code-review-knowledge SKILL.md skillA
code-review-knowledge from parcha-ai/agentrun is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add parcha-ai/agentrun/code-review-knowledge@git:20261112.d69251aPins git:20261112.d69251a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- parcha-ai/agentrun
- Path
.agents/skills/code-review-knowledge/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261112.d69251a, committed Nov 12, 2026
- Size
- 7,663 bytes
- Repository stars
- 1,181
- License
- Apache-2.0
Invariants and past defect patterns of Parcha-ai/agentrun, keyed by path glob. The code reviewer reads it from the base branch and applies only the sections whose glob matches a changed path. Use when reviewing a change, or before changing code under one of the globs below.
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
# Review knowledge: AgentRun
Each section is a path glob, then the invariants that broke before there, with the PR where a reviewer caught it. A
pattern is a lead to check, not a finding: prove it against the change. Built from 2,766 fixed Greptile findings,
our reviewer's threads and the learned review notes, PRs #1-#2328. Keep it under 10 KB; split an area into its own
file under `references/` and link it here when it grows.
## Money: `packages/serve/src/{cap,budget,decision-cap}.ts`, `packages/serve/src/runner/{metrics,model-route}.ts`, `packages/run-adapters/src/**`
- Unknown spend is `null` and stays unknown: `?? 0` on `spentUsd`/`bookedUsd` books it as $0 and lets a capped run go
on (#2232 cap.ts, #1952 port.ts, admit.ts). A zero-dollar hold is still booked.
- A request sent with no turn yet still counts (#2303). A lost request keeps its bound (#1979). A retried settle after
a failed end-mark write books once (#1952). A hold saved before admission is not spend (#1861).
- The DSL's `budget_usd` is the host's: no runner enforces it (by design).
…Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_zl3c6yd5lzxd3lzk/18b973e61e65861a3e56940ace5cf7fc6db609d980958ad136ba79f8ad8a930b.json
Then /plugin install code-review-knowledge@markdownregistry-zl3c6yd5lzxd3lzk in Claude Code. It installs git:20261112.d69251a, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add parcha-ai/agentrun/code-review-knowledge@sha256:18b973e61e65861aThe line at the top of this page pins the label git:20261112.d69251a, 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_zl3c6yd5lzxd3lzk)
2 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in parcha-ai/agentrun/code-review-knowledge since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of code-review-knowledge from somewhere else? Ask it: where did my code-review-knowledge come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 1 version of this file, committed on Nov 12, 2026.
Watch this file (sign in, one email per new version)
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/code-review-knowledge/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
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 (7663 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
parcha-ai/agentrun · 1,181 stars · license Apache-2.0 · pushed 2026-11-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zl3c6yd5lzxd3lzk GET https://markdownregistry.com/api/v1/resolve?ref=parcha-ai/agentrun/code-review-knowledge GET https://markdownregistry.com/api/v1/blob/18b973e61e65861a3e56940ace5cf7fc6db609d980958ad136ba79f8ad8a930b
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.
More from parcha-ai/agentrun
Every file in parcha-ai/agentrun
Browse by kind, by grade A, or by owner.
Kept in .agents/skills, the folder Codex reads. More agent skills for Codex.