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 skills add ychampion/cskill-agents --skill safe-worktree-slug-validationgit clone --depth 1 https://github.com/ychampion/cskill-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/skills/ychampion/cskill-agents/safe-worktree-slug-validation)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/safe-worktree-slug-validation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/safe-worktree-slug-validation/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/ychampion/cskill-agents/safe-worktree-slug-validation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/safe-worktree-slug-validation.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 | $0.00023 | $0.00419 |
| Opus 5.5 | $0.00009 | $0.00168 |
| Sonnet 5.5 | $0.00005 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
safe-worktree-slug-validation 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.
What it actually says
SKILL: Safe Worktree Slug Validation
Domain: git-worktree Trigger: Apply this when accepting user-provided prefixes for enter worktree and you need to guarantee no path traversal or invalid chars slip into the worktree directory. Source Pattern: Distilled from reviewed permission, shell-safety, and worktree-management implementations.
Core Method
Split a slug on /, reject segments that are empty, . or .., or contain characters outside a za z0 9, and enforce a maximum combined length before joining the cleaned segments into a deterministic branch name and path. Perform this validation synchronously before invoking any git commands so the CLI never creates directories outside claude worktrees.
Key Rules
- Validate each
/-separated segment independently so user evil and similar mashups fail early. - Enforce a total length cap (e.g., 64 chars) before
git worktree addto prevent excessively long refs or paths. - Reject slugs with leading/trailing slashes or repeated
..segments even when a normalization would neutralize them. - Run this check before any git fetch, mkdir, or hook execution to avoid partial side effects.
Example Application
Any agent producing a worktree name for a release hotfix can reuse this skill: call the validator on the proposed slug, surface a concise error message if it fails, and refuse to call git worktree add until the slug is safe.
Anti-Patterns (What NOT to do)
- Do not rely on
git worktree addto detect traversal; it may silently create directories in unexpected locations. - Do not treat slugs as a single string (e.g., foo bar) without splitting, because multi-segment checks are necessary.
- Avoid waiting until after
mkdiror config changes—the validation must run before any side effects.
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 · 29 lines · 23 tokens per session scan A 31c4c4f56938
safe-worktree-slug-validation is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 419 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 2026-09-03.
Other skills, from other repositories
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
merge
Resolve an in-progress merge or rebase by the intent of both sides, re-run the full gate on the merged tree, and finish the operation.
verify
Prove a completion claim with fresh evidence before making it — the gate's exit code, the real diff, the remote's checks, the reviewer's verdict.
ce-commit-push-pr
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
refs
Answer questions about a dependency's real source, history, and releases from the local checkouts managed by the refs CLI.
github-scan
Operate the first-tree github scan CLI — the GitHub notification daemon and inbox runtime. Use whenever you need to run, start, stop, inspect, poll, or debug github-scan; view or respond to GitHub-triggered work from the terminal; or wire up the github-scan statusline hook.