subagent-review

Stars0

Forks0

UpdatedJuly 4, 2026 at 16:54

Runs detect_subagents then run_subagent (codex/gemini) in review mode via subagent-orchestrator MCP, reads .agent-runs outputs, and summarizes findings. Use when the user asks for external CLI review, codex/gemini review, subagent panel, tie-breaker, or invokes /check-subagents, /run-codex-review, /run-gemini-review, /run-subagent-review.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

synthet

synthet/image-scoring-gallery

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Software Quality Assurance Analysts and TestersComputer and Mathematical Occupations·SOC 15-1253

File Explorer

2 files

SKILL.md

readonly

name	subagent-review
description	Runs detect_subagents then run_subagent (codex/gemini) in review mode via subagent-orchestrator MCP, reads .agent-runs outputs, and summarizes findings. Use when the user asks for external CLI review, codex/gemini review, subagent panel, tie-breaker, or invokes /check-subagents, /run-codex-review, /run-gemini-review, /run-subagent-review.

Subagent review (MCP)

Run external CLI coding agents through the subagent-orchestrator MCP server — not by spawning codex / gemini / claude directly in the terminal.

Prerequisites

Sibling checkout: ../subagent-orchestrator/agent-orchestrator built (npm install && npm run build there once)
MCP server enabled in .cursor/mcp.json as cli-review (or user-level subagent-orchestrator) and reloaded in Cursor

Step 1 — Resolve MCP server

Before CallMcpTool, find the enabled server where serverName is subagent-orchestrator (project key cli-review; user-level keys may also appear). Read tool schemas from mcps/*/tools/detect_subagents.json and run_subagent.json. Prefer the project server so WORKSPACE_ROOT is this repo.

Step 2 — Detect

Call detect_subagents (no arguments). Present a short table:

Agent	Available	Mode	Notes

Note: Claude is detection-only in v0.1 — do not rely on it for live run_subagent.

Step 3 — Build request

task — clear review goal (from user or slash command text)
files — workspace-relative paths from @ mentions (max 20; no .env, keys, binaries)
mode — review (default) or tie-breaker when comparing opinions
allowWrites — always false
dryRun — true when user says “dry run” or you are validating setup

Step 4 — Run

Call run_subagent with JSON per references/mcp-tools.md.

For a “panel” (user wants both agents): run sequentially — codex then gemini (or vice versa) with the same task and files. There is no run_subagent_panel tool in v0.1.

Step 5 — Read results

Parse MCP response (outputFile, summary, ok, error).
Read .agent-runs/.../stdout.md at the returned path.
Summarize for the user:

## External review summary

### Verdict
### Findings (blocker | high | medium | low | nit)
### Suggested changes
### Agent agreement (if multiple runs)
### Next steps

Do not apply patches unless the user explicitly asks.

image-scoring-gallery

Suggest files from git diff --name-only under electron/, src/, and mcp-server/ when the user did not @ paths.
Cross-repo changes: review this workspace only; open image-scoring-backend separately for backend diffs (v0.1 cannot span both roots in one MCP call).
Safety: .agent/SAFETY.md

Errors

Situation	Action
Agent not on PATH	Report `detect_subagents` notes; suggest install/auth
`allowWrites` rejected	Explain v0.1 is review-only
Claude run requested	Use Codex or Gemini instead
MCP server missing	docs/technical/EXTERNAL_CLI_REVIEWS.md; build sibling orchestrator

Rule: external-cli-subagents.mdc
Commands: /check-subagents, /run-codex-review, /run-gemini-review, /run-subagent-review
Orchestrator package: ../subagent-orchestrator/agent-orchestrator/README.md

More from this repository

same repository

changelog-commit-push

synthet/image-scoring-gallery

Update CHANGELOG.md and package.json via compiled release_bump harness, then commit/push only when the user asks. Use for /release, changelog updates, or shipping gallery versions.

2026-07-280

gallery-electron-ts

synthet/image-scoring-gallery

Works in image-scoring-gallery on electron/db.ts contract, IPC, apiService, React/Vite, and alignment with sibling image-scoring-backend schema. Use for desktop app bugs, database.engine modes, API URL/port from webui.lock, or TypeScript changes under electron/ or src/. Triggers include Electron gallery, db.ts, IPC, apiService, config.api, PostgreSQL vs api engine, and Vite renderer.

2026-07-280

gallery-ui

synthet/image-scoring-gallery

React component patterns, CSS Modules styling, design tokens, virtualization, and UX constitution for the Driftara Gallery renderer. Use for src/ UI work, styling, FilterPanel/GalleryGrid/ImageViewer, or design:check—not electron/db unless coordinated with gallery-electron-ts.

2026-07-280

validate-implementation

synthet/image-scoring-gallery

Verify implementation against spec AC-n criteria via compiled harness. Use after /implement or /test-and-fix, before /pr-ready. Parses ACs and emits the report; LLM assigns Verified/Failed/Unknown when evidence is not a clean command exit.

2026-07-280

verification-before-completion

synthet/image-scoring-gallery

Use before claiming work is complete, fixed, passing, ready to commit, or ready for PR. Runs scripts/agent_skills/verification_before_completion.py for the claim→proof catalog; LLM interprets output. Never upgrade incomplete verification.

2026-07-280

image-scoring-mcp

synthet/image-scoring-gallery

Driftara Gallery MCP — is-ui-* router-first; backend triage via sibling is-be-mcp search+dispatch.

2026-07-250

name	subagent-review
description	Runs detect_subagents then run_subagent (codex/gemini) in review mode via subagent-orchestrator MCP, reads .agent-runs outputs, and summarizes findings. Use when the user asks for external CLI review, codex/gemini review, subagent panel, tie-breaker, or invokes /check-subagents, /run-codex-review, /run-gemini-review, /run-subagent-review.

Subagent review (MCP)

Run external CLI coding agents through the subagent-orchestrator MCP server — not by spawning codex / gemini / claude directly in the terminal.

Prerequisites

Sibling checkout: ../subagent-orchestrator/agent-orchestrator built (npm install && npm run build there once)
MCP server enabled in .cursor/mcp.json as cli-review (or user-level subagent-orchestrator) and reloaded in Cursor

Step 1 — Resolve MCP server

Step 2 — Detect

Call detect_subagents (no arguments). Present a short table:

Agent	Available	Mode	Notes

Note: Claude is detection-only in v0.1 — do not rely on it for live run_subagent.

Step 3 — Build request

task — clear review goal (from user or slash command text)
files — workspace-relative paths from @ mentions (max 20; no .env, keys, binaries)
mode — review (default) or tie-breaker when comparing opinions
allowWrites — always false
dryRun — true when user says “dry run” or you are validating setup

Step 4 — Run

Call run_subagent with JSON per references/mcp-tools.md.

For a “panel” (user wants both agents): run sequentially — codex then gemini (or vice versa) with the same task and files. There is no run_subagent_panel tool in v0.1.

Step 5 — Read results

Parse MCP response (outputFile, summary, ok, error).
Read .agent-runs/.../stdout.md at the returned path.
Summarize for the user:

## External review summary

### Verdict
### Findings (blocker | high | medium | low | nit)
### Suggested changes
### Agent agreement (if multiple runs)
### Next steps

Do not apply patches unless the user explicitly asks.

image-scoring-gallery

Suggest files from git diff --name-only under electron/, src/, and mcp-server/ when the user did not @ paths.
Cross-repo changes: review this workspace only; open image-scoring-backend separately for backend diffs (v0.1 cannot span both roots in one MCP call).
Safety: .agent/SAFETY.md

Errors

Situation	Action
Agent not on PATH	Report `detect_subagents` notes; suggest install/auth
`allowWrites` rejected	Explain v0.1 is review-only
Claude run requested	Use Codex or Gemini instead
MCP server missing	docs/technical/EXTERNAL_CLI_REVIEWS.md; build sibling orchestrator

Rule: external-cli-subagents.mdc
Commands: /check-subagents, /run-codex-review, /run-gemini-review, /run-subagent-review
Orchestrator package: ../subagent-orchestrator/agent-orchestrator/README.md