mcpField
T
team-review

team-review

github.com/catlog22Testing & quality2.1k47 installsUpdated 19w ago
Repository

About team-review

team-review is a multi-agent skill for code review using scanner, reviewer, and fixer roles. It supports a pipeline from toolchain and LLM scanning through root-cause analysis to automated fixes, with rollback on failure.

Key features

  1. 01Coordinate scanner, reviewer, and fixer roles
  2. 02Scan with a toolchain and LLM
  3. 03Enrich deep analysis with root causes
  4. 04Apply fixes with rollback on failure
  5. 05Run full, fix-only, or quick-scan modes

Use cases

  1. 01Scan code and compile review findings
  2. 02Analyze root causes and produce fixes
  3. 03Run only a scan or skip review and fix

MCP support

The README describes using mcp__ccw-tools__team_msg as a message bus for team-session coordination.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/catlog22/claude-code-workflow --skill team-review

After installing, type/team-reviewin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

roles/coordinator/
role.md
roles/coordinator/commands/
analyze.md
dispatch.md
monitor.md
roles/fixer/
role.md
roles/reviewer/
role.md
roles/scanner/
role.md
specs/
dimensions.md
finding-schema.json
pipelines.md
team-config.json

Details

From the project README

Team Review

Orchestrate multi-agent code review: scanner -> reviewer -> fixer. Toolchain + LLM scan, deep analysis with root cause enrichment, and automated fix with rollback-on-failure.

Architecture

Skill(skill="team-review", args="task description")
                    |
         SKILL.md (this file) = Router
                    |
     +--------------+--------------+
     |                             |
  no --role flag              --role <name>
     |                             |
  Coordinator                  Worker
  roles/coordinator/role.md    roles/<name>/role.md
     |
     +-- analyze -> dispatch -> spawn workers -> STOP
                                    |
                    +-------+-------+-------+
                    v       v       v
                [scan]  [review]  [fix]
                team-worker agents, each loads roles/<role>/role.md

Role Registry

RolePathPrefixInner Loop
coordinatorroles/coordinator/role.md——
scannerroles/scanner/role.mdSCAN-*false
reviewerroles/reviewer/role.mdREV-*false
fixerroles/fixer/role.mdFIX-*true

Role Router

Parse $ARGUMENTS:

  • Has --role <name> -> Read roles/<name>/role.md, execute Phase 2-4
  • No --role -> @roles/coordinator/role.md, execute entry router

Shared Constants

  • Session prefix: RV
  • Session path: .workflow/.team/RV-<slug>-<date>/
  • Team name: review
  • CLI tools: ccw cli --mode analysis (read-only), ccw cli --mode write (modifications)
  • Message bus: mcp__ccw-tools__team_msg(session_id=<session-id>, ...)

Worker Spawn Template

Coordinator spawns workers using this template:

Agent({
  subagent_type: "team-worker",
  description: "Spawn <role> worker",
  team_name: "review",
  name: "<role>",
  run_in_background: true,
  prompt: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: review
requirement: <task-description>
inner_loop: <true|false>

## Progress Milestones
session_id: <session-id>
Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
Report blockers immediately via team_msg type="blocker".
Report completion via team_msg type="task_complete" after final SendMessage.

Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
})

User Commands

CommandAction
check / statusView pipeline status graph
resume / continueAdvance to next step
--fullEnable scan + review + fix pipeline
--fixFix-only mode (skip scan/review)
-q / --quickQuick scan only
--dimensions=sec,cor,prf,mntCustom dimensions
-y / --yesSkip confirmations

Completion Action

When pipeline completes, coordinator presents:

AskUserQuestion({
  questions: [{
    question: "Review pipeline complete. What would you like to do?",
    header: "Completion",
    multiSelect: false,
    options: [
      { label: "Archive & Clean (Recommended)", description: "Archive session, clean up team" },
      { label: "Keep Active", description: "Keep session for follow-up work" },
      { label: "Export Results", description: "Export deliverables to target directory" }
    ]
  }]
})

Session Directory

.workflow/.team/RV-<slug>-<date>/
├── .msg/messages.jsonl     # Team message bus
├── .msg/meta.json          # Session state + cross-role state
├── wisdom/                 # Cross-task knowledge
├── scan/                   # Scanner output
├── review/                 # Reviewer output
└── fix/                    # Fixer output

Specs Reference

Error Handling

ScenarioResolution
Unknown --role valueError with available role list
Role not foundError with expected path (roles//role.md)
CLI tool failsWorker fallback to direct implementation
Scanner finds 0 findingsReport clean, skip review + fix
User declines fixDelete FIX tasks, complete with review-only results
Fast-advance conflictCoordinator reconciles on next callback
Completion action failsDefault to Keep Active

Comments

Markdown supported