doc-defrag-audit

doc-defrag-audit is a skill for Claude Code, Codex from orlando-japan/claude-code-setting. It costs 46 tokens per session (671 once invoked), scanned A, original, MIT.

A document audit for finding conflicting, outdated, or competing project documents and deciding which one is the source of truth.

In plain words
What is it for?
Use it to review PRDs, READMEs, specifications, patch notes, legacy files, and other project guidance for conflicts, broken references, and unclear ownership.
Why use it?
It helps teams avoid following old requirements or losing track of which README, plan, or specification is authoritative.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review PRDs, READMEs, specifications, patch notes, legacy files, and other project guidance for conflicts, broken references, and unclear ownership.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orlando-japan/claude-code-setting/doc-defrag-audit
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.

Any agent
npx skills add orlando-japan/claude-code-setting --skill doc-defrag-audit
Clone the repo
git clone --depth 1 https://github.com/orlando-japan/claude-code-setting

Made for: Claude Code, Codex.

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 doc-defrag-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/doc-defrag-audit/github.svg)](https://agentmods.dev/skills/orlando-japan/claude-code-setting/doc-defrag-audit)
Your own site
<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/doc-defrag-audit"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/doc-defrag-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 doc-defrag-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/doc-defrag-audit"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/doc-defrag-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 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 $0.00046 $0.00671
Opus 5 $0.00023 $0.00336
Sonnet 5 $0.00009 $0.00134
Haiku 4.5 $0.00005 $0.00067

Measured 9d ago against content hash e5e2949aba22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

doc-defrag-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 9d 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.

templates/extra/skills/doc-defrag-audit/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document defragmentation audit

Treat document structure as architecture, not housekeeping. When the entrypoint drifts or patch notes start competing with the mainline, teams lose the ability to answer a simple question: "which document is the source of truth?"

What to audit first

  1. Mainline documents
    • Active PRD / SDD / spec / README / navigation docs
    • Files that claim to be the entrypoint or current authority
  2. Patch and legacy artifacts
    • patch, delta, v2, legacy, old, archive, rereview, handoff, checklist style documents
  3. Runtime and governance entrypoints
    • README, whitelist, rules, skill docs, agent docs, onboarding notes
  4. Reference chain
    • Does each supporting document explicitly say what it extends, supersedes, or no longer governs?

Severity model

  • P0 — mainline authority conflict
    • Two documents both appear to own the same decision space
    • A retired patch doc still looks active
  • P1 — inheritance / link drift
    • The main document is right, but surrounding docs still reference old paths, old names, or old authority
  • P2 — directory pollution / readability debt
    • The structure is technically survivable, but cluttered enough to slow down future work

Audit workflow

  1. Find the primary entrypoint
    • Identify the one file a new maintainer should read first
  2. Map the sibling docs
    • Classify each as active mainline, supporting note, process artifact, legacy, or redirect candidate
  3. Check authority statements
    • Every non-mainline doc should explicitly say one of:
      • extends
      • supersedes
      • historical only
      • operational checklist only
  4. Score the top 1-3 problems
    • Do not dump every nit; surface the highest leverage conflicts first
  5. Recommend the smallest fix that restores order
    • Prefer header clarification, redirect stubs, or navigation cleanup before aggressive file moves

Preferred output

Use a compact audit note such as:

Read the full file on GitHub · 75 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. 9d ago First seen · 75 lines · 46 tokens per session scan A e5e2949aba22

Subscribe to this mod's changes

doc-defrag-audit is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 671 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

docs-strategy

Documentation architecture, information hierarchy, style guides, versioning strategy, and cross-team documentation governance for production software projects.

LuuOW/meridian-mcp · 26 tokens

Architecture Review

When a design needs a second look before implementation starts, and what to actually evaluate when giving it one.

niels-emmer/myace · 24 tokens

plugin-review

Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.

athola/claude-night-market · 23 tokens

data-mesh-expert

Expert-level data mesh architecture, domain-oriented ownership, data products, federated governance, and self-serve platforms. Use when the user mentions architecture, domain driven, data products, governance, or platform, or when the task involves Data Mesh Principles, Domain-Oriented Data Ownership, Data as a…

personamanagmentlayer/pcl · 75 tokens

code-review

Orchestrates code review by detecting the project language and architecture, then routing to the appropriate specialized review skill (code-review-go, code-review-typescript, code-review-python, code-review-php, code-review-architecture). Falls back to the generic checklist when no specific skill applies. Invoked when…

soulcodex/agentic · 80 tokens

code-review-architecture

Architecture-focused code review covering hexagonal boundary violations, DDD anti-patterns, CQRS misuse, and microservices coupling issues. Applied in addition to the language-specific review skill when architecture markers are detected. Invoked when reviewing hexagonal architectures, DDD patterns, or microservices…

soulcodex/agentic · 63 tokens