15-second motion reel · Watch the full 2-minute interactive walkthrough (Korean) →
English | 한국어
Harness is a team-architecture factory for Claude Code. One sentence — "build a harness for this project" · "하네스 구성해줘" — and the plugin turns your domain description into an agent team and the skills they use.
v2 is a ground-up rebuild for the current Claude Code multi-agent runtime:
- Three native execution modes. v1 knew two modes built on the experimental
TeamCreateAPI, which no longer exists. v2 targets what actually ships today:- Workflow orchestration — deterministic scripts (
pipeline()/parallel()/ schemas / budgets) for fan-outs, verification loops, and large-scale runs - Persistent agent collaboration — named agents +
SendMessage+ shared task lists, with context retained across turns - Sub-agent delegation — lightweight one-shot parallel dispatch
- Workflow orchestration — deterministic scripts (
- Workflow-native quality patterns. Adversarial verification, judge panels, loop-until-dry, multi-modal sweeps, completeness critics — codified so generated harnesses filter out plausible-but-wrong output.
- No experimental flags. The
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1dependency is gone entirely. - Sane model policy. v1 pinned every agent to
model: "opus". v2 selects a tier per agent — fable / opus / sonnet — based on the task's complexity, duration, autonomy, and latency needs, and forbids unjustified blanket pins. /harness:evolveactually ships. The evolution mechanism v1 only documented is now a real skill: it captures the delta between your initial and current harness, generalizes feedback, and feeds it back into agents/skills/orchestrators.- v1 migration built in. The factory detects v1 artifacts (
TeamCreate,TeamDelete, experimental flags) and offers a mechanical migration path.
- Agent team design — six architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical Delegation), each mapped to its best v2 execution mode
- Skill generation — context-efficient skills via Progressive Disclosure
- Orchestration — data-passing protocols (structured schemas, files, messages, tasks), error handling, resume support
- Verification — trigger evals, dry runs, with-skill vs. without-skill A/B testing (optionally as a workflow itself)
- Evolution —
/harness:evolveturns usage feedback into measurable next-generation improvements
Phase 0: Audit existing harness (new / extend / maintain — v1 artifacts detected here)
Phase 1: Domain analysis (incl. control-flow shape of the work)
Phase 2: Execution mode & team architecture design
Phase 3: Agent definitions (.claude/agents/)
Phase 4: Skill generation (.claude/skills/)
Phase 5: Orchestration & CLAUDE.md pointer
Phase 6: Verification & testing
Phase 7: Maintenance — evolution via /harness:evolve
/plugin marketplace add revfactory/harness
/plugin install harness@harness-marketplacecp -r skills/harness ~/.claude/skills/harness
cp -r skills/evolve ~/.claude/skills/harness-evolveNo environment variables or experimental flags required.
하네스 구성해줘
build a harness for this project
design an agent team for <domain>
After using a generated harness:
하네스 회고해줘 / evolve the harness with this feedback
| Mode | Primitive | When |
|---|---|---|
| Workflow orchestration | Workflow scripts |
Control flow is deterministic: enumerable fan-outs, verification loops, large scale, structured outputs |
| Persistent agents | Agent(name:) + SendMessage + tasks |
Long-lived specialists that keep context; iterative feedback and negotiation |
| Sub-agent delegation | one-shot Agent calls |
Fire-and-forget parallel work; results only |
The factory picks the mode from the shape of the control flow, not from team size — and mixes modes per phase when that fits better.
your-project/
├── .claude/
│ ├── agents/ # agent definitions (who)
│ │ ├── analyst.md
│ │ ├── builder.md
│ │ └── qa.md
│ └── skills/ # skills (how) + one orchestrator (who-when-in-what-order)
│ ├── analyze/SKILL.md
│ └── build/SKILL.md
└── CLAUDE.md # minimal pointer: trigger rule + change history
See docs/migration-v1-to-v2.md. Summary: remove TeamCreate/TeamDelete/broadcast/flag references, convert fan-outs to Workflow scripts, rewrite remaining collaboration with named agents + SendMessage, drop blanket model: "opus" pins. The factory automates this when it detects v1 artifacts (Phase 0).
A controlled A/B on 15 software-engineering tasks measured the effect of structured pre-configuration on LLM code-agent output quality: mean quality 49.5 → 79.3 (+60%), 15/15 win rate, −32% output variance (n=15, author-run, see revfactory/claude-code-harness). Treat these as author-measured numbers; run your own pilot for adoption decisions.
Apache 2.0