What is agents AGENTS.md?

A repository instruction file for coding agents, describing the project's layout, rules, commands, branches, and checks. It also defines how the instructions are rendered for several agent tools.

Use it when an agent needs to set up, modify, test, or validate this agents repository. It covers installing development dependencies, running tests and linters, checking documentation, and rendering agent instructions.

It gives an agent project-specific guidance instead of making it guess how to work in the repository. The listed checks help catch errors in prompts, documentation, scripts, and Python code.

How iuliandita/agents configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to iuliandita/agents. 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/iuliandita/agents/develop/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/iuliandita/agents

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/iuliandita/agents/agents-md/github.svg)](https://agentmods.dev/instructions/iuliandita/agents/agents-md)

Your own site

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

Per session 984 This file is loaded in full into every session.

When invoked 984 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	$0.00984	$0.00984
Opus 5.5	$0.00394	$0.00394
Sonnet 5.5	$0.00197	$0.00197
Haiku 4.5	$0.00098	$0.00098

Measured yesterday against content hash b31a363a18d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agents 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 yesterday.

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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agents

Canonical global prompt rules and subagent roles for coding agents, rendered per harness (Claude Code, Codex, OpenCode, and others) with backed-up deploys. develop is the default and nightly branch, main is stable.

If AGENTS.local.md exists beside this file, read it too. It holds local paths and preferences and never relaxes the rules here.

Commands

python -m pip install -r requirements-dev.txt
python scripts/lint_prompts.py
python scripts/scan_prompt_sources.py
python scripts/check_harness_docs.py
python scripts/check_harness_contract.py
python scripts/check_docs_impact.py
python scripts/check_docs_links.py
python -m pytest -q
bash -n scripts/sync-ai-prompts scripts/render-invariants scripts/render-agents scripts/render-hermes scripts/update scripts/python-runtime.sh
python -m py_compile scripts/*.py
scripts/sync-ai-prompts --check
scripts/sync-ai-prompts --dry-run
scripts/render-agents --check
python3 .github/stack/stack-check.py
npm ci --ignore-scripts --prefix .github/tools/markdownlint && .github/tools/markdownlint/node_modules/.bin/markdownlint-cli2
lychee --config lychee.toml AGENTS.md CHANGELOG.md CONTRIBUTING.md INSTALL.md README.md SECURITY.md 'docs/**/*.md'
scripts/sync-ai-prompts && scripts/render-agents

CI also runs actionlint, gitleaks, zizmor, CodeQL, and the macOS and Windows launcher tests. The last line renders into build/generated/; it never deploys.

Layout

Sources: prompts/ (core, invariants, harnesses/*.md fragments), agents/ (role sources), templates/, skills/. prompts/harnesses/AGENTS.md is the generic-harness fragment, not this file.
build/ and everything rendered from it are outputs; never hand-edit them. Overlays prompts/local.md, prompts/private.md, prompts/private-harnesses.txt, and prompts/models.local.json are gitignored.
scripts/render_prompts.py holds the harness registry; scripts/render_agents.py, render_invariants.py, render_hermes.py, and update.py are the other entry points. Tests are in tests/.
.github/stack/canon.json and stack-check.py are the source for the vendored copies in the sibling repos (skills, mods, idstack); see .github/stack/README.md.
Docs: README.md, INSTALL.md, CONTRIBUTING.md, docs/MAINTENANCE.md. Adding or removing a harness: docs/legacy-harnesses.md and docs/harness-contract.md.

Read the full file on GitHub · 55 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.

yesterday Changed · -8 tokens per session b31a363a18d8
2d ago First seen · 55 lines · 992 tokens per session scan A 2e4a710ae27d

Subscribe to this mod's changes

agents AGENTS.md is an instructions file published in the GitHub repository iuliandita/agents (5 stars, last pushed 2d ago), licensed MIT. It adds 984 tokens to every session, about $0.0039 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 2026-11-04.

Building agents Claude Code Git and workflow Prompting ai-agents automation codex developer-tools

agents AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agents AGENTS.mdiuliandita/agents	Instructions file	5	2d ago	MIT	A	984	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

agents: Instructions file for Codex