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 commands/ourines/worktree-task-plugin/helpgit 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 | $0.00007 | $0.00545 |
| Opus 5 | $0.00003 | $0.00272 |
| Sonnet 5 | $0.00001 | $0.00109 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
help 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 yesterday.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Task Plugin Help
A plugin for managing large coding tasks using git worktrees and background Claude Code sessions.
Commands
| Command | Description |
|---|---|
/worktree-task:launch <task> |
Launch a new background task in a separate worktree |
/worktree-task:status [name] |
Check status of all or specific task |
/worktree-task:resume <name> |
Resume an interrupted task |
/worktree-task:cleanup <name> |
Clean up completed task and worktree |
/worktree-task:merge <branch> |
Merge a feature branch into current branch |
/worktree-task:rebase <branch> |
Rebase current branch onto a feature branch |
/worktree-task:help |
Show this help message |
Quick Start
# 1. Launch a complex task in the background
/worktree-task:launch "Implement user authentication with OAuth2"
# 2. Check progress
/worktree-task:status
# 3. When done, merge the changes
/worktree-task:merge feature-auth
# 4. Clean up
/worktree-task:cleanup feature-auth
How It Works
- Launch creates a git worktree (isolated copy of your repo) and spawns a Claude Code instance in a tmux session
- Monitor via
/worktree-task:statusto see progress, logs, and completion state - Resume if task gets interrupted (rate limits, API errors, network issues)
- Merge/Rebase with automatic conflict resolution powered by Claude
- Cleanup removes the tmux session and worktree when done
Best Practices
- Use for tasks that take 10+ minutes or require extensive changes
- Keep task descriptions clear and specific
- Check status periodically to monitor progress
- Use
--keep-worktreewith cleanup if you want to review changes first
File Locations
- Worktrees: Created in parent directory of your repo (e.g.,
../worktree-task-<name>) - Task prompts:
/tmp/claude_task_prompt.txt(temporary) - Monitor logs:
<plugin-dir>/.monitor_cron.log
Requirements
- macOS (for notifications)
- tmux
- git
- Python 3.8+
Links
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.
- yesterday First seen · 70 lines · 7 tokens per session scan A dbdb1ec7b71a
help is a command published in the GitHub repository ourines/worktree-task-plugin (39 stars, last pushed 8mo ago), licensed MIT. It adds 7 tokens to every session and 545 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.