workflow-codebase-knowledge SKILL.md skillA
workflow-codebase-knowledge 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-knowledge@git:20260820.16e7f08Pins git:20260820.16e7f08 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-knowledge/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260820.16e7f08, committed Aug 20, 2026
- First version recorded
- May 17, 2026
- Size
- 6,321 bytes
- Repository stars
- 3
- License
- MIT
Use to understand an unfamiliar codebase — presents architecture overview, module map, public API surfaces, and conventions as a layered mental model. Knowledge-presentation only — read-only sweep, no defect ranking, no reasoning chains. Distinct from workflow-codebase-audit (finding-oriented defect detection) and tech-writer / /swe-workbench:document (generates new prose artifacts). Ideal for onboarding, knowledge-handoff, and reviewer context-gathering.
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 Knowledge **Announce at start:** "Activating `swe-workbench:workflow-codebase-knowledge` to present a structured knowledge document." ## When to invoke - Onboarding to an unfamiliar codebase: "walk me through this repo." - Knowledge-handoff request: "give the incoming engineer a mental model of the service." - Reviewer context-gathering: "what are the public API surfaces before I start the PR review?" - Architecture exploration: "show me the module boundaries and their relationships." ## When NOT to invoke - **Defect detection or ranked findings** → use `swe-workbench:workflow-codebase-audit` (cold-start multi-axis sweep with reasoning chains and severity ranking). - **Generating new prose documentation** (READMEs, ADRs, ARCHITECTURE files) → use `/swe-workbench:document` which delegates to the `swe-workbench:tech-writer` subagent. - **Known bug with a repro** → use `/swe-workbench:debug`. - **PR diff review** → use `/swe-workbench:review`. ## Composition Read-only sweep — no subagents dispatched. May delegate file discovery to `Explore` agents in parallel for breadth when the path scope is wide. Never writes to disk. ## Path argument …
Read the whole file at its exact version.
How to install
mdr add lugassawan/swe-workbench/workflow-codebase-knowledge@sha256:46a4d38d6bb1d5d8The line at the top of this page pins the label git:20260820.16e7f08, 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_rna2rnhhyyniqh7w)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between May 17, 2026 and Aug 20, 2026, about one every 32 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260820.16e7f08 latest | 2026-08-20 | 16e7f08 | 6,321 B | A | view · diff |
| git:20260811.925e30f | 2026-08-11 | 925e30f | 6,318 B | A | view · diff |
| git:20260702.cb2392a | 2026-07-02 | cb2392a | 6,276 B | A | view · diff |
| git:20260517.903a724 | 2026-05-17 | 903a724 | 6,262 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 (6321 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_rna2rnhhyyniqh7w GET https://markdownregistry.com/api/v1/resolve?ref=lugassawan/swe-workbench/workflow-codebase-knowledge GET https://markdownregistry.com/api/v1/blob/46a4d38d6bb1d5d8fdecdca0944b162ab8613f8fdaa7505f9b9b570bc4a55d32
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.