agentleFS
gonnarungonnarun/sdp/skills/review-gate/SKILL.md

review-gate

Skill0 starsChanged 3 months agoMITView on GitHub

Review one existing artifact through SDP's normal cross-model gate without running Stages 1-8. Use when the user invokes the review gate alone, not for implementation or a full SDP workflow.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use workflow-router, security-review and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • parcadeiSkill

    workflow-router

    Goal-based workflow orchestration - routes tasks to specialist agents based on user goals

    Also in 3 projects that use this

  • SentrySkill

    security-review

    Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.

    Also in 4 projects that use this

  • MicrosoftSkill

    diagnose

    Use to systematically diagnose why scenarios fail — identifies root causes by analyzing agent traces, codebase, and behavioral patterns

    Also in 3 projects that use this

The file

Files
SKILL.md

Standalone SDP review gate

Review the named artifact once with the existing scripts/review_gate.py. Do not run the SDP stages, edit the artifact, or create a new gate. Obtain review criteria from the request; ask for the artifact or its author host only when that cannot be determined.

The primary reviewer must be the model opposite the artifact author, not whichever CLI happens to work. For an artifact authored in the current session, use the current host. For an artifact authored elsewhere, use its known author host; if unknown, ask before invoking the gate.

Artifact authorPrimary reviewerGate entry
CodexClaudePrefer bundled claude_review_gate MCP with cwd, prompt, and artifact_path. If unavailable, call the bundled scripts/review_gate.py with --reviewer claude.
Claude CodeCodexCall the bundled scripts/review_gate.py with --reviewer codex. Do not use claude_review_gate: that MCP entry is pinned for Codex-authored work.

Resolve the bundled script from this skill's plugin root, not from the reviewed project's cwd. Pass the project root as --cwd and the artifact path as a separate argument. Keep the review prompt limited to the user's criteria and the artifact's role; the engine reads and bounds the artifact itself.

For CLI fallback, substitute absolute paths in the appropriate host form (the plugin root is two directories above the skills/review-gate/ folder):

python3 "/absolute/plugin/root/scripts/review_gate.py" --cwd "/absolute/project/root" --reviewer claude "<review prompt>" "/absolute/artifact-path"

The line above is for a Codex-authored artifact. For a Claude-authored artifact, use the same command with --reviewer codex. Never copy a bare default-reviewer command between hosts.

The existing gate may try agy only after primary-reviewer infrastructure failure. agy never overrides a valid content BLOCK:. Honor require_primary_verdict and all other configured gate policy; do not switch to agy as primary or invent another fallback. If every allowed provider fails, report BLOCK: INFRA_ERROR.

Report the exact ALLOW: or BLOCK: result, actual provider, and actionable findings. MCP returns the provider with its result; for CLI, read the matching entry in .private/sdp-artifacts/gate-audit.ndjson. If no audit row exists, say provider unknown rather than guessing. A content BLOCK: ends this invocation; revise or retry only on a separate request. Never treat an infrastructure failure as review approval.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.