audit-permission-grants

audit-permission-grants is a skill for Claude Code, Codex from melodic-software/claude-code-plugins. It costs 110 tokens per session (2,130 once invoked), scanned A, original, MIT.

A checker for permission rules that control which tools a Claude Code project or user account may use. It focuses on whether those rules work across machines and still apply when automatic approval mode is enabled.

In plain words
What is it for?
Use it to review skill, command, and agent permissions, along with project and user settings files. It checks portability, automatic-mode behavior, and whether the operative permission rule is defined in the right place.
Why use it?
It finds permissions that depend on one person's file paths, interpreter rules that stop working in automatic mode, or grants placed where they cannot take effect. This helps prevent unexpected prompts and ineffective security controls.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-config plugin — 8 skills shipped together

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.

agentmods
npx agentmods add skills/melodic-software/claude-code-plugins/audit-permission-grants
Any agent
npx skills add melodic-software/claude-code-plugins --skill audit-permission-grants
Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code, Codex.

Or install claude-config, the plugin that ships this one along with the rest of its 8 skills.

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 audit-permission-grants

README.md
[![agentmods](https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-permission-grants.svg)](https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-permission-grants)
Your own site
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-permission-grants"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-permission-grants.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,130 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00110 $0.02130
Opus 5 $0.00055 $0.01065
Sonnet 5 $0.00022 $0.00426
Haiku 4.5 $0.00011 $0.00213

Measured 4d ago against content hash cd8f3ce1f0a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-permission-grants scanned grade A with 1 finding 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/permission-rule-check.sh, scripts/permission-rule-check.test.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

operator-manual (the bare-name rule must land in user-global `~/.claude/settings.json`, which a skill

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/claude-config/skills/audit-permission-grants/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Audit whether a repo's permission grants actually take effect. Answers a question the sibling audit skill does not: "Are our allow-rules and allowed-tools grants portable across machines and durable when the session enters auto mode, and is the operative rule in a place that can work?"

The principle, the three anti-patterns, and the correct pattern (with official-doc citations) live in the marketplace's permission-rule-hygiene convention, published at https://raw.githubusercontent.com/melodic-software/claude-code-plugins/main/docs/conventions/permission-rule-hygiene/README.md. The mechanical check definitions (P1/P2/P3, severities, detector invocation) are in reference/criteria.md, which carries every recommendation this skill needs at run time. The convention is the doctrine's owner, not a runtime dependency.

Scope boundary (route out)

This skill owns grant portability + auto-mode durability + who adds the operative rule. It does not own config-file correctness. Baseline deny/ask presence, overly broad patterns, and live plugin drift belong to the sibling audit skill. When a request is about those, route it there rather than answering here. The audit skill in the claude-memory plugin owns the instruction layer (CLAUDE.md / rules / auto-memory).

Arguments

Parse $ARGUMENTS for an optional scope filter. It narrows which checks may produce findings, never what the detector scans. One full detector run happens either way, and the filter is applied to its output:

  • frontmatter: skill/command/agent allowed-tools only
  • settings: project, local, and user-global permissions.allow only
  • plugins: plugin settings.json self-grant (P3) only
  • all: everything (default)

Saying so is the fix, not a workaround. The filter reads like a scan-scope, and the cost argument for making it one no longer holds: since #2249 the root is a git toplevel, $CLAUDE_PROJECT_DIR, or an explicitly named directory, never an unbounded sweep, and over this repository the two find walks measure 0.49 s and 0.41 s (2026-08-12). Detector flags to skip half a second of walk would buy nothing and add a second place for scope to be defined. The coverage block still reports the whole denominator on a filtered run, so a narrowed report never implies a narrowed scan.

Read the full file on GitHub · 143 lines

Files

What ships with it

4 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.

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. 4d ago First seen · 143 lines · 110 tokens per session scan A cd8f3ce1f0a5

Subscribe to this mod's changes

audit-permission-grants is a skill published in the GitHub repository melodic-software/claude-code-plugins (14 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 2,130 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

phpunit-migration-test-reviewing

Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.

shopwareLabs/ai-coding-tools · 32 tokens

structuring-documentation

Use when writing, editing, auditing, splitting, or measuring Markdown documentation surfaces — README.md, AGENTS.md, CLAUDE.md, and docs/ siblings. Triggers include "is this doc too long", "split this README", "measure the docs", "where does this documentation belong", "audit the documentation", and any request to…

shopwareLabs/ai-coding-tools · 89 tokens

phpunit-unit-test-writing

Use this skill when the user asks to write, generate, create, or add PHPUnit unit tests for a Shopware 6 source class — phrases like "write unit tests for X", "generate tests for ClassName", "create PHPUnit tests", "add test coverage", "test this class", "cover this with tests", "I need tests for", "unit test this"…

shopwareLabs/ai-coding-tools · 187 tokens

phpunit-migration-test-generation

Use this skill when the user asks to generate, write, or create migration tests for a Shopware 6 migration class — phrases like "generate migration tests", "write a migration test", "create migration test", "test this migration", "test Migration1234Foo". Analyzes the source migration's SQL operations to pick an…

shopwareLabs/ai-coding-tools · 141 tokens

phpunit-test-reconciling

Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.

shopwareLabs/ai-coding-tools · 32 tokens

release-info-writing

Use this skill when the user is completing features, deprecations, or breaking changes in the Shopware core repository that affect external developers, or when they ask to write release info, upgrade entries, release notes, release documentation, or changelog entries — phrases like "write a release info entry for my…

shopwareLabs/ai-coding-tools · 154 tokens