Updated 6mo ago
by raphaelchristi
harness-evolver
Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).
56 GitHub stars (56)
+3 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | +1 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | 0 |
| Oct 11 | +1 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 9 skills (9 skills found in its SKILL.md files)
- 5 forks (5 forks)
- 6mo ago last update (Last updated 6mo ago)
Install
Skills CLI
npx skills add raphaelchristi/harness-evolver
Asks which skills and agents to install. Just one: npx skills add raphaelchristi/harness-evolver --skill 'harness:certify' — add -g for every project.
Claude Code
git clone https://github.com/raphaelchristi/harness-evolvercp -r "harness-evolver/skills/certify" ~/.claude/skills/
Copies the harness:certify skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add raphaelchristi/harness-evolver
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
harness:certify
Use when the user wants to verify that the evolved agent's score is stable and reliable. Runs evaluation multiple times and reports mean ± std.
skills/certify/SKILL.md on GitHub (opens in a new tab) -
harness:deploy
Use when the user is done evolving and wants to finalize, clean up, tag the result, or push the optimized agent.
skills/deploy/SKILL.md on GitHub (opens in a new tab) -
harness:evolve
Use when the user wants to run the optimization loop, improve agent performance, evolve the agent, or iterate on quality. Requires .evolver.json to exist (run harness:setup first).
skills/evolve/SKILL.md on GitHub (opens in a new tab) -
harness:health
Use when the user wants to check dataset quality, diagnose eval issues, or before running evolve. Checks size, difficulty distribution, dead examples, coverage, and splits. Auto-corrects issues found.
skills/health/SKILL.md on GitHub (opens in a new tab) -
harness:setup
Use when the user wants to set up the evolver in their project, optimize an LLM agent, improve agent performance, or mentions evolver for the first time in a project without .evolver.json.
skills/setup/SKILL.md on GitHub (opens in a new tab) -
harness:status
Use when the user asks about evolution progress, current scores, best version, how many iterations ran, or whether the loop is stagnating.
skills/status/SKILL.md on GitHub (opens in a new tab) -
dev:dry-run
Use when the user wants to smoke-test the evolve pipeline, test tools, or verify the plugin works end-to-end. Also use when the user says 'dry run', 'smoke test', or 'test pipeline'.
.claude/skills/dev-dry-run/SKILL.md on GitHub (opens in a new tab) -
dev:release
Use when the user wants to release a new version, publish to npm, create a GitHub release, bump version, or tag a release. Also use when the user says 'release', 'publish', 'bump version', 'tag', or 'npm publish'.
.claude/skills/dev-release/SKILL.md on GitHub (opens in a new tab) -
dev:validate
Use when the user wants to validate the plugin, check integrity, verify cross-references, or before a release. Also use when the user says 'validate', 'check plugin', or 'verify'.
.claude/skills/dev-validate/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
harnessby revfactory A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
-
ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
i-have-adhdby ayghri A skill to stop your coding agent from burying the answer. ADHD-friendly output.
-
marketingskillsby coreyhaines31 Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
-
nature-skillsby Yuan1z0825 符合nature论文学术表达和科研绘图的Skill
-
baoyu-skillsby JimLiu