What is agent-stuff AGENTS.md?

Repository instructions for AI assistants working in `agent-stuff`, a collection of agent skills and subagent definitions. They describe the project layout and rules for creating or changing skills.

For navigating this repository, following its conventions, and creating, editing, migrating, or installing skills.

They give an agent the project context and prevent it from overlooking required reference skills, templates, or generated files.

How nweii/agent-stuff configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to nweii/agent-stuff. 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/nweii/agent-stuff/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/nweii/agent-stuff

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/nweii/agent-stuff/agents-md/github.svg)](https://agentmods.dev/instructions/nweii/agent-stuff/agents-md)

Your own site

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

Per session 1,248 This file is loaded in full into every session.

When invoked 1,248 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	$0.01248	$0.01248
Opus 5.5	$0.00499	$0.00499
Sonnet 5.5	$0.00250	$0.00250
Haiku 4.5	$0.00125	$0.00125

Measured 25d ago against content hash c8df8bb717b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-stuff 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 25d 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 · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-stuff

This public repository is a curated distribution of reusable agent skills and plugins.

Required context

Read nweii-skills before creating, editing, migrating, or installing skills. It defines skill structure, frontmatter, privacy tiers, installation, and source ownership.
Read nweii-loops before working on scheduled tasks, routines, or recurring automations.
Use templates/SKILL_TEMPLATE.md when starting a skill.

Public boundary

Everything tracked here is public. Keep general skills vendor-neutral and user-neutral.
A skill marked metadata.internal: true may describe Nathan's non-sensitive setup, but it must remain understandable and adaptable to a public reader.
Keep private names, confidential material, credentials, and private-repository details out of this repository.
For Nathan's paired-repository workflow, author in the complete private library, then export approved public copies here after privacy review. Preserve public skill names and install paths; nweii-skills describes export validation and deliberate variants.
Installed copies under ~/.agents/skills/ are downstream of repository source.
archive/agents/ preserves retired subagent definitions; keep them outside the active catalog.

Generated files

The pre-commit hook rebuilds the skill catalog in README.md, per-skill archives in zips/, and plugin manifests/catalogs when their sources change.
Do not hand-edit generated catalog entries or archives. Update the skill source or generator instead.
Generated archives use tracked files only. An untracked file does not enter a release archive.

Plugin packaging

Standalone source is skills/<name>/; bundled source is plugins/<id>/skills/<name>/ on the default branch. The folder defines membership, with exactly one copy per skill name in this distribution. Self-contained payloads follow fixed skill discovery in Agent Plugins 1.0.0 and Claude's path rules (checked with Claude Code 2.1.288).

Read the full file on GitHub · 47 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.

25d ago Changed · -11 lines · -268 tokens per session c8df8bb717b3
27d ago Changed · +1 lines · +52 tokens per session 1bac91ea21e3
1mo ago Changed · +85 tokens per session 30e1a04ca0e4
1mo ago Changed · +17 lines · +349 tokens per session bf5878b8c76f
1mo ago Changed · +12 lines · +721 tokens per session 19fcd8984513
1mo ago Changed · -102 lines · -844 tokens per session 542ecc108fe5
2mo ago First seen · 130 lines · 1,153 tokens per session scan A f79552aa2b32

Subscribe to this mod's changes

agent-stuff AGENTS.md is an instructions file published in the GitHub repository nweii/agent-stuff (10 stars, last pushed 10d ago), licensed MIT. It adds 1,248 tokens to every session, about $0.0050 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.

agent-stuff AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-stuff AGENTS.mdnweii/agent-stuff	Instructions file	10	10d ago	MIT	A	1,248	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
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	1,907	GitHub Copilot

agent-stuff: Instructions file for Codex