Chatgpt Apps
Haohao-end/openagent
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI.
Optimize an AI agent's harness for MCP-Atlas benchmark. An agent skill from A-EVO-Lab/a-evolve.
Install Harness Optimizer
$ npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install A-EVO-Lab/a-evolve harness-optimizer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/A-EVO-Lab/a-evolve.git skills-src && mkdir -p .claude/skills && cp -r skills-src/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer .claude/skills/harness-optimizer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "harness-optimizer" agent skill from https://github.com/A-EVO-Lab/a-evolve/tree/main/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer into .claude/skills/harness-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-optimizer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/A-EVO-Lab/a-evolve/tree/main/seed_workspaces/mcp_mh/.claude/skills/harness-optimizerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install A-EVO-Lab/a-evolve harness-optimizer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/A-EVO-Lab/a-evolve.git skills-src && mkdir -p .agents/skills && cp -r skills-src/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer .agents/skills/harness-optimizer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-optimizer" agent skill from https://github.com/A-EVO-Lab/a-evolve/tree/main/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer into .agents/skills/harness-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-optimizer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install A-EVO-Lab/a-evolve harness-optimizer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/A-EVO-Lab/a-evolve.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer .cursor/skills/harness-optimizer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-optimizer" agent skill from https://github.com/A-EVO-Lab/a-evolve/tree/main/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer into .cursor/skills/harness-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-optimizer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/A-EVO-Lab/a-evolve.git --path seed_workspaces/mcp_mh/.claude/skills/harness-optimizer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install A-EVO-Lab/a-evolve harness-optimizer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/A-EVO-Lab/a-evolve.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer .gemini/skills/harness-optimizer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-optimizer" agent skill from https://github.com/A-EVO-Lab/a-evolve/tree/main/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer into .gemini/skills/harness-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-optimizer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install A-EVO-Lab/a-evolve harness-optimizerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/A-EVO-Lab/a-evolve.git skills-src && mkdir -p .github/skills && cp -r skills-src/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer .github/skills/harness-optimizer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-optimizer" agent skill from https://github.com/A-EVO-Lab/a-evolve/tree/main/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer into .github/skills/harness-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-optimizer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install A-EVO-Lab/a-evolve harness-optimizer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/A-EVO-Lab/a-evolve.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer .opencode/skills/harness-optimizer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-optimizer" agent skill from https://github.com/A-EVO-Lab/a-evolve/tree/main/seed_workspaces/mcp_mh/.claude/skills/harness-optimizer into .opencode/skills/harness-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-optimizer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
harness-optimizer- GitHub stars
- 806
- Token cost
- ~982 tokens
- SKILL.md length
- 400 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- None found
At a glance
Optimize an AI agent's harness for MCP-Atlas benchmark. An agent skill from A-EVO-Lab/a-evolve.
- Works in 3 steps: Diagnose — Browse evolution/candidates/.… → Hypothesize — Form specific hypotheses… → Propose — Write new workspace files. You…
- Analyzing execution traces
- SKILL.md covers Objective, What You Can Modify, What You Must NOT Do and The Candidate Archive, plus 2 more sections
- Calls jq
What it does
Harness Optimizer is an agent skill from A-EVO-Lab/a-evolve. Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.
Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
When your agent uses it
- Analyzing execution traces
- Diagnosing failures
- Proposing improved prompts
Example prompts
- “/harness-optimizer”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Diagnose — Browse evolution/candidates/. Compare high-scoring vs
- Hypothesize — Form specific hypotheses about what causes failures and
- Propose — Write new workspace files. You may
What it can do on your machine
Read from SKILL.md and the folder at commit 18ba996. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Harness Optimizer loads about 982 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 400 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 400 words (~982 tokens).
“You are optimizing an AI agent's harness for MCP-Atlas — a benchmark of tool-calling tasks where the agent uses Model Context Protocol (MCP) servers to answer questions by querying APIs, databases, filesystems, and web services.”
- name
- harness-optimizer
Files
Just SKILL.md in seed_workspaces/mcp_mh/.claude/skills/harness-optimizer of A-EVO-Lab/a-evolve.
Open the folder on GitHubat commit 18ba996
Compare with similar skills
Harness Optimizer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Optimizer this skillA-EVO-Lab/a-evolve | 806 | — | ~982 | Automated safety check: Pass | None | |
| Chatgpt AppsHaohao-end/openagent | 807 | 1 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| Workflow Schema Tuningbreaking-brake/cc-wf-studio | 5.4k | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Documentation Serverandrea9293/mcp-documentation-server | 343 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Clawmemyoloshii/ClawMem | 210 | — | ~7.5k | Automated safety check: Pass | MIT | |
| AI Bomcdxgen/cdxgen | 1.1k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Workflow Schema Tuning
breaking-brake/cc-wf-studio
Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.
Documentation Server
andrea9293/mcp-documentation-server
A skill your agent uses when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval.
Clawmem
yoloshii/ClawMem
ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring…
AI Bom
cdxgen/cdxgen
Generates AI-BOM, MCP inventory, AI skill inventory, and AI authorship provenance documents with cdxgen, cataloging models, inference services, Hugging Face purls, MCP servers and their…
Comfy
Comfy-Org/comfy-skills
Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…
More from A-EVO-Lab/a-evolve
All 17 skills in this repoData Formats
A-EVO-Lab/a-evolve
Reading, writing, and converting common data formats (CSV, Excel, JSON, YAML) with correct handling of encoding, types, and edge cases.
Python Data Analysis
A-EVO-Lab/a-evolve
Best practices for multi-step Python tasks including data analysis, HuggingFace datasets, token counting, and any task requiring state across multiple python() calls.
Python Packages
A-EVO-Lab/a-evolve
Installing and using common Python packages in SkillBench containers.
Scientific Computing
A-EVO-Lab/a-evolve
Strategies for scientific computing, numerical methods, bioinformatics/DNA tasks, logic circuit design, algorithmic challenges, and ML training tasks.
Screenshot Analysis
A-EVO-Lab/a-evolve
How to interpret accessibility tree elements and correlate them with screenshot regions for accurate GUI interaction.
Skill Usage
A-EVO-Lab/a-evolve
How to discover, load, and effectively use skills to solve SkillBench tasks.
Related
Works with
Categories
Questions about Harness Optimizer
What does Harness Optimizer do?
Optimize an AI agent's harness for MCP-Atlas benchmark. An agent skill from A-EVO-Lab/a-evolve. Harness Optimizer is an agent skill from A-EVO-Lab/a-evolve. Optimize an AI agent's harness for MCP-Atlas benchmark.
When should I use Harness Optimizer?
Harness Optimizer fits situations like: analyzing execution traces; diagnosing failures; proposing improved prompts.
How do I install Harness Optimizer in Claude Code?
Run `npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a claude-code`. Or copy the skill folder (seed_workspaces/mcp_mh/.claude/skills/harness-optimizer in A-EVO-Lab/a-evolve) into .claude/skills/harness-optimizer in your project. Claude Code loads it when a task matches its description.
How do I install Harness Optimizer in Codex?
Run `npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a codex`. Or copy the skill folder (seed_workspaces/mcp_mh/.claude/skills/harness-optimizer in A-EVO-Lab/a-evolve) into .agents/skills/harness-optimizer in your project. Codex loads it when a task matches its description.
Can I use Harness Optimizer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add A-EVO-Lab/a-evolve --skill harness-optimizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-optimizer, .gemini/skills/harness-optimizer, .github/skills/harness-optimizer and .opencode/skills/harness-optimizer in your project.
What does Harness Optimizer need to run?
Going by SKILL.md and its folder, Harness Optimizer needs the command-line tools its instructions call (jq).
Does Harness Optimizer access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Harness Optimizer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Harness Optimizer use?
No licence was found for Harness Optimizer or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Harness Optimizer use?
About 982 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Harness Optimizer?
Skills that share tags, products or a category with Harness Optimizer: Chatgpt Apps (Haohao-end/openagent, 807 stars), Workflow Schema Tuning (breaking-brake/cc-wf-studio, 5.4k stars), Documentation Server (andrea9293/mcp-documentation-server, 343 stars) and Clawmem (yoloshii/ClawMem, 210 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Optimizer?
A-EVO-Lab (a GitHub organization) maintains it in A-EVO-Lab/a-evolve, which has 806 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on August 22, 2026.
Source: A-EVO-Lab/a-evolve on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.