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 malob/nix-config --skill audit-permissionsgit clone --depth 1 https://github.com/malob/nix-configWrote 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/malob/nix-config/audit-permissions)<a href="https://agentmods.dev/skills/malob/nix-config/audit-permissions"><img src="https://agentmods.dev/badge/skills/malob/nix-config/audit-permissions/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/malob/nix-config/audit-permissions"><img src="https://agentmods.dev/badge/skills/malob/nix-config/audit-permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 15 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 13 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 14 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 15 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 45 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 48 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 60 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 122 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 447 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 17 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 18 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 19 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 295 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Rogue Agent · line 34 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 219 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 323 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00067 | $0.03777 |
| Opus 5 | $0.00034 | $0.01888 |
| Sonnet 5 | $0.00013 | $0.00755 |
| Haiku 4.5 | $0.00007 | $0.00378 |
Grade A, and why
audit-permissions scanned grade A with 2 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 9d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Read(~/.claude/settings.json) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `Bash(curl *)`, `Bash(wget *)` — network exfiltration risk How it starts
The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Claude Permissions
Scan project-local Claude Code settings files, aggregate permission patterns, and recommend promotions to global configuration.
Workflow Overview
This audit runs in three phases, each as a separate task. Use TaskCreate at the start to create all three tasks, then work through them sequentially with user input via AskUserQuestion.
- Phase 1: Promote to Global — Requires user judgment. Present candidates, get decisions, apply to global config.
- Phase 2: Automated Redundancy Cleanup — Script-driven. After Phase 1 promotions, run cleanup script to remove local permissions now covered by global. Present for sanity-checking, then apply.
- Phase 3: Judgment Calls — Everything requiring user input: security hygiene, policy conflicts, one-off cruft, empty file deletion, moderate-risk items.
Initial Setup
- Check for symlinked global settings:
readlink -f ~/.claude/settings.json
If the global settings file is a symlink, note the real path. All writes to ~/.claude/settings.json must edit the symlink target, not create a new file that replaces the symlink.
-
Load user preferences from
~/.claude/cc-maintenance.local.md(if it exists). See User Preferences section below. Apply any configured defaults (risk tolerance, auto-cleanup preference). -
Read global CLAUDE.md from
~/.claude/CLAUDE.mdto identify tool preference policies for Phase 3 policy conflict detection. -
Run the discovery and extraction pipeline:
scripts/discover-settings.sh | xargs scripts/extract-permissions.py
-
Read the actual global settings from
~/.claude/settings.json— compare against the real allow list, not just the static examples in this skill. -
Create tasks for the three phases:
TaskCreate: "Review and promote permissions to global config"
TaskCreate: "Automated redundancy cleanup"
TaskCreate: "Judgment calls: security, policy, and cruft"
- Analyze the data and categorize permissions (see Categorization Rules below).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 453 lines · 67 tokens per session scan A aac63cdd2253
audit-permissions is a skill published in the GitHub repository malob/nix-config (462 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 3,777 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
restart__pull_request
A pull-request restart workflow for replacing a messy review with a new pull request containing one clean commit and a summary of the earlier discussion.
validate__japanese
A Japanese-language review for Markdown documents, such as READMEs, manuals, and blog drafts. It checks writing style, spacing, line breaks, and links to real code symbols.
write__structured_comment
A code-commenting rule for recording only knowledge that cannot be expressed in the code, such as unfinished facts, outside-world facts, or explicit user instructions. Each comment must use an approved marker such as TODO or FIXME and stay short.
clean__comment_out
A source-cleanup workflow that removes non-documentation comments from files changed during coding, except for approved markers such as TODO, FIXME, or SAFETY.
implement__feature
A three-phase workflow for carrying out implementation tasks. It plans and tests the work, delegates implementation using test-driven development (TDD), then runs repeated code reviews.
prepare__issue
An orchestration workflow that prepares an already acknowledged issue for implementation and changes its status to ready when finished.