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 instructions/ourines/worktree-task-plugin/claude-mdgit 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 | $0.00793 | $0.00793 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
worktree-task-plugin CLAUDE.md 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
A Claude Code plugin that enables spawning autonomous agent sessions in separate git worktrees via tmux. Manages large coding tasks that would otherwise overflow context by delegating phases to subagents.
Architecture
├── .claude-plugin/plugin.json # Plugin manifest (name, version, repo)
├── skills/worktree-task/SKILL.md # Auto-trigger skill definition
├── commands/*.md # Slash command definitions (/worktree-task:*)
├── hooks/
│ ├── hooks.json # Hook registrations (SessionStart, Stop, SessionEnd)
│ └── handlers/*.py # Hook implementations
├── scripts/*.py # Core Python scripts for task management
└── references/*.md # Prompt templates for spawned agents
Core Flow
- launch.py - Creates worktree + tmux session, launches agent (Claude Code or Codex), sends task prompt
- status.py - Captures tmux pane output, shows git info from worktree
- resume.py - Detects error type (rate_limit, api_error, timeout), sends recovery message
- cleanup.py - Kills tmux session, optionally removes worktree
- merge.py / rebase.py - Spawns Claude in tmux to auto-resolve git conflicts
Key Design Patterns
- tmux as state: Sessions track running tasks, pane capture provides status
- Worktrees for isolation: Each task gets its own working directory
- Template substitution:
$TASK_DESCRIPTION,$WORKTREE_DIRinreferences/*.md - Hook-based updates:
on-session-start.pychecks GitHub Releases API for updates (24h cache)
Common Commands
# Test a script directly
python3 scripts/launch.py feature/test "Test task description"
python3 scripts/status.py # List all sessions
python3 scripts/status.py <session-name> # Detailed session status
python3 scripts/resume.py <session> --check # Check without sending message
python3 scripts/cleanup.py <session> --remove-worktree
# Manual tmux operations
tmux list-sessions
tmux attach -t <session>
tmux kill-session -t <session>
# Git worktree operations
git worktree list
git worktree remove <path>
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 · 84 lines · 793 tokens per session scan A 4078eb57f7fa
worktree-task-plugin CLAUDE.md is an instructions file published in the GitHub repository ourines/worktree-task-plugin (39 stars, last pushed 8mo ago), licensed MIT. It adds 793 tokens to every session, about $0.0040 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.