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 hashgraph-online/awesome-codex-plugins --skill git-worktree-isolationgit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWrote 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/hashgraph-online/awesome-codex-plugins/git-worktree-isolation)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/git-worktree-isolation"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/git-worktree-isolation/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/hashgraph-online/awesome-codex-plugins/git-worktree-isolation"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/git-worktree-isolation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01464 |
| Opus 5 | $0.00044 | $0.00732 |
| Sonnet 5 | $0.00018 | $0.00293 |
| Haiku 4.5 | $0.00009 | $0.00146 |
Grade A, and why
git-worktree-isolation 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 3d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktree Isolation
用途
- 确保每个开发任务(feature / fix / spike)在 隔离的 worktree + 分支 中执行,主工作区始终保持可切换状态。
- 在多 agent 并行场景下,每个 agent 拥有独立文件系统视图,避免写冲突。
- 任务完成后提供 结构化收口决策(merge / PR / keep / discard),而不是任凭 worktree 积累。
触发信号
/team-execute分派的并行实现任务。wave-execution中同一 Wave 的多个工作项。- 需要在不影响主分支的情况下进行探索性实现或 spike。
- 当前工作区有未提交变更,但需要紧急处理另一个任务。
- Code review 后的修改需要在隔离环境中完成。
核心原则
- 一个任务 = 一个 worktree = 一个分支——不共用 worktree。
- worktree 有明确生命周期——创建时绑定任务 ID,完成后必须做收口决策。
- 主工作区是调度中心——编排和合并在主工作区进行,实现在 worktree 中进行。
工作流
1. 创建隔离环境
# 命名规则: .worktrees/{slug}-{task-id}
git worktree add .worktrees/{slug}-{task-id} -b task/{slug}/{task-id}
# 验证隔离
cd .worktrees/{slug}-{task-id}
git branch --show-current # → task/{slug}/{task-id}
命名约定:
| 元素 | 格式 | 示例 |
|---|---|---|
| Worktree 路径 | .worktrees/{slug}-{task-id} |
.worktrees/auth-T001 |
| 分支名 | task/{slug}/{task-id} |
task/auth/T001 |
| Spike 分支 | spike/{slug}/{description} |
spike/auth/oauth-flow |
2. 在 worktree 中执行
进入 worktree 目录 →
加载任务上下文(STATE.md 对应工作项)→
执行实现 →
运行测试 →
提交到 worktree 分支
执行约束:
- 每个 worktree 中的 agent 只操作任务范围内的文件。
- 不在 worktree 中修改共享配置(package.json / pom.xml 等),除非任务明确要求。
- 提交信息包含任务 ID:
feat(T001): implement auth flow。
3. 收口决策
任务完成后,在 主工作区 执行收口:
| 决策 | 条件 | 操作 |
|---|---|---|
| Merge | 代码通过 review + 测试 | git merge task/{slug}/{task-id} + 清理 worktree |
| PR | 需要异步 review 或 CI | 创建 PR + 保留 worktree 直到合并 |
| Keep | 任务暂停但稳定 | 标记为 paused,保留 worktree |
| Discard | spike 完成或方向废弃 | 删除 worktree + 分支 |
# Merge 路径
cd /path/to/main-worktree
git merge --no-ff task/{slug}/{task-id} -m "feat(T001): implement auth flow"
git worktree remove .worktrees/{slug}-{task-id}
git branch -d task/{slug}/{task-id}
# Discard 路径
git worktree remove --force .worktrees/{slug}-{task-id}
git branch -D spike/{slug}/{description}
4. 清理巡检
定期(或每次 /team-review 前)执行清理:
# 列出所有 worktree
git worktree list
# 清理已删除的 worktree 引用
git worktree prune
# 查找已合并但未清理的任务分支
git branch --merged main | grep 'task/'
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.
- 3d ago First seen · 138 lines · 88 tokens per session scan A c4d125f82d1b
git-worktree-isolation is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (956 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 1,464 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 2026-09-05.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
review-prs
Triage open PRs — screen from the diff, delegate the admission judgment to audit-the-list, then merge or close on GitHub. Fire when the maintainer asks to review PRs, process the PR queue, or judge whether a specific PR should be merged.
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
git-github-flow
Use for branch prep, clean commits, PR descriptions, GitHub issue triage, changelogs, release notes, review response, merge readiness, or publishing a branch safely.
feature-spec
Kicks off a new feature by finding the next incomplete phase in specs/roadmap.md, creating a git branch, interviewing the user about scope/decisions/context, and writing a dated spec directory under specs/ containing plan.md, requirements.md, and validation.md. Trigger when the user says "feature spec", "next phase"…