同一任务 PR 读取 references/post-pr-closeout.md:PR_OPEN 关闭空闲 claim 并保留 Git 现场,PR_MERGED 验证吸收后本地收尾,PR_CLOSED_UNMERGED 保留工作;远程分支删除必须单独授权。
审计与分类
先确认真实 repo root、当前 branch、integration target 和本轮 owned surface,再读取:
git status --short --branch、相关 diff、untracked/ignored 候选;git worktree list --porcelain和本地分支占用;git merge-base --is-ancestor <branch-tip> <target>或等价吸收证据;- coordination registry 中的 Agent/claim 状态;
- 项目规则、官方 closeout 命令和 Windows junction/reparse point。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 85 lines · 71 tokens per session scan A c059b2256377
briefbound-development-cleanup is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 24d ago), licensed MIT. It adds 71 tokens to every session and 1,625 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.
using-git-worktrees
当需要开始与当前工作区隔离的功能开发,或在执行实现计划之前使用——通过原生工具或 git worktree 回退机制确保隔离工作区存在.
finishing-a-development-branch
当实现完成、所有测试通过、需要决定如何集成这份工作时使用.
release-notes
Draft user-facing release notes from a git log range. Trigger when the user asks for "release notes", "changelog entry", or "what shipped this week" with a git ref range. Output is markdown sections grouped by Features / Fixes / Breaking with PR links.
chinese-commit
写 git commit 时使用。生成规范的 Conventional Commits(英文 type + 中文主题),主题精炼。.