knowledge-audit

knowledge-audit is a skill for Claude Code from Aimeerrhythm/enterprise-change-workflow. It costs 40 tokens per session (1,524 once invoked), scanned A, original, MIT.

A health check for a project’s knowledge base, meaning the collection of Markdown documents that records useful project rules and facts.

In plain words
What is it for?
Use it to scan knowledge documents, measure their size and composition, and receive a health report with improvement suggestions.
Why use it?
It reveals stale references, files that are too small or large, and content that mainly repeats source code instead of preserving important knowledge.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the ecw plugin — 15 skills, 3 commands, 7 agents 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/aimeerrhythm/enterprise-change-workflow/knowledge-audit
Any agent
npx skills add Aimeerrhythm/enterprise-change-workflow --skill knowledge-audit
Clone the repo
git clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflow

Made for: Claude Code.

Or install ecw, the plugin that ships this one along with the rest of its 15 skills, 3 commands, 7 agents.

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 knowledge-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/aimeerrhythm/enterprise-change-workflow/knowledge-audit.svg)](https://agentmods.dev/skills/aimeerrhythm/enterprise-change-workflow/knowledge-audit)
Your own site
<a href="https://agentmods.dev/skills/aimeerrhythm/enterprise-change-workflow/knowledge-audit"><img src="https://agentmods.dev/badge/skills/aimeerrhythm/enterprise-change-workflow/knowledge-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,524 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 5.1 $0.00040 $0.01524
Opus 5 $0.00020 $0.00762
Sonnet 5 $0.00008 $0.00305
Haiku 4.5 $0.00004 $0.00152

Measured 6d ago against content hash 9d7712d75d80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

knowledge-audit 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 6d 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.

skills/knowledge-audit/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Base Health Audit

You are a knowledge base quality auditor. When user invokes this Skill, perform a comprehensive health check on the project's knowledge base.

Prerequisites

Check if .claude/ecw/ecw.yml exists:

  • Exists → Read paths.knowledge_root
  • Not exists → Use default .claude/knowledge/

Audit Steps

Step 1: Basic Statistics

Scan all .md files under knowledge root:

  • Count total files, total lines
  • Count files and lines per domain (first-level subdirectories)
  • Identify tiny files (<25 lines) and oversized files (>300 lines)
find <knowledge_root> -name "*.md" -type f | wc -l
find <knowledge_root> -name "*.md" -type f -exec wc -l {} + | sort -n

Step 2: Content Composition Analysis

For each non-00-index.md file, sample content (first 50 + middle 50 + last 50 lines), classify into:

Content Type Recognition Pattern Value Assessment
Pseudocode/Call chains Contains , FacadeImpl, BizServiceImpl, Manager line-by-line translation Low value (AI can read source directly)
Business constraints/rules Contains "must", "not allowed", "priority", "condition", "invariant" High value (cross-file aggregation)
State transitions/tables Contains state machines, error code tables, dependency tables Medium-high value (structured info)
Config listings Contains Nacos, enum value lists, config item tables Low value (stale-prone, greppable)
Navigation/overview Contains directory structure, Facade map, entry locator table High value (AI locating efficiency boost)

Output estimated percentage for each type (based on sampling).

Step 3: Three-Criteria Compliance Check

For high-percentage "Pseudocode/Call chains" and "Config listings", check if they meet any of the three criteria:

Three-Criteria Standard (keep if meets any one):

  1. Cross-file scattered — Info scattered across 3+ files, AI needs extensive reading to piece together
  2. Implicit intent — Code has what but no why, and not knowing why leads AI to wrong decisions in edge cases
  3. Counter-intuitive design — Code behavior looks like a bug but is actually intentional business requirement

Read the full file on GitHub · 186 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. 6d ago First seen · 186 lines · 40 tokens per session scan A 9d7712d75d80

Subscribe to this mod's changes

knowledge-audit is a skill published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,524 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 2026-08-31.

Related

Other skills, from other repositories

init

Bootstrap or update a repo for hashb compliance -- Project Profile, rules, business scaffolds. Idempotent.

iamvonpasion/hashb · 23 tokens

audit

Compliance audit — scan entire repo against hashb standards. Scored report with prioritized findings.

iamvonpasion/hashb · 18 tokens

memory-to-skill

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…

zilliztech/memsearch · 82 tokens

lifecycle-messaging

Email/SMS lifecycle and deliverability framework for SMB Product-Builder products that send transactional or lifecycle messages (booking reminders, CRM sequences, receipts, win-back). Codifies provider selection (Resend/Postmark/Twilio/SendGrid), domain auth (SPF/DKIM/DMARC), consent and compliance (TCPA, CAN-SPAM…

avelikiy/great_cto · 132 tokens

a11y-audit

Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…

greglas75/zuvo · 147 tokens

dependency-audit

Dependency health and internal coupling audit for Node.js/TypeScript projects. 11 dimensions: supply chain CVEs, supply-chain integrity (typosquat/dependency-confusion/malicious-package/SBOM), freshness, dead dependencies, license compliance, bundle weight, circular dependencies, coupling metrics, architecture…

greglas75/zuvo · 116 tokens