audit-documentation
Audit Markdown against repository evidence; fix safe inaccuracies.
Scope
- Use supplied scope; otherwise audit all tracked
*.md files.
- Exclude ISSUES.md, BACKLOG.md, DECISIONS.md, COMMANDS.md, and
CONTEXT.md. Use
/audit-memory when the user requests memory files.
- A finding limit caps reporting, not coverage. Empty scope returns
no-findings.
Contract
- Validate actionable claims against files, configuration, symbols, scripts,
and contracts. An unexecuted command is not verified behavior.
- Fix the smallest evidence-backed error that could materially mislead. If docs
express better intended behavior than code, report a code gap. Preserve
ambiguous content and name the missing decision.
- Do not edit source, tests, memory files, or product policy.
Workflow
Record scope and inspect enough context to establish its claims. For large
scopes, parallelize non-overlapping read-only investigations; the owning agent
validates candidates, resolves conflicts, and edits.
Check:
- referenced commands, paths, configuration keys, and interface names
- architecture and workflow claims against current code and configuration
- contradictions, renamed concepts, and drift across in-scope documents
- templates or examples that disagree with their canonical source
Mark statically indeterminate claims unverified. Ignore style, fix supported
inaccuracies, and leave code gaps or unresolved intent unchanged. Do not log the
audit to memory.
Write a concise summary with:
# Documentation Audit Summary — scope and verdict## Fixes Applied## Code Gaps## Decisions Needed
Findings include severity, location, evidence, impact, outcome (fixed,
code-gap, or needs-user-decision), and type (command, path, config,
interface, architecture, or cross-doc). Use None for empty sections.
Finish when every document is checked and every material finding has an outcome.
1---2name: audit-documentation3description: Audit Markdown docs for static accuracy and cross-document consistency against the repo, fixing what is safe. Excludes memory files by default.4---56# audit-documentation78Audit Markdown against repository evidence; fix safe inaccuracies.910## Scope1112- Use supplied scope; otherwise audit all tracked `*.md` files.13- Exclude ISSUES.md, BACKLOG.md, DECISIONS.md, COMMANDS.md, and14 CONTEXT.md. Use `/audit-memory` when the user requests memory files.15- A finding limit caps reporting, not coverage. Empty scope returns16 `no-findings`.1718## Contract1920- Validate actionable claims against files, configuration, symbols, scripts,21 and contracts. An unexecuted command is not verified behavior.22- Fix the smallest evidence-backed error that could materially mislead. If docs23 express better intended behavior than code, report a code gap. Preserve24 ambiguous content and name the missing decision.25- Do not edit source, tests, memory files, or product policy.2627## Workflow2829Record scope and inspect enough context to establish its claims. For large30scopes, parallelize non-overlapping read-only investigations; the owning agent31validates candidates, resolves conflicts, and edits.3233Check:3435- referenced commands, paths, configuration keys, and interface names36- architecture and workflow claims against current code and configuration37- contradictions, renamed concepts, and drift across in-scope documents38- templates or examples that disagree with their canonical source3940Mark statically indeterminate claims unverified. Ignore style, fix supported41inaccuracies, and leave code gaps or unresolved intent unchanged. Do not log the42audit to memory.4344Write a concise summary with:45461. `# Documentation Audit Summary` — scope and verdict472. `## Fixes Applied`483. `## Code Gaps`494. `## Decisions Needed`5051Findings include severity, location, evidence, impact, outcome (`fixed`,52`code-gap`, or `needs-user-decision`), and type (`command`, `path`, `config`,53`interface`, `architecture`, or `cross-doc`). Use `None` for empty sections.54Finish when every document is checked and every material finding has an outcome.
conn-castle