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 dangerous-config-file-protectiongit 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/dangerous-config-file-protection)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/dangerous-config-file-protection"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/dangerous-config-file-protection/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/dangerous-config-file-protection"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/dangerous-config-file-protection.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 | $0.00028 | $0.00379 |
| Opus 5.5 | $0.00011 | $0.00152 |
| Sonnet 5.5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
dangerous-config-file-protection 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: Dangerous Config File Protection
Domain: sensitive-paths
Trigger: Guard every filesystem modification that touches .git, .claude, .gitconfig, or other config-critical paths before running the tool.
Source Pattern: Distilled from reviewed permission, shell-safety, and worktree-management implementations.
Core Method
Maintain explicit lists of filenames and directories that should never be touched automatically. Before allowing any tool action, expand the requested path, normalize casing, and compare the basename or enclosing directory against those lists. If a match appears, decline the action or require a human permission grant with the narrowest scope possible.
Key Rules
- Normalize to lowercase and POSIX separators before comparing, matching Windows/macOS semantics.
- Check both file-level names (e.g.,
.gitconfig) and directories (e.g.,.git,.claude,.vscode) to block entire trees that hold secrets or tooling. - Prefer generating narrow permission scopes when the path lives inside a controlled skill directory; otherwise, deny outright.
- Log each blocked attempt with a sanitized path so operators can trace why the denial happened.
Example Application
When the user asks to edit ~/.claude/skills/confidential-skill/SKILL.md, detect that the path enters .claude, normalize it, and refuse the automatic edit while suggesting a narrower permission grant instead of broad config-directory access.
Anti-Patterns (What NOT to do)
- Don’t rely on loose wildcard matching that can accidentally miss or overmatch sensitive config paths.
- Don’t skip casing normalization; mixed-case variants of the same protected path must behave the same.
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 · 28 lines · 28 tokens per session scan A 09a5020df6e8
dangerous-config-file-protection is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 379 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 2026-08-30.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
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…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
wish
Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
report
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.