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 skills add midFang/ai-agent-skills-workflow --skill bugfix-worktreegit clone --depth 1 https://github.com/midFang/ai-agent-skills-workflowWrote 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/midfang/ai-agent-skills-workflow/bugfix-worktree)<a href="https://agentmods.dev/skills/midfang/ai-agent-skills-workflow/bugfix-worktree"><img src="https://agentmods.dev/badge/skills/midfang/ai-agent-skills-workflow/bugfix-worktree/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/midfang/ai-agent-skills-workflow/bugfix-worktree"><img src="https://agentmods.dev/badge/skills/midfang/ai-agent-skills-workflow/bugfix-worktree.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00144 | $0.04686 |
| Opus 5.5 | $0.00058 | $0.01874 |
| Sonnet 5.5 | $0.00029 | $0.00937 |
| Haiku 4.5 | $0.00014 | $0.00469 |
Grade A, and why
bugfix-worktree 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 1mo 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bugfix Worktree
目的
建立一个半自动 bug 修复流程:一个 bug 对应一个分支、一个 worktree、一个独立修复窗口。
issues/<版本>/*.csv 是任务控制表,放在要修复的业务项目根目录里,例如 /path/to/business-project/issues/2026-06-25-test/bug_batch.csv。它不要放进任何单个 bug 的 worktree,也不要放到全局 skill 项目里。
单个 bug 的详细过程记录放在外部版本目录,例如 issues/<版本>/tasks/BUG-013-TASK.md。不要只放在 worktree 里,因为 worktree 是临时代码现场,合并后还可能需要回看任务记录。
这个 skill 不负责把模糊 bug 猜成真相。优先使用用户已经人工确认过的描述和明确的验证方法。
职责边界:本 skill 主要负责领取 bug、创建 worktree、修复、AI 自证验证、构建待验证 APK、按需安装。用户验证通过后的合并和 worktree 清理,优先交给 $bugfix-done。
Issues 表
推荐文件位置:
issues/<版本>/bug_batch.csv
例如:
issues/2026-06-24/bug_batch.csv
推荐列:
bug_id标题或title问题描述人工确认描述状态branchworktree_pathbase_repotarget_branch复现场景验收标准ai_verify_planai_verify_cmdai_verify_resultai_verify_evidenceapk_pathinstall_devicehuman_verify_resulthuman_verify_notecommittask_file备注
推荐状态:
draft, ready, needs_info, in_progress, fixed, ai_verified, apk_built, installed, human_verified, merged, integration_verified, worktree_removed, blocked
如果 CSV 缺少流程列,先备份,再补列。保留原始 bug 字段,不要破坏用户从腾讯文档导出的内容。
写入 CSV 前,在同目录创建简单锁文件,例如 <csv>.lock。如果锁文件很新,停止并提示可能有另一个窗口正在更新。只有确认锁已陈旧时,才说明原因后移除。
准备阶段
$bugfix-worktree 不应该在真正开始修 bug 时才频繁追问用户。应在从 $bug2csv 导出文件生成 issues/<版本>/bug_batch.csv 时,先把每条 bug 整理到可执行状态。
准备阶段推荐做法:
- 保留原始
问题描述。 - 用户或 AI 补充
人工确认描述,尽量写清楚真实复现过程。 - AI 根据人工确认描述生成
复现场景和验收标准草案。 - 用户只需要确认明显不对或缺关键条件的行。
- 信息足够开始修的行标记为
ready。 - 信息明显不足、会导致 AI 猜测的行标记为
needs_info,先不要领取修复。
字段含义:
复现场景:这个 bug 在什么条件下发生。写设备、系统、账号状态、连接方式、前置操作等。它回答“在哪里、怎么触发”。验收标准:修好后怎样算通过。写可观察结果,例如“只出现一个弹窗”“点击后跳到系统权限页”“PC 端持续有声音”。它回答“怎么判断修好了”。
示例:
bug_id,人工确认描述,复现场景,验收标准,状态
BUG-013,等待接收设备同意超时会出现两个弹窗,安卓发起端向 PC 接收端发起投屏,PC 不点击同意,等待请求超时,超时后安卓端只出现一个超时提示,不同时出现普通超时弹窗和连接失败超时弹窗,ready
单 bug TASK 文件
每个 bug 必须维护一个单 bug 过程记录文件,放在当前版本目录:
issues/<版本>/tasks/<bug_id>-TASK.md
例如:
issues/2026-06-24/tasks/BUG-013-TASK.md
What ships with it
1 file 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.
- 1mo ago First seen · 402 lines · 144 tokens per session scan A 6b2b8a5498d7
bugfix-worktree is a skill published in the GitHub repository midFang/ai-agent-skills-workflow (2 stars, last pushed 4mo ago), licensed MIT. It adds 144 tokens to every session and 4,686 once invoked, about $0.0006 per session on Opus 5.5. 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
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
enable-check-includes-strict
Enable and migrate Chromium targets and directories to checkincludesstrict = true, diagnosing and resolving header include violations as part of the checkincludesstrict LSC. Use when adding directories to the allowlist, enabling strict header checks on targets, or resolving CHECKINCLUDESSTRICTUNTRIAGED targets.
resolve-handoff
Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
cy-orquestrate-issue
Orchestrate GitHub bug resolution through a new CompozyOS managed worktree and Claude Opus 5.5 Medium session per issue. Investigate reported bugs, create missing issues, and dispatch an executor responsible for a detailed PR, green CI, and all CodeRabbit and Greptile feedback. Use when asked to delegate issue…