audit-document-system

audit-document-system is a skill for Claude Code, Codex from bankszach/document-systems. It costs 76 tokens per session (482 once invoked), scanned A, original, MIT.

A document-auditing skill for checking policies, specifications, plans, reports, procedures, and other operating documents as systems of rules and state changes.

In plain words
What is it for?
Use it to assess document integrity, readiness, behavioral proof, and conformity with supplied invariants, then classify findings such as clarify, revise, delete, or needs evidence.
Why use it?
It helps find missing authority, scope, evidence, exceptions, verification, acceptance criteria, and change control before a document is relied on.

Skill for Claude CodeCodex

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/bankszach/document-systems/audit-document-system
Any agent
npx skills add bankszach/document-systems --skill audit-document-system
Clone the repo
git clone --depth 1 https://github.com/bankszach/document-systems

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 482 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 $0.00076 $0.00482
Opus 5 $0.00038 $0.00241
Sonnet 5 $0.00015 $0.00096
Haiku 4.5 $0.00008 $0.00048

Measured 2d ago against content hash 64ee214057c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-document-system 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 2d 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/document-systems/skills/audit-document-system/SKILL.md · 53 lines

What it actually says

Audit Document System

Audit the document as a behavioral system. Do not rewrite or promote it unless the user separately asks for implementation.

Workflow

  1. Identify the document's stated type, status, owner, authority, and audience.
  2. Distinguish source text from your interpretation.
  3. If an Expression exists, use it. Otherwise extract a proposal Expression without treating the extraction as authoritative.
  4. Call list_document_profiles for the apparent primary profile.
  5. Call validate_document_expression with only the lineage records actually supplied. Never describe unsupplied repository lineage as valid.
  6. Inspect semantic_assertions: confirm that consequential values and state transitions are covered, cite supplied reviewed evidence, and pass. Absence of assertions is not semantic verification.
  7. Perform the semantic review in references/audit-rubric.md.
  8. Classify findings as keep, clarify, relocate, promote-to-code, delete, or needs-evidence.
  9. Report integrity, supplied-invariant conformance, readiness, behavioral proof, and human acceptance separately.

Hard boundaries

  • A structurally valid document is not necessarily ready for use.
  • A passed test is not intended-use validation.
  • Validation is not human acceptance.
  • A title, uppercase keyword, checkbox, or official appearance does not create authority.
  • An exception without an owner, stop rule, and closure evidence remains open.
  • A generated audit finding is a review candidate, not automatic truth.

Output contract

Return:

  • scoped document and profile;
  • observed findings with exact evidence;
  • deterministic validation receipt, exact validation scope, and not_established states;
  • semantic findings and failure consequences;
  • proposed changes with expected behavioral effect;
  • unresolved human decisions;
  • unchanged source status unless promotion was explicitly authorized.
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 53 lines · 76 tokens per session scan A 64ee214057c8

Subscribe to this mod's changes

audit-document-system is a skill published in the GitHub repository bankszach/document-systems (0 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 482 once invoked, about $0.0004 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

ssotize

Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…

LilMGenius/paperthin · 78 tokens

visual-html-renderer

HTMLを最終成果物として生成・検証・プレビューしたい時に使う共通レンダラー。Use this shared renderer when the user wants content turned into a final, validated, previewable HTML artifact. 現行rendererの表現能力を前提にagentが文書モデルを直接設計し、表・リスト・コード・注記・図・生成画像を選んだHTML bundleとセッション限定のプレビューURLを提示する。Triggers: html出力して, HTMLにして, HTMLで出して, この内容をHTMLで出して, HTMLでプレビューして…

u-ichi/reviewable-html-workbench · 268 tokens

image-companion

A symbolic slide image for a document passage, consistent with the artifact's companion images. Use when the user wants a diagram or visual symbol for a section. Composes /forge + Codex.

jongwony/epistemic-protocols · 43 tokens

docs-sync-external

Use when customer-facing or public documentation needs to catch up with internal docs or shipped changes — "our public docs still mention the old flag", "sync the user guide", "update the customer docs", "is anything in the external docs outdated or leaking internal detail?", "update the docs site". Narrower than…

The01Geek/prflow · 88 tokens

ce:compound

Document a recently solved problem to compound your team's knowledge.

marcusrbrown/systematic · 14 tokens

onboarding

Generate or regenerate ONBOARDING.md to help new contributors understand a codebase. Use when the user asks to 'create onboarding docs', 'generate ONBOARDING.md', 'document this project for new developers', 'write onboarding documentation', 'vonboard', 'vonboarding', 'prepare this repo for a new contributor', 'refresh…

marcusrbrown/systematic · 114 tokens