Borrowing it
Nothing to install: this file belongs to AHepi/DeepReason. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AHepi/DeepReason/main/.claude/skills/dr-audit-docs-drift/SKILL.mdgit clone --depth 1 https://github.com/AHepi/DeepReasonWrote 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/ahepi/deepreason/dr-audit-docs-drift)<a href="https://agentmods.dev/skills/ahepi/deepreason/dr-audit-docs-drift"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/dr-audit-docs-drift/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/ahepi/deepreason/dr-audit-docs-drift"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/dr-audit-docs-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00770 |
| Opus 5.5 | $0.00021 | $0.00308 |
| Sonnet 5.5 | $0.00010 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
dr-audit-docs-drift 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit: documentation vs code
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).
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.
- 2mo ago First seen · 64 lines · 52 tokens per session scan A bacb48a34794
dr-audit-docs-drift is a skill published in the GitHub repository AHepi/DeepReason (141 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 770 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…