| name | elegance-pipeline |
| description | Run a persistent multi-agent workflow scoring source-file code quality: 4 scouts, 2 judges, a planner, a verifier, and 1 gated implementer. Use when you want to rank how clean a repo's files are and convert the weakest into gated refactor work. Triggers on "find ugly files", "review code quality". |
| allowed-tools | Read, Grep, Glob, Bash, Agent |
| effort | high |
Elegance Pipeline
Multi-agent code-elegance workflow with persistent state and stage gates.
The orchestrator runs in Python (pipeline.py); the scoring is language-agnostic
over the target repo, anchored by whatever root file fits it — CLAUDE.md,
package.json for a Node.js project, or *.sln for a .NET solution.
Pipeline stages
4 Scouts (parallel, opus) -> 2 Judges (parallel, opus) -> 1 Planner (opus)
-> 1 Verifier (opus) -> 1 Implementer (gated, opus)
State manager
All orchestration goes through the pipeline state manager:
python ${CLAUDE_PLUGIN_ROOT}/elegance_pipeline/pipeline.py [--state-dir <dir>] <command>
Commands: init, status, prompt, submit, signal
Default state lives at .claude/elegance_pipeline/state/ and is shared by default.
If you want one dedicated team per spec, give each run its own --state-dir.
How to orchestrate
- Run
status to see which slots are ready
- For each ready slot, run
prompt --role <role> --slot <slot> to get the task prompt
- Spawn the appropriate fully qualified subagent (
elegance-pipeline:elegance-scout,
elegance-pipeline:elegance-judge, elegance-pipeline:elegance-planner,
elegance-pipeline:elegance-verifier, or elegance-pipeline:elegance-implementer).
If your runtime exposes a different fully qualified name, use that exact identifier instead of the bare short name.
- After each agent completes, submit its output via the state manager
- Run
status again to see what unlocked
- Repeat until the pipeline is complete or blocked
Orchestration rules
- Scouts run in parallel (all 4 at once via background agents)
- Judges run in parallel after ALL scouts are submitted
- Planner runs after BOTH judges are submitted
- Verifier runs after the planner is submitted
- Implementer only runs when the implementation signal is READY
- Never bypass stage gates
- If the verifier says no implementation is warranted, stop
Agent model mapping
| Role | Agent | Model | Access |
|---|
| Scout | elegance-pipeline:elegance-scout | opus | read-only |
| Judge | elegance-pipeline:elegance-judge | opus | read-only |
| Planner | elegance-pipeline:elegance-planner | opus | read-only |
| Verifier | elegance-pipeline:elegance-verifier | opus | read-only |
| Implementer | elegance-pipeline:elegance-implementer | opus | full edit |
Manual signal override
python ${CLAUDE_PLUGIN_ROOT}/elegance_pipeline/pipeline.py [--state-dir <dir>] signal on
python ${CLAUDE_PLUGIN_ROOT}/elegance_pipeline/pipeline.py [--state-dir <dir>] signal off
