What is init_agents_md AGENTS.md?

A set of operating instructions for coding agents working in a project. AGENTS.md is a standard project file that records rules an agent should follow before and during changes.

Use it to check project rules before editing, understand which instructions apply to each directory, keep related compatibility files aligned, and follow the project’s implementation and verification requirements.

It gives the agent a clear order of authority, editing boundaries, and completion expectations, reducing guesses and unfinished or unsupported work.

How Juce-me/init_agents_md configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Juce-me/init_agents_md. 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/Juce-me/init_agents_md/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Juce-me/init_agents_md

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/juce-me/init_agents_md/agents-md/github.svg)](https://agentmods.dev/instructions/juce-me/init_agents_md/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/juce-me/init_agents_md/agents-md"><img src="https://agentmods.dev/badge/instructions/juce-me/init_agents_md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/juce-me/init_agents_md/agents-md"><img src="https://agentmods.dev/badge/instructions/juce-me/init_agents_md/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,817 This file is loaded in full into every session.

When invoked 2,817 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.

Model	Per session	Once invoked
Fable 5.1	$0.02817	$0.02817
Opus 5.5	$0.01127	$0.01127
Sonnet 5.5	$0.00563	$0.00563
Haiku 4.5	$0.00282	$0.00282

Measured 1mo ago against content hash fc7e67a69c36, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

init_agents_md 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 1mo 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 · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Template version: 2026-09-08

Drop-in operating instructions for coding agents. Read this file before every task.

Working code only. Finish the job. Plausibility is not correctness.

This file follows the AGENTS.md open standard. At the project root and beside every directory-specific AGENTS.md, symlink compatibility files to the local instructions:

ln -s AGENTS.md CLAUDE.md
ln -s AGENTS.md GEMINI.md

When Superpowers is already available, invoke using-superpowers before ordinary task handling and use relevant skills. Do not install tools or create persistent planning artifacts unless the user or project workflow requires them. When docs/AGENTS.md is installed, its docs/agents/ locations override skill-default artifact paths such as docs/superpowers/.

0. Non-negotiables

These rules override later guidance in this file:

No flattery or filler. Start with the answer or action.
Disagree with false premises. Explain the evidence before proceeding.
Never fabricate. Read the source, run the command, or state what remains unknown.
Do not guess through material ambiguity. Follow the decision rule in section 8.
Change only what the request requires. No drive-by fixes, refactors, or formatting.
Protect existing work and contracts. Preserve user changes, architecture boundaries, public interfaces, and migration paths unless the user changes them.
Do not commit sensitive personal or local data. Use repo-relative paths and placeholders; never commit secrets, tokens, real emails, local machine usernames, hostnames, or production identifiers. A configured Git author name may be used where project documentation requires attribution.
No agent or tool branding in branches, commits, PRs, or project content unless explicitly requested.

1. Before editing

State the intended outcome, observable acceptance criteria, files in scope, and verification. Use a numbered plan only when the work is non-trivial.
Before editing a target file, read the instruction chain from the project root through its directory, including nested AGENTS.md files the runtime did not load automatically. Then read the target file and relevant callers or consumers.
Check the worktree and preserve unrelated changes. If required work overlaps uncertain user edits, stop and ask.
When approaches differ materially, explain the tradeoff and recommend one. Do not add ceremony for trivial, reversible edits.

Read the full file on GitHub · 186 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.

1mo ago Changed · +11 lines · +589 tokens per session fc7e67a69c36
2mo ago First seen · 175 lines · 2,228 tokens per session scan A a9add6804be9

Subscribe to this mod's changes

init_agents_md AGENTS.md is an instructions file published in the GitHub repository Juce-me/init_agents_md (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,817 tokens to every session, about $0.0113 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 2026-08-31.

init_agents_md AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
init_agents_md AGENTS.mdJuce-me/init_agents_md	Instructions file	5	1mo ago	MIT	A	2,817	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

init_agents_md: Instructions file for Codex