workflow-codebase-audit SKILL.md skillA
workflow-codebase-audit from lugassawan/swe-workbench is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lugassawan/swe-workbench/workflow-codebase-audit@git:20261005.a1463b5Pins git:20261005.a1463b5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lugassawan/swe-workbench
- Path
skills/workflow-codebase-audit/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261005.a1463b5, committed Oct 5, 2026
- First version recorded
- Aug 2, 2026
- Size
- 7,511 bytes
- Repository stars
- 3
- License
- MIT
Use for cold-start, time-boxed, multi-axis audits of unfamiliar codebases — take-home assessments, post-acquisition or due-diligence reviews, pre-refactor tech-debt sweeps. Dispatches the auditor subagent for the broad sweep, optionally fans out to security-auditor / debugger on top findings (only when --depth=deep), and renders ranked findings with reasoning chains and counter-evidence fields.
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
# Workflow: Codebase Audit (cold-start multi-domain sweep) **Announce at start:** "Activating `swe-workbench:workflow-codebase-audit` to run the cold-start audit sweep." ## When to invoke - Take-home or technical assessment requiring a broad codebase review. - Post-acquisition or due-diligence review of an unfamiliar repo. - Inherited-service onboarding: "I just took ownership of this, what's the state of it?" - Pre-refactor tech-debt sweep across a monorepo or service. ## When NOT to invoke - Single-domain security audit → use `swe-workbench:security-auditor` directly (depth-first, OWASP-focused). - Known bug with a repro → use `/swe-workbench:debug` (root-cause + fix lifecycle). - PR diff review → use `/swe-workbench:review` or `swe-workbench:workflow-pr-review`. - Code already familiar; you know what to look for → run targeted tools directly. ## Composition This skill orchestrates; domain analysis is delegated to: - `swe-workbench:auditor` subagent — broad multi-domain sweep (security, perf, reliability, tooling, testing, dead-code). - `swe-workbench:security-auditor` subagent — depth-first CVE + threat review; **deep mode only**, top-N security findings. …
Read the whole file at its exact version.
How to install
mdr add lugassawan/swe-workbench/workflow-codebase-audit@sha256:9aad1468f842ac8dThe line at the top of this page pins the label git:20261005.a1463b5, 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.
[](https://markdownregistry.com/a/art_k2ureyxpwgypsxur)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 2, 2026 and Oct 5, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.a1463b5 latest | 2026-10-05 | a1463b5 | 7,511 B | A | view · diff |
| git:20260828.71a6399 | 2026-08-28 | 71a6399 | 7,037 B | A | view · diff |
| git:20260821.93037a7 | 2026-08-21 | 93037a7 | 7,067 B | A | view · diff |
| git:20260811.925e30f | 2026-08-11 | 925e30f | 6,951 B | A | view · diff |
| git:20260802.bba96ce | 2026-08-02 | bba96ce | 6,909 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7511 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
lugassawan/swe-workbench · 3 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_k2ureyxpwgypsxur GET https://markdownregistry.com/api/v1/resolve?ref=lugassawan/swe-workbench/workflow-codebase-audit GET https://markdownregistry.com/api/v1/blob/9aad1468f842ac8d56d9fcef9e7890d54733a45141396c8e38667f8dbc84027d
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.