Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add johardi/claude-stack/plugin install cstack-collabWrote 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/johardi/claude-stack/list-worktrees)<a href="https://agentmods.dev/skills/johardi/claude-stack/list-worktrees"><img src="https://agentmods.dev/badge/skills/johardi/claude-stack/list-worktrees/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/johardi/claude-stack/list-worktrees"><img src="https://agentmods.dev/badge/skills/johardi/claude-stack/list-worktrees.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 | $0.00119 | $0.00736 |
| Opus 5.5 | $0.00048 | $0.00294 |
| Sonnet 5.5 | $0.00024 | $0.00147 |
| Haiku 4.5 | $0.00012 | $0.00074 |
Grade A, and why
list-worktrees scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List Worktrees
A read-only inventory of Claude agent worktrees — the worktrees created by Agent({isolation: "worktree"}) or by cstack-collab orchestration. Used to figure out which worktrees exist before deciding what to do with them (handoff from inside, reclaim from outside).
When to Use
Use when:
- The user types
/cstack-collab:list-worktrees. - The user asks for an overview: "what agents are running", "which branches are stuck", "show me the worktrees", "what's holding feature/X".
- Before invoking
handofforreclaimand the user hasn't named a specific worktree — list first, then ask.
Skip when:
- The user already named a specific branch / agent id and just wants to act on it. Go straight to
worktree.py inspector tohandoff/reclaim.
How to Run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/worktree.py" list
Or, for downstream scripting:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/worktree.py" list --json
Output shape (human-readable):
agent-<id>
path: <absolute path>
branch: <branch name or "(detached)">
lock: unlocked | locked (pid N alive) | locked (pid N dead — stale lock)
state: clean | dirty | N unpushed | combinations
The script ignores plain user-created worktrees — only worktrees that carry the claude agent <id> lock marker or the CLAUDE_BASE file are listed.
Interpreting the Output
| Lock | State | Recommendation |
|---|---|---|
| live PID | clean | Agent is working normally. Leave it alone. |
| live PID | dirty / unpushed | If the user wants to take the branch over: type /cstack-collab:handoff in that agent's session. Don't reclaim — it would kill the agent. |
| stale PID | clean | Safe to /cstack-collab:reclaim without flags. |
| stale PID | dirty / unpushed | /cstack-collab:reclaim (default --stash) preserves the work to a recovery ref. |
| unlocked | any | The harness has already released this. Reclaim removes the directory; nothing else to clean up. |
Don't
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.
- 1mo ago First seen · 59 lines · 119 tokens per session scan A 6a66de53daa3
list-worktrees is a skill published in the GitHub repository johardi/claude-stack (2 stars, last pushed 5mo ago), licensed MIT. It adds 119 tokens to every session and 736 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.