What is agent-harnesses?

Guides for operating several coding-agent hosts, including Claude Code, Codex, Copilot, Cursor, Grok, Jules, and OpenCode. Each host has its own settings, permissions, and session rules.

Use it to start and customize coding-agent sessions, configure providers, connect repositories, manage remote coding environments, and review results.

It prevents instructions for one coding-agent host from being applied to another. It also helps keep configuration and session work within the correct host.

agent-harnesses — Skill for Claude Code and Codex by fmind/dot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add fmind/dot --skill agent-harnesses

Clone the repo

git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/agent-harnesses/github.svg)](https://agentmods.dev/skills/fmind/dot/agent-harnesses)

Your own site

<a href="https://agentmods.dev/skills/fmind/dot/agent-harnesses"><img src="https://agentmods.dev/badge/skills/fmind/dot/agent-harnesses/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fmind/dot/agent-harnesses"><img src="https://agentmods.dev/badge/skills/fmind/dot/agent-harnesses.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 536 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00536
Opus 5.5	$0.00010	$0.00214
Sonnet 5.5	$0.00005	$0.00107
Haiku 4.5	$0.00002	$0.00054

Measured 7d ago against content hash 51b6a310e62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-harnesses scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agent-harnesses/SKILL.md · 41 lines

What it actually says

Agent Harnesses

Operate the selected coding-agent host without conflating its configuration, permissions, or lifecycle with another host. Antigravity has its own agy owner.

Workflow

Every host follows these steps; read only the matching guide for its specifics and required resources.

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. Report version gaps before applying a newer recipe, and keep release-specific details upstream.
Resolve precedence and permission scope first: before changing execution behavior; hooks and extensions execute code.
Verify the result, resulting artifacts, and the host's own instruction or skill discovery. Use agent-project for shared instruction layout and mcp-setup for MCP registration.

Task guides

claude: Claude Code sessions and customization.
codex: Codex sessions and customization.
copilot: Copilot sessions and extensions.
grok: Grok Build sessions and configuration.
notifications: Diagnose or change managed turn notifications and their hooks per host.
opencode: OpenCode sessions and provider configuration.

Gotchas

Edit managed host keys in fmind/dot: on this workstation, Claude, Codex, Copilot, Grok, 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.

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago Changed 51b6a310e62f
9d ago Changed · +3 lines 532f8d197d49
11d ago Changed 842471be0f6b
12d ago Changed · -12 lines 849546737ba4
14d ago Changed 9fbc0d71dd53
17d ago Changed · +5 lines 03b0f0b5c0e0
26d ago Changed · +11 lines · -4 tokens per session aa296b4c50d1
29d ago First seen · 34 lines · 28 tokens per session scan A 6d6c286e5eea

Subscribe to this mod's changes

agent-harnesses is a skill published in the GitHub repository fmind/dot (11 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 536 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.

Building agents Claude Code ai-agents chezmoi dotfiles fish-shell mise

dotfiles-bootstrap

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

sebastienrousseau/dotfiles · 88 tokens

vibe

Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…

sebastienrousseau/dotfiles · 137 tokens

agent-harnesses