What is ai-act-skills AGENTS.md?

An instruction guide for using the ai-act-compliance skill, which helps assess software against the European Union AI Act and related ISO standards.

Use it for questions about AI risk categories, required documentation, impact assessments, AI literacy, incident reporting, and related compliance topics.

It gives coding agents a defined way to recognize AI compliance tasks and follow the repository’s prescribed references and limits.

How abk1969/ai-act-skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to abk1969/ai-act-skills. 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/abk1969/ai-act-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/abk1969/ai-act-skills

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/abk1969/ai-act-skills/agents-md/github.svg)](https://agentmods.dev/instructions/abk1969/ai-act-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/abk1969/ai-act-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/abk1969/ai-act-skills/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/abk1969/ai-act-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/abk1969/ai-act-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 990 This file is loaded in full into every session.

When invoked 990 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	$0.00990	$0.00990
Opus 5	$0.00495	$0.00495
Sonnet 5	$0.00198	$0.00198
Haiku 4.5	$0.00099	$0.00099

Measured 9d ago against content hash 02b25702f08e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-act-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 9d 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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — ai-act-skills

Pointer file for AGENTS-aware runtimes (OpenAI Codex, GitHub Copilot CLI, Cursor, and any harness that follows the agentskills.io specification).

Skill provided by this repository

Skill ID	Entry	Manifest	Reference
`ai-act-compliance`	`skills/ai-act-compliance/SKILL.md`	`skills/ai-act-compliance/ssl.json` (SSL-1.0, arXiv:2604.24026)	`skills/ai-act-compliance/`

Description — Authoritative EU AI Act (Regulation 2024/1689) compliance skill, strictly anchored on ISO/IEC 42001:2023 (AIMS) and ISO/IEC 27090:2025 (AI cybersecurity).

Triggers — Risk classification (art. 5/6/50), conformity assessment (arts. 8–17, 26–27), Annex IV technical documentation, FRIA (art. 27), AI literacy (art. 4), substantial modification (art. 25), regulatory sandboxes (arts. 57–63), GPAI (arts. 51–55), serious-incident reporting (art. 73), ISO 42001 / 27090 mapping.

Resource profile — permission: filesystem.read only. No network, no credentials, no code execution, no external tool calls. touches_sensitive_resources: false.

Recommended install location

Per the superpowers:writing-skills convention (Anthropic):

~/.agents/skills/ai-act-compliance/      # Codex / AGENTS-aware
~/.claude/skills/ai-act-compliance/      # Claude Code
~/.gemini/skills/ai-act-compliance/      # Gemini CLI

How a Codex / AGENTS-aware host should activate the skill

Discovery — read this AGENTS.md at the project root; identify the skill entry at skills/ai-act-compliance/SKILL.md.
Frontmatter parse — read the YAML frontmatter; the description field is the canonical trigger source.
Activation — when a user message matches the description's triggers (see also ssl.json intent_signature for 14 sample queries), load SKILL.md and follow its scene graph (S_PREPARE_SCOPE → S_ACQUIRE_FACTS → S_REASON_TIER → S_ACT_OBLIGATIONS → S_VERIFY_ARTIFACTS → S_FINALIZE_REPORT, with S_RECOVER_INCIDENT parallel route).
Reference reading — when a scene cites references/NN-<topic>.md, read that file. The 15 reference files are the depth content.

Read the full file on GitHub · 83 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.

9d ago First seen · 83 lines · 990 tokens per session scan A 02b25702f08e

Subscribe to this mod's changes

ai-act-skills AGENTS.md is an instructions file published in the GitHub repository abk1969/ai-act-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 990 tokens to every session, about $0.0049 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.

Legal and compliance agent-skills ai-act ai-compliance ai-cybersecurity ai-governance aims

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

ai-act-skills: Instructions file for Codex