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/stealth-factory/skills/agents-mdgit clone --depth 1 https://github.com/stealth-factory/skillsWrote 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.
[](https://agentmods.dev/instructions/stealth-factory/skills/agents-md)<a href="https://agentmods.dev/instructions/stealth-factory/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/stealth-factory/skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03025 | $0.03025 |
| Opus 5 | $0.01512 | $0.01512 |
| Sonnet 5 | $0.00605 | $0.00605 |
| Haiku 4.5 | $0.00302 | $0.00302 |
Grade A, and why
skills 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.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI agents (and humans) authoring skills in this repository.
What this repo is
A collection of skills.sh-compatible agent skills.
Each skill is reusable, on-demand context for an AI coding agent. One skill =
one folder under skills/ with a SKILL.md.
Project tracking: Linear — Skills.
Layout
skills/<skill-name>/SKILL.md # flat (preferred)
skills/<category>/<skill-name>/SKILL.md # only if you have enough to categorise
<skill-name> is kebab-case and matches the name: in the frontmatter. No
manifest file is needed — the skills CLI auto-discovers these paths.
SKILL.md format
---
name: my-skill # kebab-case, matches the folder
description: <one line> # SEE BELOW — this is the most important field
metadata:
author: stealth-factory
version: "1.0.0" # bump on meaningful change (semver)
---
# Title
<the body the agent loads when the skill fires>
The description is the trigger (write it carefully)
It's the only part of a skill that's always in the agent's context; the body loads only when the description matches the task. So write it as concrete triggers, not marketing:
- Good:
Use when an iPhone/iPad page shows black bars, content is cut off at the bar edge, a cropped shadow, or the page jumps after the keyboard closes. - Bad:
Helps with iOS Safari styling.
Lead with what the skill does, then "Use when …" listing the situations, symptoms, and phrases a user might say.
The body
- Write for the agent, not end users — actionable facts, steps, rules.
- Keep it scannable (headings, short sections, tables, code blocks).
- Progressive disclosure: keep
SKILL.mdfocused; if a skill needs heavy reference material or scripts, put them in sibling files and link to them so they load only when needed. - Prefer facts and case-dependent guidance over a single rigid recipe, so the skill stays useful across situations.
- Note provenance (how a non-obvious claim was verified) when it helps trust.
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 · 231 lines · 3,025 tokens per session scan A 1a0f0c6472a1
skills AGENTS.md is an instructions file published in the GitHub repository stealth-factory/skills (3 stars, last pushed 10d ago), licensed MIT. It adds 3,025 tokens to every session, about $0.0151 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
FDEOps AGENTS.md
AGENTS.md instructions for suboss87/FDEOps, covering agents.md - working in the fdeops repository, if you are helping use fdeops in an engagement, if you are contributing to this repository and boundaries.
design-skills CLAUDE.md
Instructions for cuellarfr/design-skills, covering claude.md, what this repo is, skill architecture, plugin packaging and the 10 skills.
core-ai CLAUDE.md
Claude Code instructions for helius-labs/core-ai, covering core ai, compiler-managed sync, mcp server pin, skill versioning and router surface maintenance.
core-ai AGENTS.md
AGENTS.md instructions for helius-labs/core-ai, covering core ai — agent instructions, repository overview, mcp server setup, api key setup and public tool surface.
oh-my-openagent AGENTS.md
AGENTS.md instructions for code-yeongyu/oh-my-openagent, covering oh-my-opencode — opencode plugin, default workflow — how to take on any task, structure, initialization flow and 14 opencode hook handlers.
pm-pilot AGENTS.md
Instructions for arezous/pm-pilot, covering pm pilot, how this workspace works, core principles, context first and context grows through use.