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.
git clone --depth 1 https://github.com/jjmartres/ai-coding-agentsWrote 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/commands/jjmartres/ai-coding-agents/worktree)<a href="https://agentmods.dev/commands/jjmartres/ai-coding-agents/worktree"><img src="https://agentmods.dev/badge/commands/jjmartres/ai-coding-agents/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/commands/jjmartres/ai-coding-agents/worktree"><img src="https://agentmods.dev/badge/commands/jjmartres/ai-coding-agents/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 | $0.00020 | $0.00351 |
| Opus 5.5 | $0.00008 | $0.00140 |
| Sonnet 5.5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
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 18d 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.
What it actually says
Worktree Manager Command
Unified command to manage isolated git worktrees in .worktree/ and handle session relocations.
Syntax
/worktree <action> [options]
/worktree create <branch>: Creates.worktree/<branch>and relocates OpenCode session./worktree list: Lists all active worktrees and PR/MR status./worktree delete <branch>: Removes a specific worktree and prunes branch./worktree cleanor/worktree delete --merged: Cleans up all worktrees whose PR/MR is merged.
Instructions for Agent
- Parse action from
$ARGUMENTS:- If action is
createor starts withadd/new:- Delegate to
/worktree.createworkflow with remaining arguments.
- Delegate to
- If action is
listorlsor empty:- Delegate to
/worktree.listworkflow.
- Delegate to
- If action is
delete,rm,remove:- Delegate to
/worktree.deleteworkflow with remaining arguments.
- Delegate to
- If action is
clean,prune,clean-merged, ormerged:- Delegate to
/worktree.delete --mergedworkflow.
- Delegate to
- If an argument is given without an action verb (e.g.
/worktree feature-foo):- Check if it matches an existing worktree -> switch session there using
tools.opencode.session_move. - Otherwise, assume creation -> run
/worktree.createworkflow.
- Check if it matches an existing worktree -> switch session there using
- If action is
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.
- 18d ago First seen · 34 lines · 20 tokens per session scan A 107d57e592e6
worktree is a command published in the GitHub repository jjmartres/ai-coding-agents (49 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 351 once invoked, about $0.0001 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 2026-09-28.
Other commands, from other repositories
resolve-review
Resolve reviewer feedback - from GitHub PRs, chat, or any reviewer.
make-pr
Commit staged changes, create or update a pull request.
publish
Release a new package version — semver bump from commits, tag, registry publish, GitHub Release.
bump
Full dependency and toolchain bump — deps to latest major, Node pins, GitHub Actions, audit, validate, commit.
rebase
Rebase the current branch on main, a local branch, or a remote branch (with fetch).
ship
Commit all changes and push to remote.