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-broken/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-broken)<a href="https://agentmods.dev/skills/ahepi/deepreason/dr-audit-broken"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/dr-audit-broken/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-broken"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/dr-audit-broken.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 | $0.00044 | $0.00715 |
| Opus 5.5 | $0.00018 | $0.00286 |
| Sonnet 5.5 | $0.00009 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
dr-audit-broken 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
pip install -e . --break-system-packages -qandpip install pytest pytest-xdist jsonschema --break-system-packages -q. Run every command below withpython -mwhere applicable; save each full output toproof/broken-<n>.txt.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 → verdictbroken; green serially → verdictflaky(row it; flaky is a finding unless baseline-listed).python tools/docs_verify.py— compare failing checks to the baseline list. Non-baseline failure → verdictbroken(the check or the code it pins moved; the fix tranche decides which).python scripts/wheel_smoke.pythenpython -u scripts/wheel_operational_smoke.py— any non-zero exit → verdictbroken, target = the pin named in the output.- RETIRED (operator ruling 2026-08-22, CLAUDE.md §Build and test):
the root sweep is no longer an audit instrument. Do NOT run
tools/root_sweep.py. Writeproof/broken-sweep.txtcontaining the single lineretired 2026-08-22 — see CLAUDE.mdso the proof count stays auditable. - Write
broken.md: the table of every non-baseline delta, one row per finding, columns as the LEDGER. Matches baseline exactly → the table plus one line:all instruments at baseline, with the five proof files as the required proof of looking (G2).
GATE
Pass: every instrument ran (four live instruments + the retirement
marker file = five proof files) AND every non-baseline delta has a
LEDGER row with disposition parked.
Verdict labels: broken | flaky | baseline.
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 · 62 lines · 44 tokens per session scan A fe3db61580cb
dr-audit-broken is a skill published in the GitHub repository AHepi/DeepReason (141 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 715 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
observability-langsmith
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
reenable-test
Guide for investigating, fixing, verifying via TDD, and re-enabling disabled or flaky Chromium tests (C++, Android Java, or WebUI). Use this skill when asked to deflake, fix, or re-enable a disabled or flaky test case, or to verify post-submit stability of a re-enabled test. Don't use for disabling a failing test…
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.