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.
npx skills add orlando-japan/claude-code-setting --skill doc-defrag-auditgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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.
[](https://agentmods.dev/skills/orlando-japan/claude-code-setting/doc-defrag-audit)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Mainline documents
- Active PRD / SDD / spec / README / navigation docs
- Files that claim to be the entrypoint or current authority
- Patch and legacy artifacts
patch,delta,v2,legacy,old,archive,rereview,handoff,checkliststyle documents
- Runtime and governance entrypoints
- README, whitelist, rules, skill docs, agent docs, onboarding notes
- 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
- Find the primary entrypoint
- Identify the one file a new maintainer should read first
- Map the sibling docs
- Classify each as active mainline, supporting note, process artifact, legacy, or redirect candidate
- Check authority statements
- Every non-mainline doc should explicitly say one of:
- extends
- supersedes
- historical only
- operational checklist only
- Every non-mainline doc should explicitly say one of:
- Score the top 1-3 problems
- Do not dump every nit; surface the highest leverage conflicts first
- 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:
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.
- 9d ago First seen · 75 lines · 46 tokens per session scan A e5e2949aba22
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.
Other skills, from other repositories
docs-strategy
Documentation architecture, information hierarchy, style guides, versioning strategy, and cross-team documentation governance for production software projects.
Architecture Review
When a design needs a second look before implementation starts, and what to actually evaluate when giving it one.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
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…
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…
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…