kb-audit

kb-audit is a skill for Claude Code from waelmas/codeplow. It costs 118 tokens per session (2,598 once invoked), scanned A, original, MIT.

A documentation checker that compares Markdown files with the project's actual code. It reports whether each document is current, partly outdated, outdated, or describing planned work, with file-and-line evidence.

In plain words
What is it for?
Use it to audit project documentation and save one evidence-based audit note in an Obsidian knowledge base.
Why use it?
It finds documentation that makes claims the code no longer supports, so stale information is easier to correct.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the obsidian-kb plugin — 8 skills, 8 commands shipped together

Good fit Use it to audit project documentation and save one evidence-based audit note in an Obsidian knowledge base.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add waelmas/codeplow
Claude Code
/plugin install obsidian-kb

Made for: Claude Code.

Or install obsidian-kb, the plugin that ships this one along with the rest of its 8 skills, 8 commands.

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 kb-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/waelmas/codeplow/kb-audit/github.svg)](https://agentmods.dev/skills/waelmas/codeplow/kb-audit)
Your own site
<a href="https://agentmods.dev/skills/waelmas/codeplow/kb-audit"><img src="https://agentmods.dev/badge/skills/waelmas/codeplow/kb-audit/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 kb-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/waelmas/codeplow/kb-audit"><img src="https://agentmods.dev/badge/skills/waelmas/codeplow/kb-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,598 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 $0.00118 $0.02598
Opus 5.5 $0.00047 $0.01039
Sonnet 5.5 $0.00024 $0.00520
Haiku 4.5 $0.00012 $0.00260

Measured 2mo ago against content hash 6ce250f9921d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kb-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 2mo 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.

obsidian-kb/skills/kb-audit/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kb-audit - Documentation Rot Detector

Scan every markdown doc in the current project, verify concrete claims against the code, and produce a single verdict note in the vault: which docs are current, which are stale, and exactly why. Every flagged claim carries a file:line reference as proof.

This skill is the standalone version of the audit that kb-init runs as part of its full flow. Run this any time you want to re-check documentation freshness without re-populating the vault.

Step 0: Preflight - Obsidian available and running?

Follow the Preflight Check in the obsidian-kb awareness skill (${CLAUDE_PLUGIN_ROOT}/skills/obsidian-kb/SKILL.md).

Step 1: Resolve the Project Vault

Follow the Vault Resolution Algorithm in ${CLAUDE_PLUGIN_ROOT}/skills/obsidian-kb/SKILL.md. Strict priority: user argument → path overlap → frontmatter → strong name match → STOP and ask.

Capture both $VAULT_NAME and $VAULT_PATH.

Print the confirmation line on your first reply:

"Using vault <Vault Name> at <path> (matched via <tier>). Auditing project docs against current code."

Step 1b: Vault Access Sequence

Switch Obsidian's active vault to the resolved one so post-audit CLI verification works:

CURRENT=$(timeout 3 obsidian vault info=name 2>/dev/null)
if [[ "$CURRENT" != "$VAULT_NAME" ]]; then
  ENCODED=$(printf '%s' "$VAULT_NAME" | sed 's/ /%20/g')
  open "obsidian://open?vault=${ENCODED}"   # macOS; xdg-open on Linux; start on Windows
  sleep 3
  CURRENT=$(timeout 3 obsidian vault info=name 2>/dev/null)
fi
if [[ "$CURRENT" == "$VAULT_NAME" ]]; then CLI_MODE=1; else CLI_MODE=0; fi

Step 2: Inventory Project Markdown Docs

Find every markdown file in the project (not the vault - the project's docs we're auditing):

find "$PWD" -type f \( -name '*.md' -o -name '*.mdx' \) \
  -not -path '*/node_modules/*' \
  -not -path '*/.git/*' \
  -not -path '*/dist/*' \
  -not -path '*/build/*' \
  -not -path '*/.next/*' \
  -not -path '*/target/*' \
  -not -path '*/vendor/*' \
  -not -path '*/venv/*' \
  -not -path '*/.venv/*' \
  -not -path '*/__pycache__/*' \
  2>/dev/null | sort

Read the full file on GitHub · 224 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. 2mo ago First seen · 224 lines · 118 tokens per session scan A 6ce250f9921d

Subscribe to this mod's changes

kb-audit is a skill published in the GitHub repository waelmas/codeplow (8 stars, last pushed 6mo ago), licensed MIT. It adds 118 tokens to every session and 2,598 once invoked, about $0.0005 per session on Opus 5.5. 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

kb-audit compared with skills from other repositories

kb-audit next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kb-auditwaelmas/codeplowSkill86mo agoMITA118Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code