What is agent-harness-init?

A setup guide for choosing which AI model handles planning, coding, checking, and research tasks in Codex. It saves these choices in a project-only or general configuration.

Use it to set model routing for different agent-harness roles and to warn about invalid settings.

It removes the need to choose model settings manually for every sprint and can use defaults when no configuration exists.

agent-harness-init — Skill for Claude Code and Codex by bouob: A setup guide for choosing which AI model handles…

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.

agentmods

npx agentmods add skills/bouob/agent-harness/agent-harness-init

Any agent

npx skills add bouob/agent-harness --skill agent-harness-init

Clone the repo

git clone --depth 1 https://github.com/bouob/agent-harness

Made for: Claude Code, Codex.

Or install agent-harness, the plugin that ships this one along with the rest of its 5 skills, 1 command, 1 hook.

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/bouob/agent-harness/agent-harness-init.svg)](https://agentmods.dev/skills/bouob/agent-harness/agent-harness-init)

Your own site

<a href="https://agentmods.dev/skills/bouob/agent-harness/agent-harness-init"><img src="https://agentmods.dev/badge/skills/bouob/agent-harness/agent-harness-init.svg" alt="Measured on agentmods" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,094 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00036	$0.02094
Opus 5	$0.00018	$0.01047
Sonnet 5	$0.00007	$0.00419
Haiku 4.5	$0.00004	$0.00209

Measured 5d ago against content hash 2904d72351b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-harness-init 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 5d 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.

codex/skills/agent-harness-init/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Harness Init for Codex

Configure Codex-only model routing for agent-harness.

This skill is the Codex equivalent of Claude Code's /agent-harness:init. Codex does not provide a namespaced slash command for this plugin, so users call this skill as agent-harness-init or $agent-harness:agent-harness-init.

Interaction Goals

This skill should feel like a short first-run setup flow, not a schema dump.

In the first reply, explain in plain language that this sets model routing for planning, checking, coding, and simple research tasks.
Do not show JSON, raw role names, or file paths in the first reply unless the user passed --show or explicitly asked for them.
Keep canonical option labels and example replies in English in this skill. The assistant may still phrase the surrounding explanation in the user's language and should map equivalent replies from other languages.
Ask for at most two decisions in the first round:
- scope: This project only or All projects
- setup style: Quick recommended setup, Follow current session for everything, or Custom setup
Prefer short reply templates such as 1 + 1 or This project only + Custom setup.
Delay .gitignore, exact target paths, and resolved JSON until preview or until the user asks for technical details.
Treat Quick recommended setup as the user-facing label for balanced.
Treat Follow current session for everything as the user-facing label for all-inherit.
For Custom setup, ask by work type first, then map to internal roles:
- Planning and review -> planner and evaluator
- Coding -> generator.code and generator.write
- Research / simple tasks -> generator.research and generator.collect
Default each work-type pair to the same model and reasoning unless the user asks to split them further.
Use concrete examples in the prompt because earlier Codex models are more reliable with explicit answer formats than with open-ended questions.

Read the full file on GitHub · 272 lines

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.

5d ago First seen · 272 lines · 36 tokens per session scan A 2904d72351b1

Subscribe to this mod's changes

agent-harness-init is a skill published in the GitHub repository bouob/agent-harness (5 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,094 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Autonomous Building agents Multi-Agent agent-teams claude-code claude-code-plugin harness-engineering

ci-review

CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs specialized review agents, scores findings, and submits a GitHub PR review via post-review.sh. Always executes post-review.sh to submit a review on every run (including zero-findings runs). Triggers…

rube-de/cc-skills · 127 tokens

pr-check

PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.

rube-de/cc-skills · 67 tokens

council

Consult external AI council (Gemini 3.8 Flash, Codex, GLM-5.3, Kimi) for thorough reviews and consensus-driven decisions. Use ONLY when explicitly invoked with "/council" or when user says "consult the council", "invoke council", or "council review". Do NOT auto-trigger on generic phrases like "thorough review".

rube-de/cc-skills · 82 tokens

babysit

PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.

rube-de/cc-skills · 53 tokens

pr-validity

PR validity analysis: fetch PR diff, extract new code additions, search existing codebase for duplicate or overlapping implementations, classify changes, and create a structured GitHub issue.

rube-de/cc-skills · 38 tokens

brainstorm

You MUST use this skill before /pm when work is ambiguous, scope is unclear, or multiple approaches exist. Explores problem space, proposes 2-3 approaches with trade-offs, and produces an approved spec document that feeds into both issue creation (/pm) and implementation planning (/cdt). Triggers: brainstorm, explore…

rube-de/cc-skills · 96 tokens