Audit: documentation vs code
SkillDocs & knowledgeAudit dimension - find where documentation deviates from code, using the executable doc checks plus a staleness and unchecked-claims census. Invoked by dr-audit-orchestrator when docs-drift.md is missing.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Audit: documentation vs code skill
What this skill tells your AI
The instructions your AI receives, as published by ahepi/deepreason in .claude/skills/dr-audit-docs-drift/SKILL.md and read by ahel’s review.
Entry: LEDGER.md exists, docs-drift.md missing. Exit:
docs-drift.md written, LEDGER rows added, proofs in proof/.
The primary instrument already exists: every load-bearing map claim
carries an executable check: line. This worker runs the instrument,
then censuses what the instrument cannot see.
Operations
python tools/docs_verify.py > proof/docs-full.txt— non-baseline failing check → verdictdrifted(doc says X, tree says not-X), one row per check.python tools/docs_verify.py --audit > proof/docs-audit.txt— any finding → verdicttoothless-check(a check that cannot fail guards nothing), one row each.python tools/docs_verify.py --links > proof/docs-links.txt— any danglingDR-reference → verdictdrifted.python tools/docs_verify.py --stale > proof/docs-stale.txt— table the stale list as verdictstale-stamprows (advisory:Verified-atbehind the code it describes; not proof of drift, proof nobody has looked).- Unchecked-claims census, docs outside the map (they carry no
check:lines): for each file indocs/*.md(top level only),rg -c 'check:' <file>. Zero checks AND the file's header/Status line asserts a current-state claim → verify that one claim by grep against the tree; broken → verdictdrifted(the RESEARCH_BACKEND header precedent, ledgered as E20). Row only the header/Status claim — deep prose audit is a spec-drift or manual tranche, not this pass. - Write
docs-drift.md: one table, columns as the LEDGER, plus the count line. All clean → the table plusall doc instruments at baselinewith the five proof files (G2).
GATE
Pass: five proof files exist; every non-baseline instrument delta has
a row; every drifted row's disposition is parked. Verdict labels:
drifted | toothless-check | stale-stamp | baseline.
Activation plant (first run)
Change one numeral inside one map document's prose claim (not its
check: line), run step 1 scoped
(python tools/docs_verify.py <file> if supported, else full),
confirm the check catches it OR row the miss as a toothless-check
finding against that document; git checkout -- the file, paste the
clean status. Either outcome is a valid activation (the plant proves
the instrument's edge, red or blind).
Outlets
| Situation | Outlet |
|---|---|
| Impulse to fix the doc now | PARK — doc-fix prompt, route dr-change-orchestrator |
| Check fails because the CODE regressed | verdict drifted, note code-side, PARK with route deepreason-orchestrator |
| Stale stamp on a passing doc | verdict stale-stamp, disposition baseline — re-stamping without re-running is the one forbidden move |
Signals
- GitHub stars
- 142
- Forks
- 14
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
dr-audit-docs-drift- Source
- github.com/ahepi/deepreason