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/lexfrei/ccc/worktree-sweepnpx skills add lexfrei/ccc --skill worktree-sweepgit clone --depth 1 https://github.com/lexfrei/cccWrote 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/lexfrei/ccc/worktree-sweep)<a href="https://agentmods.dev/skills/lexfrei/ccc/worktree-sweep"><img src="https://agentmods.dev/badge/skills/lexfrei/ccc/worktree-sweep.svg" alt="Measured on agentmods" 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 | $0.00095 | $0.01285 |
| Opus 5 | $0.00048 | $0.00642 |
| Sonnet 5 | $0.00019 | $0.00257 |
| Haiku 4.5 | $0.00010 | $0.00128 |
Grade A, and why
worktree-sweep 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 3d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find and remove stale git worktrees, then report reclaimed space.
Operates in report → confirm → execute order. Nothing is removed until the user approves the plan. After approval, perform the removals autonomously. Choices are gathered through interactive questions, not flags.
Step 0: Determine the scan scope (never hardcode paths)
Resolve where to look, in this priority order:
- A path passed in
$ARGUMENTS— use it verbatim as the scan root. - Otherwise, if the current working directory is inside a git repository, ask the user (interactive question) which scope to use:
- this repository only — the repo the current directory belongs to;
- all repositories under the clone root — find the hosting root by walking up to the common ancestor that contains many
<owner>/<repo>directories, and show the resolved root in the question so the user can confirm or correct it.
- If the current directory is not inside a repository and no path was given — ask the user for the directory to scan. Do not assume a default like
~/git.
For multi-repo scope, enumerate repositories by locating each .git directory (a directory, not a gitdir file) under the resolved root.
Step 1: Enumerate worktrees
For each in-scope repository:
git -C "$REPO" worktree list --porcelain
The first entry is the main checkout — never a removal candidate. Every additional entry is a candidate. Also note the current worktree (the one this session runs in, if any) and exclude it.
Step 2: Classify each candidate
For every candidate worktree path $WT:
-
Dirty — uncommitted or untracked changes:
git -C "$WT" status --porcelainA non-empty result means dirty. Inspect what changed before judging (see Step 4).
-
Locked —
git worktree list --porcelainprints alockedline. Read the lock reason. If it embeds a PID (e.g.pid 29180), check whether that process is still alive:ps -p "$PID" >/dev/null 2>&1 && echo live || echo stale
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.
- 3d ago First seen · 96 lines · 95 tokens per session scan A ad7578300efb
worktree-sweep is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 95 tokens to every session and 1,285 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…