skill-auditor

skill-auditor is an agent for Claude Code from athola/claude-night-market. It costs 36 tokens per session (1,359 once invoked), scanned A, original, MIT.

An automated reviewer for checking the quality and structure of skills, which are reusable instructions for an agent. It examines their content, organization, efficiency, reliability, and use of tools.

In plain words
What is it for?
Auditing all skills in a plugin or reviewing one skill, then producing a report, machine-readable analysis, quality score, or prioritized improvement plan.
Why use it?
It helps find unclear instructions, wasted text, standards violations, unreliable activation, and integration problems before they affect users.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the abstract plugin — 16 skills, 17 commands, 5 agents, 4 hooks shipped together

Good fit Auditing all skills in a plugin or reviewing one skill, then producing a report, machine-readable analysis, quality score, or prioritized improvement plan.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/athola/claude-night-market/skill-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market

Made for: Claude Code.

Or install abstract, the plugin that ships this one along with the rest of its 16 skills, 17 commands, 5 agents, 4 hooks.

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 skill-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/athola/claude-night-market/skill-auditor/github.svg)](https://agentmods.dev/agents/athola/claude-night-market/skill-auditor)
Your own site
<a href="https://agentmods.dev/agents/athola/claude-night-market/skill-auditor"><img src="https://agentmods.dev/badge/agents/athola/claude-night-market/skill-auditor/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 skill-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/athola/claude-night-market/skill-auditor"><img src="https://agentmods.dev/badge/agents/athola/claude-night-market/skill-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,359 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 $0.00036 $0.01359
Opus 5 $0.00018 $0.00679
Sonnet 5 $0.00007 $0.00272
Haiku 4.5 $0.00004 $0.00136

Measured 11d ago against content hash 1f512439cf19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill-auditor 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.

plugins/abstract/agents/skill-auditor.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Auditor Agent

Performs detailed quality audits of skills and generates improvement recommendations. Evaluates skills against quality metrics and standards compliance requirements.

Purpose

Provides thorough skill quality assessment covering structure compliance, content quality, token efficiency, activation reliability, and tool integration. Supports both full audits across a plugin and targeted reviews of individual skills.

Capabilities

  • Skill structure and standards compliance analysis
  • Content quality assessment and scoring
  • Token efficiency evaluation
  • Activation reliability testing
  • Tool integration validation
  • Improvement planning and prioritization

Inputs

  • mode: detailed-audit (default) or targeted-review
  • scope: Plugin path or individual skill path
  • output: markdown-report, json-analysis, quality-score, or improvement-plan

Workflow

Detailed Audit

  1. Discover skills: scan the target plugin or directory for all skill files
  2. Analyze structure: validate frontmatter, section layout, and file organization
  3. Evaluate quality: score each skill against the quality metrics below
  4. Generate improvements: rank issues by severity and propose fixes
  5. Create report: produce the final audit report in the requested format

Targeted Review

  1. Analyze skill: examine a single skill in depth
  2. Check compliance: verify against all standards
  3. Suggest improvements: produce specific, ranked recommendations
  4. Validate fixes: re-check after changes are applied

Quality Metrics

Each skill is scored on five weighted dimensions:

Dimension Weight What it measures
Structure compliance 25% Frontmatter, sections, naming
Content quality 25% Clarity, completeness, examples
Token efficiency 20% Size vs. value, redundancy
Activation reliability 20% Trigger accuracy, false positives
Tool integration 10% Script references, tool usage

Read the full file on GitHub · 183 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. 11d ago First seen · 183 lines · 36 tokens per session scan A 1f512439cf19

Subscribe to this mod's changes

skill-auditor is an agent published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,359 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

1-ceo-quality-control-agent

Universal quality control orchestrator and final authority for any software development project. Dynamically discovers and coordinates with available sub-agents, performs comprehensive multi-dimensional quality assessment, security validation, and deployment readiness verification. Adapts to any project type…

ccplugins/awesome-claude-code-plugins · 222 tokens

reviewer

A code-review agent that checks a branch against its requirements and reports correctness, security, clarity, minimality, consistency, resilience, and performance issues. It writes its report in Traditional Chinese.

SatoruoGojoo/octopus · 65 tokens

audit-reviewer

Phase sign-off reviewer for /audit. Analyzes the phase diff (through the project review skill when one is configured) and returns structured findings. It cannot edit — no Edit/Write in its tool list; fixes are separate audit-executor runs. Spawned by the audit plugin; not meant for direct use.

AleksandarBisevac/claude-plugins · 68 tokens

audit-explorer

Read-only codebase auditor for /audit:init fan-out. Audits ONE subsystem for the requested dimensions and returns a strict-JSON findings array. Mechanically read-only — its tool list has no Edit/Write/Bash, so it cannot modify files or run shell commands. Spawned by the audit plugin; not meant for direct use.

AleksandarBisevac/claude-plugins · 72 tokens

gate

Independent verification delegate. Checks finished work against what was actually asked, runs the tests, reports findings by severity. Never edits anything. Use before completing consequential work; run in the foreground.

markskrypka/stem · 39 tokens

code-reviewer

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.

ccplugins/awesome-claude-code-plugins · 30 tokens