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/ourines/worktree-task-plugin/worktree-tasknpx skills add ourines/worktree-task-plugin --skill worktree-taskgit clone --depth 1 https://github.com/ourines/worktree-task-pluginWhat 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 | $0.00070 | $0.00870 |
| Opus 5 | $0.00035 | $0.00435 |
| Sonnet 5 | $0.00014 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
worktree-task 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Task Manager
This skill manages large coding tasks by spawning autonomous agent instances (默认 Claude Code，可选 --codex/--agent-cmd) in separate git worktrees via tmux sessions.
When to Use
- User wants to execute a large task (>20 subtasks) without blocking current session
- User mentions "background", "parallel", "worktree", or "autonomous" execution
- Task involves creating a new service, major refactoring, or implementing complex features
- User wants to continue other work while a large task runs
Available Commands
Use these slash commands for precise control:
| Command | Description |
|---|---|
/worktree:launch |
Launch a new background task |
/worktree:status |
Check status of all or specific tasks |
/worktree:resume |
Resume an interrupted task |
/worktree:cleanup |
Clean up completed tasks |
Core Workflow
1. Launch a Task
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/launch.py <branch-name> "<task-description>"
Example:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/launch.py feature/my-task "Execute the task: implement new feature. Read the tasks.md and implement all phases."
The script will:
- Verify git status is clean (or prompt to commit/stash)
- Create a git worktree with the specified branch
- Create a tmux session
- Launch Claude Code by default (use
--codexfor default Codex command or--agent-cmdto switch, e.g.,codex --yolo -m gpt-5.1-codex-max -c model_reasoning_effort="high") - Send the task with instructions to use Task tool for each phase
2. Monitor Progress
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/status.py [session-name]
Without arguments, lists all active sessions. With a session name, shows detailed status.
3. Resume an Interrupted Task
If a task is interrupted (rate limit, API error, timeout):
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/resume.py <session-name> [message]
Options:
--retry- Retry the last failed task--check- Only check status, don't send message
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.
- 2d ago First seen · 103 lines · 70 tokens per session scan A 9c944eb2ee83
worktree-task is a skill published in the GitHub repository ourines/worktree-task-plugin (39 stars, last pushed 8mo ago), licensed MIT. It adds 70 tokens to every session and 870 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…