deep-audit SKILL.md skillA

deep-audit from pedrohcgs/claude-code-my-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pedrohcgs/claude-code-my-workflow/deep-audit@git:20260927.7650048

Pins git:20260927.7650048 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pedrohcgs/claude-code-my-workflow
Path
.claude/skills/deep-audit/SKILL.md
Versions recorded
7
Latest version
git:20260927.7650048, committed Sep 27, 2026
First version recorded
Jun 9, 2026
Size
11,604 bytes
Repository stars
1,718
License
MIT

Comprehensive adversarial audit of a theory, proof, math/econ paper, codebase, or set of claims — decompose into components, fan out independent skeptics that must return CONCRETE defects, adjudicate every finding with a separate judge, fix all confirmed defects, then re-verify. Use when correctness must be bulletproof and single-pass or round-by-round review is too slow and too shallow. Invoke for "audit this rigorously", "find ALL the bugs/gaps", "make this rock solid…

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

# Deep adversarial audit

A convergent alternative to slow round-by-round review. Instead of one reviewer finding one or two issues per pass, fan out many independent skeptics over the *whole* artifact at once, adjudicate what they find, fix everything confirmed, and re-verify. Modeled on the multi-agent methodology behind hard formal-proof efforts (diverse independent portfolio, adversarial throughout, concrete evidence only, synthesize-challenge-repeat).

## When to reach for this
- The artifact is dense enough that a single review keeps surfacing *new* issues each pass (the tell that round-by-round is the wrong tool).
- Correctness is the priority and the cost of a missed defect is high (a paper going to a top venue, a proof, a security-sensitive change, a migration).
- The user asked to "fix ALL of it", "be deeper", "converge faster", "100% rock solid".

Requires the user to have opted into multi-agent orchestration (they asked for a workflow / deep audit / to fan out agents, or ultracode is on). If they haven't, propose it and its rough cost first.

## The method
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_we33xonxjcjscut2/d1cbf2061f98612e27e1aaffa2bbe8f88f5e00c9967b3dcdbfa5c77d59118106.json

Then /plugin install deep-audit@markdownregistry-we33xonxjcjscut2 in Claude Code. It installs git:20260927.7650048, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add pedrohcgs/claude-code-my-workflow/deep-audit@sha256:d1cbf2061f98612e

The line at the top of this page pins the label git:20260927.7650048, 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_we33xonxjcjscut2.svg)](https://markdownregistry.com/a/art_we33xonxjcjscut2)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in pedrohcgs/claude-code-my-workflow/deep-audit since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of deep-audit from somewhere else? Ask it: where did my deep-audit come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 7 versions of this file, between Jun 9, 2026 and Sep 27, 2026, about one every 18 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260927.7650048 latest2026-09-27 7650048 11,604 BA view · diff
git:20260927.0425fd62026-09-27 0425fd6 11,573 BA view · diff
git:20260927.6535de72026-09-27 6535de7 11,178 BA view · diff
git:20260821.66003332026-08-21 6600333 11,052 BA view · diff
v1.0.02026-08-21 6fe4b52 12,482 BA view · diff
v1.0.02026-08-21 8a2f894 10,780 BA view · diff
v1.0.02026-06-09 1ebee45 10,745 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (11604 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

pedrohcgs/claude-code-my-workflow · 1,718 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_we33xonxjcjscut2
GET https://markdownregistry.com/api/v1/resolve?ref=pedrohcgs/claude-code-my-workflow/deep-audit
GET https://markdownregistry.com/api/v1/blob/d1cbf2061f98612e27e1aaffa2bbe8f88f5e00c9967b3dcdbfa5c77d59118106

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 pedrohcgs/claude-code-my-workflow

adjudicate-review SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/adjudicate-review/SKILL.md · Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model —…
git:20261106.a8c8716 · audit A · 1,718 stars
audit-reproducibility SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/audit-reproducibility/SKILL.md · Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata…
git:20261106.a8c8716 · audit A · 1,718 stars
blast-radius SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/blast-radius/SKILL.md · Before and after changing anything shared — a function's return value, a signature, a schema, a label set, a config…
git:20261106.a8c8716 · audit A · 1,718 stars
capture-environment SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/capture-environment/SKILL.md · Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and…
git:20261106.a8c8716 · audit A · 1,718 stars
coauthor-brief SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/coauthor-brief/SKILL.md · Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed…
git:20261106.a8c8716 · audit A · 1,718 stars
commit SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/commit/SKILL.md · Commit the current work — runs the quality, consistency and passport gates, branches off main if needed, stages…
git:20261106.a8c8716 · audit A · 1,718 stars
compile-latex SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/compile-latex/SKILL.md · Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides"…
git:20261106.a8c8716 · audit A · 1,718 stars
create-lecture SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/create-lecture/SKILL.md · Create a new Beamer lecture `.tex` from source papers and materials, with notation consistency checks and the project's…
git:20261106.a8c8716 · audit A · 1,718 stars
credible-claims SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/credible-claims/SKILL.md · Research-brief + claim-record discipline for delegated or AI-assisted research work. Use when starting any substantive…
git:20261106.a8c8716 · audit A · 1,718 stars
data-analysis SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/data-analysis/SKILL.md · End-to-end R data analysis pipeline — exploration → cleaning → regression → publication-ready tables and figures. Use…
git:20261106.a8c8716 · audit A · 1,718 stars
data-management-plan SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/data-management-plan/SKILL.md · Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the…
git:20261106.a8c8716 · audit A · 1,718 stars
deploy SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/deploy/SKILL.md · Render Quarto `.qmd` slides to HTML and sync to `docs/` for GitHub Pages. Use when user says "deploy", "publish the…
git:20261106.a8c8716 · audit A · 1,718 stars

Every file in pedrohcgs/claude-code-my-workflow

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