Agent-Harness-Kit: Instructions file for Codex

AGENTS.md

Agent-Harness-Kit AGENTS.md is an instructions file for Codex, OpenCode from Eduardo-Salvador/Agent-Harness-Kit. It costs 4,938 tokens per session, scanned A, original, MIT.

A shared instruction file for Agent-Harness-Kit, a system that routes coding requests through different levels of planning and review. It requires each request to be classified as direct-trivial, vibe, graph-only, or full-harness before the matching process begins.

In plain words
What is it for?
Use it to route requests, decide when to load planning or review skills, handle context pressure, and apply safeguards around integrations, permissions, data changes, and external effects.
Why use it?
It prevents small tasks from receiving unnecessary ceremony and ensures complex or risky work gets the required checks, approvals, and context.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is Eduardo-Salvador/Agent-Harness-Kit's own configuration. It tells Codex and OpenCode how to work on Agent-Harness-Kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Agent-Harness-Kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Eduardo-Salvador/Agent-Harness-Kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Eduardo-Salvador/Agent-Harness-Kit/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Eduardo-Salvador/Agent-Harness-Kit

Made for: Codex, OpenCode.

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.

agentmods badge for Agent-Harness-Kit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eduardo-salvador/agent-harness-kit/agents-md/github.svg)](https://agentmods.dev/instructions/eduardo-salvador/agent-harness-kit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/eduardo-salvador/agent-harness-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/eduardo-salvador/agent-harness-kit/agents-md/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.

agentmods 80×15 button for Agent-Harness-Kit AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/eduardo-salvador/agent-harness-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/eduardo-salvador/agent-harness-kit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,938 This file is loaded in full into every session.
When invoked 4,938 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04938 $0.04938
Opus 5 $0.02469 $0.02469
Sonnet 5 $0.00988 $0.00988
Haiku 4.5 $0.00494 $0.00494

Measured 4d ago against content hash a8e374ee90c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Agent-Harness-Kit AGENTS.md 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 4d 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.

AGENTS.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Harness Kit — operational map

Codex loads this file before work. Claude Code imports it from CLAUDE.md. This is the shared, platform-neutral policy map; load details progressively and do not preload the repository.

Request-routing gate — before all Harness ceremony

Before first-run, status/resume loading, feature discovery, planning, graph, TDD, review, or full status ceremony, automatically load .agents/skills/request-router/SKILL.md and follow request routing. Classify every request into exactly one lane: direct-trivial, vibe, graph-only, or full-harness.

Route deterministically first, then assign the orthogonal assurance level none, light, or full; follow adaptive execution and assurance. Use an available economical AI classifier only when genuine ambiguity remains and classification costs less than the work; never add a provider dependency, invent credentials, hardcode a model ID, or claim a silent same-context model switch. Explicit full-harness always wins. Automatically select full-harness only for two or more real agents/independent contexts, a human decision loop, a required audit, a model too weak or uncertain for the work, unresolved consequential ambiguity, or an explicit request. API, dependency, migration, authentication, integration, or other risk keywords alone do not force the lane; they may raise assurance or narrow authority after inspection.

Before decomposing graph-only or full-harness work, run the mandatory executable preflight with all declared paths, scripts, environment names, native commands, validator, browser requirement, and proven worker capacity. A failed probe becomes an exact prerequisite or capability-degradation result before graph creation; never discover these setup defects through repeated implementation replans.

Direct-trivial fast path

A request is direct-trivial only when the decided, localized change is presentation/static content or an equally mechanical value, introduces no product behavior or full-Harness condition, and should take only a few minutes. Read the target and nearest rules, make the edit, run the smallest useful check, and create no Harness artifacts.

Read the full file on GitHub · 106 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.

  1. 4d ago Changed · +25 lines · +538 tokens per session a8e374ee90c6
  2. 9d ago First seen · 81 lines · 4,400 tokens per session scan A 96cfd45e13b7

Subscribe to this mod's changes

Agent-Harness-Kit AGENTS.md is an instructions file published in the GitHub repository Eduardo-Salvador/Agent-Harness-Kit (6 stars, last pushed 5d ago), licensed MIT. It adds 4,938 tokens to every session, about $0.0247 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens