grade SKILL.md skillA
grade from svenroth-ai/shipwright is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add svenroth-ai/shipwright/grade@git:20260916.49a7bd9Pins git:20260916.49a7bd9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- svenroth-ai/shipwright
- Path
plugins/shipwright-grade/skills/grade/SKILL.md- Versions recorded
- 6
- Latest version
- git:20260916.49a7bd9, committed Sep 16, 2026
- First version recorded
- Jul 4, 2026
- Size
- 14,426 bytes
- Repository stars
- 14
- License
- MIT
Grade any git repository against the Control Grade rubric (A–F), read-only and deterministic. Projects a cold repo's git history + tests + configs into the same GradeInputs the compliance dashboard uses and reuses the shared scoring engine unchanged. Underivable dimensions render honest n/a and become the "what adopting Shipwright would light up" story. TRIGGER when: the user wants to grade a repository, score a repo's control posture, run /shipwright-grade, get a Control Grade for a local…
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
# Shipwright Grade **Read-only Control Grade for any git repository.** Point it at a local path; it derives what it honestly can from the repo's git history, test inventory and config files, maps those signals onto the shared `GradeInputs`, and reuses the same `compute_grade` engine that powers the compliance dashboard and the certification gate. Dimensions it cannot derive render **n/a** (excluded from the score, never faked) and are surfaced as *controls Shipwright would light up*. > **Honest ceiling.** A cold-repo grade is a *heuristic estimate from the > outside* — it inspects history and structure, it does not verify behaviour. > Every heuristic grade is labelled as such. ## ⚠️ Cross-repo contract — the Command Center renders this report **This report has an external consumer.** The Command Center WebUI ([shipwright-webui](https://github.com/svenroth-ai/shipwright-webui)) renders the `ReportModel` graph **field-for-field** on its *"Grade your repo"* screen — deliberately, so that screen and the downloadable HTML report cannot tell different stories. It consumes `grade.py --format json`, which is literally …
Read the whole file at its exact version.
How to install
mdr add svenroth-ai/shipwright/grade@sha256:6966029b8e3e981fThe line at the top of this page pins the label git:20260916.49a7bd9, 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_m2iq2xoh6cuwrlnq)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jul 4, 2026 and Sep 16, 2026, about one every 15 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260916.49a7bd9 latest | 2026-09-16 | 49a7bd9 | 14,426 B | A | view · diff |
| git:20260714.9def639 | 2026-07-14 | 9def639 | 14,018 B | A | view · diff |
| git:20260707.53cde05 | 2026-07-07 | 53cde05 | 10,214 B | A | view · diff |
| git:20260707.5357ad2 | 2026-07-07 | 5357ad2 | 9,369 B | A | view · diff |
| git:20260704.04ae79a | 2026-07-04 | 04ae79a | 9,117 B | A | view · diff |
| git:20260704.3737436 | 2026-07-04 | 3737436 | 5,896 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 (14426 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
svenroth-ai/shipwright · 14 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_m2iq2xoh6cuwrlnq GET https://markdownregistry.com/api/v1/resolve?ref=svenroth-ai/shipwright/grade GET https://markdownregistry.com/api/v1/blob/6966029b8e3e981fb8209b77e518d5555629aaeaf358e1d03d37bbde77efa79d
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.