graph-run-reviewer SKILL.md skillA
graph-run-reviewer from ronmizrahi/ai-sdlc-graph is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ronmizrahi/ai-sdlc-graph/graph-run-reviewer@git:20260920.2a23c63Pins git:20260920.2a23c63 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ronmizrahi/ai-sdlc-graph
- Path
plugins/sdlc-graph/skills/graph-run-reviewer/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260920.2a23c63, committed Sep 20, 2026
- Size
- 9,351 bytes
- Repository stars
- 17
- License
- MIT
Review a finished or stuck sdlc-graph run — read its state file, its milestone journals and (when it was traced) every state it passed through, find what actually went wrong, and write the eval that would have caught it. Runs the offline auditor first for the mechanical defects, then looks for the classes no static check reaches: an observation that contradicts the journal, a gate that passed too cleanly, a ledger entry that does not match the tools present, a transition that was legal but…
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
# Graph Run Reviewer ## Goal **Turn one run into one or more tests.** A run that went wrong and produced no eval is a run whose lesson expires with the person who read it. This skill exists to stop that: it reads the artifacts a run leaves behind, works out what actually happened, and — for anything nothing would have caught — writes the check that catches it next time. It is deliberately **not** a remediation tool. It never resumes the run, never fixes the code, never edits the state file. The retired monitor agent was trustworthy for exactly that reason, and it is the reason this can be pointed at a live run without changing its outcome. ## Use When - A run reached `BLOCKED` and you want to know whether the graph or the orchestrator was at fault. - A run reached `DONE` and something about it felt wrong. - After a change to the graph, on a run that exercised it. - You want the run's lessons turned into tests before you forget them. ## Do Not Use When - **You want the run fixed or continued.** That is `sdlc-graph` itself — `resume`. - **You want the code reviewed.** That is `code-quality-pipeline`. This reviews the *run*, not the diff it produced. …
Read the whole file at its exact version.
How to install
mdr add ronmizrahi/ai-sdlc-graph/graph-run-reviewer@sha256:f9ea10ab7ac5e02bThe line at the top of this page pins the label git:20260920.2a23c63, 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_gbyu7cayscuq2v7v)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 20, 2026.
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 (9351 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
ronmizrahi/ai-sdlc-graph · 17 stars · license MIT · pushed 2026-09-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gbyu7cayscuq2v7v GET https://markdownregistry.com/api/v1/resolve?ref=ronmizrahi/ai-sdlc-graph/graph-run-reviewer GET https://markdownregistry.com/api/v1/blob/f9ea10ab7ac5e02b5724bdfa77c04d2ef7817a61277859438894369c04d13704
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.