briefbound-development-cleanup

briefbound-development-cleanup is a skill for Claude Code, Codex from CCDawn/codex-skills. It costs 71 tokens per session (1,625 once invoked), scanned A, original, MIT.

A cleanup procedure for finishing software tasks safely after a change has been verified or integrated. It covers temporary files, generated noise, task-owned processes, Git branches, worktrees, and task claims.

In plain words
What is it for?
Use it to audit and remove rebuildable local leftovers, stop processes started by the task, and decide whether branches or worktrees should be cleaned up, deferred, or retained.
Why use it?
It prevents useful work, user changes, or evidence from being deleted when it is unclear what belongs to the completed task. It also makes sure cleanup stays limited to items that can be proven safe to remove.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the briefbound-skills plugin — 30 skills shipped together

Install

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.

agentmods
npx agentmods add skills/ccdawn/codex-skills/briefbound-development-cleanup
Any agent
npx skills add CCDawn/codex-skills --skill briefbound-development-cleanup
Clone the repo
git clone --depth 1 https://github.com/CCDawn/codex-skills

Made for: Claude Code, Codex.

Or install briefbound-skills, the plugin that ships this one along with the rest of its 30 skills.

Wrote 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.

agentmods badge for briefbound-development-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-development-cleanup.svg)](https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-development-cleanup)
Your own site
<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>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash c059b2256377, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

skills/engineering/briefbound-development-cleanup/SKILL.md · 85 lines

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-loopbriefbound-thread-coordinationbriefbound-pr-reviewbriefbound-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。
  • 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.mdPR_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。

Read the full file on GitHub · 85 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 85 lines · 71 tokens per session scan A c059b2256377

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories