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-orchestrator/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-orchestrator)<a href="https://agentmods.dev/skills/ahepi/deepreason/dr-audit-orchestrator"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/dr-audit-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.01120 |
| Opus 5 | $0.00044 | $0.00560 |
| Sonnet 5 | $0.00018 | $0.00224 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
dr-audit-orchestrator 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit orchestrator (router)
Rated for inexpensive models: every worker step is a command to run,
an output to paste, or a comparison against docs/AUDIT_BASELINES.md.
Pin the model actually used in the LEDGER header (L3).
Artifacts (route on which is missing)
Tranche dir: experiments/<UTC-date>-audit/. Artifacts, in order:
| Artifact | Written by | Exists means |
|---|---|---|
LEDGER.md |
this router, at open | scope chosen, baselines copied in |
ACTIVATION.md |
this router, first run only | every GATE mutation-proven red once |
broken.md |
dr-audit-broken | instrument deltas tabled |
dead.md |
dr-audit-dead | per-package symbol census tabled |
docs-drift.md |
dr-audit-docs-drift | doc-check deltas + stale list tabled |
spec-drift.md |
dr-audit-spec-drift | both drift directions tabled |
goal-trace.md |
dr-audit-goal-trace | every law rowed with a verdict |
AUDIT_REPORT.md + PARKED.md |
this router, at close | audit complete |
Loop: open LEDGER.md; route to the first worker whose artifact is
missing; when all five exist, close (assemble report). One worker per
invocation.
LEDGER format
Header: date, model id, HEAD sha, baselines-file sha
(git rev-parse HEAD:docs/AUDIT_BASELINES.md). Then one row per
finding, updated live as work happens (G5):
| id | dimension | target | gate | verdict | proof file | disposition |
Verdict labels are fixed per worker (X3). Disposition is exactly one
of: parked (prompt written in PARKED.md), baseline (matches
AUDIT_BASELINES.md, no action), activation (planted, restored).
Workers write distilled rows and put raw command output in
proof/<id>.txt files (G7).
PRECEDENCE (the one list for this family, S4)
- Committed run roots are read, never written — GATE at close:
git status --porcelain -- experiments/ | grep -v <tranche-dir>prints nothing. docs/AUDIT_BASELINES.mddecides expected-vs-finding, over memory and over any document's prose. A wrong baseline is itself a finding: row it, park a baseline-correction prompt.- PARK over fix: the audit edits nothing outside its tranche dir —
GATE at close:
git diff --statnames only the tranche dir. - A verdict row without a
proof/file is unwritten work: the close gate counts rows vs proof files and refuses on mismatch (G1). - Baselines move only in a non-audit tranche, with this family's close gate re-run there.
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.
- yesterday Changed · +4 lines 7ecdf2890fe9
- 8d ago First seen · 82 lines · 88 tokens per session scan A 6f8005f0b5b1
dr-audit-orchestrator is a skill published in the GitHub repository AHepi/DeepReason (142 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,120 once invoked, about $0.0004 per session on Opus 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.