dr-audit-broken SKILL.md skillA

dr-audit-broken from ahepi/deepreason is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ahepi/deepreason/dr-audit-broken@git:20260822.12aca6d

Pins git:20260822.12aca6d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ahepi/deepreason
Path
.claude/skills/dr-audit-broken/SKILL.md
Versions recorded
3
Latest version
git:20260822.12aca6d, committed Aug 22, 2026
First version recorded
Aug 13, 2026
Size
2,779 bytes
Repository stars
141
License
MIT

Audit dimension - find broken code by running every committed verification instrument and tabling deltas against the recorded baselines. Invoked by dr-audit-orchestrator when broken.md is missing.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Audit: broken code

Entry: `LEDGER.md` exists, `broken.md` missing. Exit: `broken.md`
written, LEDGER rows added, proofs in `proof/`.

Broken means: an instrument's output moved from
`docs/AUDIT_BASELINES.md` §Instruments. The instruments define
broken; this worker adds no judgment of its own (G3).

## Operations

1. `pip install -e . --break-system-packages -q` and
   `pip install pytest pytest-xdist jsonschema --break-system-packages -q`.
   Run every command below with `python -m` where applicable; save
   each full output to `proof/broken-<n>.txt`.
2. `python -m pytest tests/ -q -n 4` — compare failures to the
   baseline failure list. Re-run any non-baseline failure serially
   (`python -m pytest <nodeid> -q`) before rowing it: still red →
   verdict `broken`; green serially → verdict `flaky` (row it; flaky
   is a finding unless baseline-listed).
3. `python tools/docs_verify.py` — compare failing checks to the
   baseline list. Non-baseline failure → verdict `broken` (the check
   or the code it pins moved; the fix tranche decides which).
4. `python scripts/wheel_smoke.py` then
   `python -u scripts/wheel_operational_smoke.py` — any non-zero exit
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ahepi/deepreason/dr-audit-broken@sha256:fe3db61580cb36eb

The line at the top of this page pins the label git:20260822.12aca6d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7wnkobqucglctxwv.svg)](https://markdownregistry.com/a/art_7wnkobqucglctxwv)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Aug 13, 2026 and Aug 22, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20260822.12aca6d latest2026-08-22 12aca6d 2,779 BA view · diff
git:20260813.1b2bc672026-08-13 1b2bc67 2,766 BA view · diff
git:20260813.51f16b92026-08-13 51f16b9 2,711 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2779 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ahepi/deepreason · 141 stars · license MIT · pushed 2026-09-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7wnkobqucglctxwv
GET https://markdownregistry.com/api/v1/resolve?ref=ahepi/deepreason/dr-audit-broken
GET https://markdownregistry.com/api/v1/blob/fe3db61580cb36ebc8e22bdc2f8001e74292496c6868f8af11891f46531eaf78

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from ahepi/deepreason

authoring-skills SKILL.md skill
ahepi/deepreason · .claude/skills/authoring-skills/SKILL.md · Rules for writing, editing, and retiring skill and workflow files for LLM agents. Use when creating a SKILL.md or…
git:20260812.49486fe · audit A · 141 stars
deepreason-orchestrator SKILL.md skill
ahepi/deepreason · .claude/skills/deepreason-orchestrator/SKILL.md · Entry point for any DeepReason problem. Routes work to exactly one subskill at a time and enforces the scope contract…
git:20260903.8641470 · audit A · 141 stars
dr-ask-the-right-question SKILL.md skill
ahepi/deepreason · .claude/skills/dr-ask-the-right-question/SKILL.md · Question discipline for working DeepReason - route every question to the cheapest authority (record, then framework…
git:20260813.5683bc4 · audit A · 141 stars
dr-audit-dead SKILL.md skill
ahepi/deepreason · .claude/skills/dr-audit-dead/SKILL.md · Audit dimension - find code that is no longer used, via a reference census over every top-level symbol, one package per…
git:20260813.1b2bc67 · audit A · 141 stars
dr-audit-docs-drift SKILL.md skill
ahepi/deepreason · .claude/skills/dr-audit-docs-drift/SKILL.md · Audit dimension - find where documentation deviates from code, using the executable doc checks plus a staleness and…
git:20260813.51f16b9 · audit A · 141 stars
dr-audit-goal-trace SKILL.md skill
ahepi/deepreason · .claude/skills/dr-audit-goal-trace/SKILL.md · Audit dimension - verify every ledgered operator design law is actually enforced somewhere in code or gates, so stated…
git:20260813.51f16b9 · audit A · 141 stars
dr-audit-orchestrator SKILL.md skill
ahepi/deepreason · .claude/skills/dr-audit-orchestrator/SKILL.md · Router for the code-audit family. Runs five read-only audit dimensions (broken, dead, docs-drift, spec-drift…
git:20260905.c67e9d2 · audit A · 141 stars
dr-audit-spec-drift SKILL.md skill
ahepi/deepreason · .claude/skills/dr-audit-spec-drift/SKILL.md · Audit dimension - find where the code deviates from the spec series and where shipped surface is spec-silent, by a…
git:20260813.51f16b9 · audit A · 141 stars
dr-capture-request SKILL.md skill
ahepi/deepreason · .claude/skills/dr-capture-request/SKILL.md · Record an operator's suggested change verbatim and split it into numbered requirements (REQUEST.md). First phase of…
git:20260730.6cf4d20 · audit A · 141 stars
dr-change-orchestrator SKILL.md skill
ahepi/deepreason · .claude/skills/dr-change-orchestrator/SKILL.md · Entry point for implementing an operator-suggested change to DeepReason. Routes through capture, spec, plan, stepwise…
git:20260903.8641470 · audit A · 141 stars
dr-deliver-change SKILL.md skill
ahepi/deepreason · .claude/skills/dr-deliver-change/SKILL.md · Close a validated change tranche — final commit and push, requirement-by-requirement reconciliation against the…
git:20260813.5683bc4 · audit A · 141 stars
dr-diagnose SKILL.md skill
ahepi/deepreason · .claude/skills/dr-diagnose/SKILL.md · Locate the cause of a DeepReason defect from the typed record, not from code reading. Produces DIAGNOSIS.md naming one…
git:20260903.d23eb93 · audit A · 141 stars

Every file in ahepi/deepreason

Browse by kind, by grade A, or by owner.