agent-harnesses
Operate and configure Claude Code, Codex, Copilot, Grok, and OpenCode.
Skill by Médéric HURIER (Fmind)
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fmind-agent-harnesses
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-harnesses
What's inside
- Skill name
agent-harnesses- Description
- Operate and configure Claude Code, Codex, Copilot, Grok, and OpenCode.
- License
- MIT
- Metadata
- kind: collection · author: Médéric HURIER (Fmind) · source: github.com/fmind/dot/tree/main/skills/agent-harnesses · created: 2026-09-16 · updated: 2026-10-24
- Instructions
- 30 lines in SKILL.md · view on GitHub
Files (9)
- SKILL.md
- GUIDE.md · references/claude/
- GUIDE.md · references/codex/
- GUIDE.md · references/copilot/
- GUIDE.md · references/grok/
- features.md · references/grok/references/
- notifications.md · references/
- GUIDE.md · references/opencode/
- features.md · references/opencode/references/
SKILL.md (first lines)
# Agent Harnesses Operate the selected coding-agent host without conflating its configuration, permissions, or lifecycle with another host. Antigravity has its own [agy](../agy/SKILL.md) owner. ## Workflow Every host follows these steps; read only the matching guide for its specifics and required resources. 1. **Check official docs for version-sensitive features**: read the relevant official page and changelog before relying on flags, settings, models, or feature availability; installed help can omit supported flags, so check the version-specific CLI reference before declaring a feature unavailable. Match the installed version, product surface, account, and platform before applying a recipe, report version gaps, and keep release-specific details upstream. Each guide's operation links cover session recovery, automation, and integration decisions; discover other capabilities from the host's official documentation index. 1. **Resolve precedence and permission scope first**: before changing execution behavior; hooks and extensions execute code. 1. **Verify** the result, resulting artifacts, and the host's own instruction or skill discovery. Use [agent-project](../agent-project/SKILL.md) for shared instruction layout and [mcp-setup](../mcp-setup/SKILL.md) for MCP registration. ## Task guides <!-- guides:start --> - [claude](references/claude/GUIDE.md): Claude Code sessions and customization. - [copilot](references/copilot/GUIDE.md): Copilot sessions and extensions. - [notifications](references/notifications.md): Diagnose or change managed turn notifications, brain session-context hooks, and their wiring per host. - [opencode](references/opencode/GUIDE.md): OpenCode sessions and provider configuration. <!-- guides:end --> ## Gotchas - **Edit managed host keys in fmind/dot**: on this workstation, Claude, Copilot, and OpenCode settings are merged from `modify_*` chezmoi templates in `~/.local/share/chezmoi`. A direct edit to a managed key (including through `/config` or a host's settings skill) reverts on `chezmoi apply --force`; unmanaged keys survive. Change the source, preview with `chezmoi diff`, then apply. - **Install vendor skills through the policy**: each guide's Official Skills section names the host's sources; install a requested package only through the [vendor-skill policy](../agent-project/references/vendor-skills.md) and retain the existing package manager's ownership.
From fmind/dot, MIT.
More from fmind/dot
- 0.636score
code-security
Médéric HURIER (Fmind)
Review code security, threat-model designs, and vet third-party skills; scan secrets and vulnerabilities with Gitleaks and Trivy.
SkillAFreshness: A★ 12Claude Code +9 - 0.636score
dot-cli
Médéric HURIER (Fmind)
Run dot: doctor, login/setup, repo status/pull, trust, secret run, cache/prune, disk space, orphans, context budgets, archives.
SkillAFreshness: A★ 12Claude Code +9 - 0.636score
full-review
Médéric HURIER (Fmind)
Full review or routine upkeep: read every repo area, fix tools, dead code, stale config, and ignore files, and prove all checks pass.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
diagrams-as-code
Médéric HURIER (Fmind)
Create and check Mermaid, SVG, and D2 diagrams and README illustrations.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
chrome-devtools
Médéric HURIER (Fmind)
Debug Chrome with DevTools MCP: console, network, performance, accessibility.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
course-development
Médéric HURIER (Fmind)
Design technical courses, lessons, exercises, and executable labs.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
dot-skills
Médéric HURIER (Fmind)
Maintain fmind/dot skill packages, catalog budgets, package contracts, and installed links.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
agent-frameworks
Médéric HURIER (Fmind)
Build Python agents with Google ADK, LangChain, LangGraph, and agents-cli.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
agent-protocols
Médéric HURIER (Fmind)
Implement A2A agents, MCP servers, and ACP editor integrations in Python.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
agent-usage
Médéric HURIER (Fmind)
Analyze agent token usage and costs with dot and DuckDB queries.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
chezmoi
Médéric HURIER (Fmind)
Manage chezmoi source names, templates, secrets, diffs, and deployment in fmind/dot.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
agent-evaluation
Médéric HURIER (Fmind)
Evaluate prompt, model, retrieval, and agent changes with repeated graded trials.
SkillAFreshness: A★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 24, 2026 (4 days ago)
- Last release
- Oct 24, 2026 (4 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/fmind/dot
- Website
- fmind.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Médéric HURIER (Fmind)
- 0.636score
full-review
Médéric HURIER (Fmind)
Full review or routine upkeep: read every repo area, fix tools, dead code, stale config, and ignore files, and prove all checks pass.
SkillAFreshness: A★ 12Claude Code +9 - 0.636score
dot-cli
Médéric HURIER (Fmind)
Run dot: doctor, login/setup, repo status/pull, trust, secret run, cache/prune, disk space, orphans, context budgets, archives.
SkillAFreshness: A★ 12Claude Code +9 - 0.636score
code-security
Médéric HURIER (Fmind)
Review code security, threat-model designs, and vet third-party skills; scan secrets and vulnerabilities with Gitleaks and Trivy.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
agent-frameworks
Médéric HURIER (Fmind)
Build Python agents with Google ADK, LangChain, LangGraph, and agents-cli.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
chezmoi
Médéric HURIER (Fmind)
Manage chezmoi source names, templates, secrets, diffs, and deployment in fmind/dot.
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
dot-skills
Médéric HURIER (Fmind)
Maintain fmind/dot skill packages, catalog budgets, package contracts, and installed links.
SkillAFreshness: A★ 12Claude Code +9
Cite this page
agent-harnesses skill. Agent Mart. https://agentmart.dev/skills/fmind-agent-harnesses (last updated 2026-10-24)