dangerous-config-file-protection

dangerous-config-file-protection is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 28 tokens per session (379 once invoked), scanned A, original, MIT.

A filesystem-safety skill that protects sensitive configuration files and directories before changes are allowed.

In plain words
What is it for?
Use it when checking whether an agent may modify paths such as .git, .claude, .gitconfig, or .vscode.
Why use it?
It reduces the risk of overwriting files that store secrets, version-control data, or tool settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it when checking whether an agent may modify paths such as .git, .claude, .gitconfig, or .vscode.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/dangerous-config-file-protection
Install

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.

Any agent
npx skills add ychampion/cskill-agents --skill dangerous-config-file-protection
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for dangerous-config-file-protection

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/dangerous-config-file-protection/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/dangerous-config-file-protection)
Your own site
<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.

agentmods 80×15 button for dangerous-config-file-protection

Your own site · 80×15
<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>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00379
Opus 5 $0.00014 $0.00189
Sonnet 5 $0.00006 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 11d ago against content hash 09a5020df6e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 11d 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.

agents/claude-code/skills/dangerous-config-file-protection/SKILL.md · 28 lines

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.
Changes

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.

  1. 11d ago First seen · 28 lines · 28 tokens per session scan A 09a5020df6e8

Subscribe to this mod's changes

dangerous-config-file-protection is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 379 once invoked, about $0.0001 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 2026-08-30.