graph-run-reviewer skillA
graph-run-reviewer is agent-read markdown (skill) from ronmizrahi/ai-sdlc-graph: 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 wrong.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns 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@git:20260920.2a23c63mdr add ronmizrahi/ai-sdlc-graph/graph-run-reviewer@sha256:f9ea10ab7ac5e02bPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_gbyu7cayscuq2v7v)
1 badge views in 30 days
Versions
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 · 10 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 agent 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.