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.
npx agentmods add instructions/nweii/agent-stuff/agents-mdgit clone --depth 1 https://github.com/nweii/agent-stuffWhat 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 | $0.01153 | $0.01153 |
| Opus 5 | $0.00576 | $0.00576 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Instructions for AI assistants working on this repository.
What this repo is
A personal collection of AI agent skills and subagent definitions. It follows the Claude/Anthropic Agent Skills format.
Directory structure
agent-stuff/
├── skills/ # Agent Skills (Claude format)
├── agents/ # Subagent definitions (copy-only, not installed by bunx)
├── zips/ # Auto-built per-skill zips for drag-into-Claude.ai (generated)
├── templates/ # Templates for new components
└── scripts/ # Catalog + zip build scripts (run by the pre-commit hook)
Reference skills
- Read
nweii-skillsbefore creating, editing, migrating, or installing skills. - If
nweii-loopsis available, read it before working on scheduled tasks, routines, or recurring automations. - Treat those skills as the sources of truth. Do not duplicate their conventions here.
Creating skills
Use templates/SKILL_TEMPLATE.md as a starting point. Key requirements:
- Description is critical — Must clearly state what the skill does and when to use it
- Keep
SKILL.mdunder 500 lines; split complex content into referenced files - Include concrete examples
- Test that the description triggers the skill appropriately
Frontmatter reference
All frontmatter fields for SKILL.md:
| Field | Type | Purpose |
|---|---|---|
name |
required | Lowercase with hyphens, max 64 chars |
description |
required | What skill does + when to use it, max 1024 chars |
argument-hint |
optional | Hint shown after /name, e.g. [issue-number] |
disable-model-invocation |
optional | If true, only user can invoke via /name |
user-invocable |
optional | If false, only Claude can invoke (not shown as /command) |
allowed-tools |
optional | Comma-separated list of tools, e.g. Read, Grep, Glob |
model |
optional | Model to use for this skill |
context |
optional | fork runs in subagent; agent specifies agent type |
agent |
optional | Agent type for context: fork (e.g., Explore, Plan) |
hooks |
optional | Hooks integration |
metadata |
custom | Author/version tracking — see Metadata conventions |
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 First seen · 130 lines · 1,153 tokens per session scan A f79552aa2b32
agent-stuff AGENTS.md is an instructions file published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 13d ago), licensed MIT. It adds 1,153 tokens to every session, about $0.0058 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.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.