agentmods.dev

audit-permission-state

audit-permission-state is a skill for Claude Code, Codex from melodic-software/claude-code-plugins. It costs 158 tokens per session (4,413 once invoked), scanned A, original, MIT.

A report of which Claude Code permissions are actually active on a computer. It reads permission settings from managed, user, project, local, and older start-directory locations, then works out which rules allow, ask, or deny actions.

In plain words
What is it for?
Use it to inspect the active permission state, trace rules to their sources, understand precedence, and provide the result to another tool.
Why use it?
Permission files can contain conflicting rules, and simply listing them does not show which rule wins. This explains the effective result and identifies settings that could not be read.

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

not rated 13 +1 yesterday A scan 158 tokens original MIT
View the source file melodic-software/claude-code-plugins
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-state
Any agent
npx skills add melodic-software/claude-code-plugins --skill audit-permission-state
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-state

README.md
[![agentmods](https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-permission-state.svg)](https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-permission-state)
Your own site
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-permission-state"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-permission-state.svg" alt="Measured on agentmods" height="20"></a>
Per session 158 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00158 $0.04413
Opus 5 $0.00079 $0.02207
Sonnet 5 $0.00032 $0.00883
Haiku 4.5 $0.00016 $0.00441

Measured 3d ago against content hash 4baebe541663, 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-state 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 3d ago.

The scan reads SKILL.md. This mod also ships 13 executable files (scripts/automode-block-lint.sh, scripts/automode-block-lint.test.sh, scripts/automode-entry-diff.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.

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.

plugins/claude-config/skills/audit-permission-state/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

/permissions lists your rules and the settings file each one came from, and for "where is this rule written" that is the answer, so use it. What it does not do is resolve the outcome: it will show you an allow and a deny for the same tool without saying which wins, it cannot tell a scope that was empty from one it could not read, there is no claude permissions subcommand or machine-readable export, and none of it exists outside a live session. This skill computes that locally, in a form another tool can consume.

It answers a question the siblings do not. audit-permission-grants asks whether the grants you wrote are durable and portable; audit asks whether your config files are correct. This skill asks what is in effect: which scopes exist on this machine, which of them this reader could actually open, and what each one holds.

Scope boundary (route out)

  • Grant portability and auto-mode durability (P1/P2/P3) → claude-config:audit-permission-grants.
  • Settings-file correctness, baseline deny/ask presence, plugin drift → claude-config:audit.
  • The instruction layer (CLAUDE.md, rules, auto-memory) → the claude-memory plugin.

Report-only, permanently

This skill writes no settings file, in any scope, under any flag. That is the contract, and it holds including under --oracle. It is not the same as writing nothing at all: --oracle spawns a real claude -p session, and a session rewrites ~/.claude.json and adds project, session-env, security, subagent and backup state under your config directory. The flag prints that before it spawns anything. Every other action writes nothing anywhere. Managed policy is read-only by construction: those are admin-write OS locations or a claude.ai Owner role, so a plugin could not author them even if it wanted to.

Arguments

Parse $ARGUMENTS:

  • --scopes: surface records only, no rule inventory. Use when the question is "which scopes exist and which could you read", not "what is in them".
  • --entry-diff: run the full pipeline through to the auto-mode entry diff (Phase 3 below).
  • --oracle: with --entry-diff, cross-check the prediction against the harness's own drop narration. Spawns a real claude -p session; never fires without this flag. See its cost notice, which the run prints before anything is spawned.
  • (no argument): surfaces plus one record per allow/ask/deny rule, then the merge.

Read the full file on GitHub · 305 lines

Files

What ships with it

17 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. 3d ago First seen · 305 lines · 158 tokens per session scan A 4baebe541663

Subscribe to this mod's changes

audit-permission-state is a skill published in the GitHub repository melodic-software/claude-code-plugins (13 stars, last pushed yesterday), licensed MIT. It adds 158 tokens to every session and 4,413 once invoked, about $0.0008 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.

Securityagentsai-toolsclaude-codemarketplacemcpplugins
Related

Other skills, from other repositories

deep-research

Conducts iterative deep research on any topic using web search, progressive exploration, and structured synthesis. Use when asked for comprehensive research, deep investigation, thorough analysis, or multi-source exploration of any topic. Triggers: research, investigate, deep dive, comprehensive analysis, explore…

jimmc414/claude-code-plugin-marketplace · 64 tokens

error-ux

Principles and patterns for writing error messages that help users recover. Use when auditing, writing, or improving error messages in code. Triggers: error messages, user experience, error handling, exception messages, validation errors.

jimmc414/claude-code-plugin-marketplace · 48 tokens

adversarial-patterns

Library of realistic adversarial attack vectors and anti-patterns to avoid. Contains examples of valid attacks and subtle gaming patterns to reject.

jimmc414/claude-code-plugin-marketplace · 32 tokens

documentation-testing

Provides heuristics for identifying incomplete or broken documentation. Use when validating README setup instructions, testing onboarding flows, or auditing documentation quality. Triggers: docs, readme, onboarding, setup validation, documentation audit.

jimmc414/claude-code-plugin-marketplace · 45 tokens

adversarial-analysis

Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.

jimmc414/claude-code-plugin-marketplace · 37 tokens

match-stable-pairs

For two-sided matching: hospital-resident, stable marriage, college admissions. Gale-Shapley algorithm for stable matching with preferences.

jimmc414/claude-code-plugin-marketplace · 32 tokens