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 agentmods add skills/bankszach/document-systems/audit-document-systemnpx skills add bankszach/document-systems --skill audit-document-systemgit clone --depth 1 https://github.com/bankszach/document-systemsWhat 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 | $0.00076 | $0.00482 |
| Opus 5 | $0.00038 | $0.00241 |
| Sonnet 5 | $0.00015 | $0.00096 |
| Haiku 4.5 | $0.00008 | $0.00048 |
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.
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
- Identify the document's stated type, status, owner, authority, and audience.
- Distinguish source text from your interpretation.
- If an Expression exists, use it. Otherwise extract a proposal Expression without treating the extraction as authoritative.
- Call
list_document_profilesfor the apparent primary profile. - Call
validate_document_expressionwith only the lineage records actually supplied. Never describe unsupplied repository lineage as valid. - 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. - Perform the semantic review in references/audit-rubric.md.
- Classify findings as
keep,clarify,relocate,promote-to-code,delete, orneeds-evidence. - 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_establishedstates; - semantic findings and failure consequences;
- proposed changes with expected behavioral effect;
- unresolved human decisions;
- unchanged source status unless promotion was explicitly authorized.
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.
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.
- 2d ago First seen · 53 lines · 76 tokens per session scan A 64ee214057c8
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.
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…
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…
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.
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…
ce:compound
Document a recently solved problem to compound your team's knowledge.
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…