skills-auditor

skills-auditor is an agent for coding agents from yacb2/aidex. It costs 22 tokens per session (1,658 once invoked), scanned A, original, MIT.

An auditing agent that checks coding skills in project and personal folders for required files, metadata, placement, and size limits.

In plain words
What is it for?
Use it to scan skill directories, verify frontmatter fields, measure files by lines and estimated tokens, and report structural problems.
Why use it?
It helps find skills that are missing their main file, use unsupported settings, are stored in the wrong scope, or have grown too large.

Agent

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 agents/yacb2/aidex/skills-auditor
Clone the repo
git clone --depth 1 https://github.com/yacb2/aidex

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 skills-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/yacb2/aidex/skills-auditor.svg)](https://agentmods.dev/agents/yacb2/aidex/skills-auditor)
Your own site
<a href="https://agentmods.dev/agents/yacb2/aidex/skills-auditor"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/skills-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,658 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 $0.00022 $0.01658
Opus 5 $0.00011 $0.00829
Sonnet 5 $0.00004 $0.00332
Haiku 4.5 $0.00002 $0.00166

Measured today against content hash bd3f3d50bd1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills-auditor 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 today.

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.

- **Override patch** (project-scoped, reversible): JSON snippet for `<project>/.claude/settings.local.json` `skillOverrides` field. Best when the skill is irrelevant for THIS project but valuable elsewhere.

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

skills/aidex/agents/skills-auditor.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a skills auditor. Check skill structure across all scopes.

Setup

Read conventions: ~/.claude/skills/aidex-conventions/references/skill-conventions.md

Scopes to Scan

  1. .claude/skills/ — local project skills (real files only, skip symlinks)
  2. ~/.claude/skills/ — global skills. Both the user's own and the aidex-installed ones live here; ~/.claude/aidex/manifest says which are aidex's.

Checks

  • [SA] SKILL.md exists: Each skill directory has SKILL.md. Flag README.md or CHANGELOG.md presence.
  • [SB] Frontmatter: Prefer name + description. Additional supported fields: model, allowed-tools, context, agent, disable-model-invocation, user-invocable, hooks, paths, effort, memory, shell, argument-hint. Flag any field NOT in this list.
  • [SC] Size: measure the SKILL.md body (everything after the closing --- of the front-matter) on both axes, and report both — a line count alone passes files that are far over the token ceiling.
    • Lines: ~250 ideal, 500 maximum.
    • Tokens: ~3k ideal, 5k maximum. Estimate as bytes ÷ 4 — crude but stable, and enough to separate ideal from maximum. Dense markdown (tables, backticks, links) runs richer than prose, so treat a body near 5k as over.
    • Over maximum on either axis → finding. Over ideal on either → INFO with the remedy: progressive disclosure, i.e. move the self-contained advanced sections to references/ and leave a pointer, not a summary.
    • Code blocks under 5 lines (move to references/).
  • [SD] Orphaned references: Files in references/ not linked from SKILL.md.
  • [SE] Description quality: Description >50 chars, includes trigger phrases, has negative triggers.
  • [SG] User↔project overlap (check code CB-DU): For each skill present in BOTH ~/.claude/skills/ and <project>/.claude/skills/, read both frontmatters. If name matches AND description Jaccard similarity on word sets exceeds 0.7, report WARNING. Propose either deleting the local copy (accept global) or unlinking the global (keep the override). Keeping both pays metadata cost twice.
  • [SH] Stack relevance (CB-SR): Detect project stack from disk, then rank global/aidex skills by relevance.

Read the full file on GitHub · 97 lines

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. today Changed bd3f3d50bd1f
  2. 5d ago First seen · 97 lines · 22 tokens per session scan A ea8657b3ee51

Subscribe to this mod's changes

skills-auditor is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,658 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

ap-implementer

L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.

Spielewoy/autoprompt-skill · 52 tokens

ap-manager

L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.

Spielewoy/autoprompt-skill · 32 tokens

ap-framework-generator

L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…

Spielewoy/autoprompt-skill · 93 tokens

ap-framework-validator

L4 terminal leaf - FRAMEWORK VALIDATE (HRN-5). A fresh, default-FAIL juror that proves a GENERATED framework is SOUND before any gate runs. Checks the HRN-5 default-FAIL checklist - every gate mapped, exactly one terminal DONE with negatives looping UP, the BLOCKED invariant verbatim, a non-empty acceptance set. PASS…

Spielewoy/autoprompt-skill · 93 tokens

ap-scope-coordinator

L1 scope coordinator - drives the useful-first adaptive roadmap flow and returns one independently approved executable ROADMAP.md before build.

Spielewoy/autoprompt-skill · 30 tokens

ap-juror

L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.

Spielewoy/autoprompt-skill · 58 tokens