Skip to content
Back to search

harness-marketplace

MarketplaceWorks with Claude CodeGitHub

A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/revfactory-harness/badge.svg)](/listings/revfactory-harness)

HTML

<a href="/listings/revfactory-harness"><img src="/api/listings/revfactory-harness/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Via marketplace

/plugin marketplace add revfactory/harness
/plugin install harness@harness-marketplace

As global skills

cp -r skills/harness ~/.claude/skills/harness
cp -r skills/evolve ~/.claude/skills/harness-evolve

No environment variables or experimental flags required.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "harness-marketplace",
  3. "owner": {
  4. "name": "revfactory",
  5. "email": "revfactory@gmail.com",
  6. "url": "https://github.com/revfactory"
  7. },
  8. "plugins": [
  9. {
  10. "name": "harness",
  11. "source": "./",
  12. "description": "에이전트 팀 & 스킬 아키텍트 v2. 도메인/프로젝트에 맞는 하네스를 구성하고, 전문 에이전트를 정의하며, 에이전트가 사용할 스킬을 생성하는 메타 스킬. 워크플로우 오케스트레이션 · 퍼시스턴트 에이전트 협업 · 서브에이전트 위임 3중 실행 모드 지원.",
  13. "version": "2.1.0"
  14. }
  15. ]
  16. }
README.md · README · 125 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="https://img.shields.io/badge/Version-2.1.0-brightgreen.svg" alt="Version">
  3. <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License"></a>
  4. <img src="https://img.shields.io/badge/Claude_Code-Plugin-purple.svg" alt="Claude Code Plugin">
  5. <img src="https://img.shields.io/badge/Execution_Modes-3-teal.svg" alt="3 Execution Modes">
  6. <img src="https://img.shields.io/badge/Patterns-6+Quality-orange.svg" alt="Patterns">
  7. </p>
  8. <p align="center">
  9. <a href="https://revfactory.github.io/harness-animation/">
  10. <img src="harness_reel_en.gif" alt="Harness in 15 seconds: one request becomes an agent team" width="800">
  11. </a>
  12. <br>
  13. <sub>15-second motion reel · <a href="https://revfactory.github.io/harness-animation/">Watch the full 2-minute interactive walkthrough (Korean) →</a></sub>
  14. </p>
  15. # Harness v2 — The Team-Architecture Factory for Claude Code
  16. **English** | [한국어](README_KO.md)
  17. > **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.
  18. ## What's new in v2
  19. v2 is a ground-up rebuild for the current Claude Code multi-agent runtime:
  20. - **Three native execution modes.** v1 knew two modes built on the experimental `TeamCreate` API, which no longer exists. v2 targets what actually ships today:
  21. 1. **Workflow orchestration** — deterministic scripts (`pipeline()` / `parallel()` / schemas / budgets) for fan-outs, verification loops, and large-scale runs
  22. 2. **Persistent agent collaboration** — named agents + `SendMessage` + shared task lists, with context retained across turns
  23. 3. **Sub-agent delegation** — lightweight one-shot parallel dispatch
  24. - **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.
  25. - **No experimental flags.** The `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` dependency is gone entirely.
  26. - **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.
  27. - **`/harness:evolve` actually 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.
  28. - **v1 migration built in.** The factory detects v1 artifacts (`TeamCreate`, `TeamDelete`, experimental flags) and offers a mechanical migration path.
  29. ## Core features
  30. - **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
  31. - **Skill generation** — context-efficient skills via Progressive Disclosure
  32. - **Orchestration** — data-passing protocols (structured schemas, files, messages, tasks), error handling, resume support
  33. - **Verification** — trigger evals, dry runs, with-skill vs. without-skill A/B testing (optionally as a workflow itself)
  34. - **Evolution** — `/harness:evolve` turns usage feedback into measurable next-generation improvements
  35. ## Workflow
  36. ```
  37. Phase 0: Audit existing harness (new / extend / maintain — v1 artifacts detected here)
  38. Phase 1: Domain analysis (incl. control-flow shape of the work)
  39. Phase 2: Execution mode & team architecture design
  40. Phase 3: Agent definitions (.claude/agents/)
  41. Phase 4: Skill generation (.claude/skills/)
  42. Phase 5: Orchestration & CLAUDE.md pointer
  43. Phase 6: Verification & testing
  44. Phase 7: Maintenance — evolution via /harness:evolve
  45. ```
  46. ## Install
  47. ### Via marketplace
  48. ```shell
  49. /plugin marketplace add revfactory/harness
  50. /plugin install harness@harness-marketplace
  51. ```
  52. ### As global skills
  53. ```shell
  54. cp -r skills/harness ~/.claude/skills/harness
  55. cp -r skills/evolve ~/.claude/skills/harness-evolve
  56. ```
  57. No environment variables or experimental flags required.
  58. ## Usage
  59. ```
  60. 하네스 구성해줘
  61. build a harness for this project
  62. design an agent team for <domain>
  63. ```
  64. After using a generated harness:
  65. ```
  66. 하네스 회고해줘 / evolve the harness with this feedback
  67. ```
  68. ### Choosing an execution mode
  69. | Mode | Primitive | When |
  70. |------|-----------|------|
  71. | **Workflow orchestration** | `Workflow` scripts | Control flow is deterministic: enumerable fan-outs, verification loops, large scale, structured outputs |
  72. | **Persistent agents** | `Agent(name:)` + `SendMessage` + tasks | Long-lived specialists that keep context; iterative feedback and negotiation |
  73. | **Sub-agent delegation** | one-shot `Agent` calls | Fire-and-forget parallel work; results only |
  74. 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.
  75. ## Generated artifacts
  76. ```
  77. your-project/
  78. ├── .claude/
  79. │ ├── agents/ # agent definitions (who)
  80. │ │ ├── analyst.md
  81. │ │ ├── builder.md
  82. │ │ └── qa.md
  83. │ └── skills/ # skills (how) + one orchestrator (who-when-in-what-order)
  84. │ ├── analyze/SKILL.md
  85. │ └── build/SKILL.md
  86. └── CLAUDE.md # minimal pointer: trigger rule + change history
  87. ```
  88. ## Migrating from v1
  89. See [docs/migration-v1-to-v2.md](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).
  90. ## Prior results (v1)
  91. 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](https://github.com/revfactory/claude-code-harness)). Treat these as author-measured numbers; run your own pilot for adoption decisions.
  92. ## License
  93. Apache 2.0

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.