What is multi-harness-agent-template AGENTS.md?

A repository instruction file called AGENTS.md that tells coding agents how to work in a project. It defines project identity, the order for reading instructions, and modes such as exploring, planning, implementing, and reviewing.

Use it to document the codebase, identify the main technologies and maintainers, point agents to detailed rules, and limit what they may change in each operating mode.

It gives agents a shared source of project rules and reduces the risk of following outdated or conflicting instructions.

multi-harness-agent-template AGENTS.md — Instructions file for Codex and OpenCode by stephanemalho: A repository instruction file called AGE

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 instructions/stephanemalho/multi-harness-agent-template/agents-md

Clone the repo

git clone --depth 1 https://github.com/stephanemalho/multi-harness-agent-template

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/stephanemalho/multi-harness-agent-template/agents-md.svg)](https://agentmods.dev/instructions/stephanemalho/multi-harness-agent-template/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/stephanemalho/multi-harness-agent-template/agents-md"><img src="https://agentmods.dev/badge/instructions/stephanemalho/multi-harness-agent-template/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,351 This file is loaded in full into every session.

When invoked 1,351 The same file — it is already loaded in full.

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	$0.01351	$0.01351
Opus 5	$0.00675	$0.00675
Sonnet 5	$0.00270	$0.00270
Haiku 4.5	$0.00135	$0.00135

Measured 5d ago against content hash 0b7c2daae570, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

multi-harness-agent-template 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 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.

AGENTS.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the canonical entrypoint for all AI coding agents working in this repository.

Keep it short, current, and practical. Put detailed project knowledge in docs/agent-rules/, docs/skills/, and docs/templates/.

Project Identity

Project name: PROJECT_NAME_REPLACE_ME
Project type: PROJECT_TYPE_REPLACE_ME
Primary stack: STACK_REPLACE_ME
Runtime/package manager: RUNTIME_REPLACE_ME
Main branch: main
Human maintainer: OWNER_REPLACE_ME

Source Of Truth

Use this order when gathering project instructions:

AGENTS.md
docs/agent-rules/README.md
The task-specific files in docs/agent-rules/
The task-specific workflow in docs/skills/
Harness-specific adapter docs only when working on that harness

Do not put canonical business rules only in .codex/, .claude/, .gemini/, or another harness folder.

Agent Operating Modes

Explore

Read-only. Understand architecture, dependencies, existing decisions, and risks.

Plan

Read-only. Produce an implementation plan, touched files, validation commands, and risks.

Implement

Edit only inside the approved scope.

Review

Read-only. Check correctness, tests, architecture, security, and rule compliance.

Validate

Run deterministic checks and report exact command results.

Parallel Agent Workflow

Each active task branch is owned by one harness: Codex, Claude Code, Gemini CLI, or another configured harness.
A harness coordinator may use multiple native agents or subagents on its branch.
Parallel writing is allowed only when the coordinator assigns explicit, non-overlapping file ownership. Shared contracts and files have one writer at a time.
Requests to use agents, subagents, or parallel work never authorize creating a branch, clone, or worktree.
Additional worktrees require explicit approval from the human maintainer. An optional helper may be retained only for that approved case.
Use each harness's native delegation model; do not assume every harness exposes identical agent capabilities, nesting, tools, or isolation.
Branch format: agent/<harness>/<ticket-or-task>/<short-slug>.
Harness names: codex, claude, gemini, or another lowercase tool id.
Agents may propose changes, but final merge requires human review.
Agents must not merge or push directly to main.

Read the full file on GitHub · 146 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 · 146 lines · 1,351 tokens per session scan A 0b7c2daae570

Subscribe to this mod's changes

multi-harness-agent-template AGENTS.md is an instructions file published in the GitHub repository stephanemalho/multi-harness-agent-template (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,351 tokens to every session, about $0.0068 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.

Building agents

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 · 5,182 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

multi-harness-agent-template AGENTS.md