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/builderced/agent-skills/agents-mdgit clone --depth 1 https://github.com/BuilderCed/agent-skillsWhat 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 | $0.00317 | $0.00317 |
| Opus 5 | $0.00159 | $0.00159 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
agent-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 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.
What it actually says
AGENTS.md
This repository contains cross-platform AI agent skills for regulated industries and underserved markets.
Build & Test
# Lint all skills
bash scripts/audit-all.sh
# Install a skill locally (Claude Code)
npx skills add . --skill eu-ai-act-compliance -a claude-code
# Install a skill locally (Cursor)
npx skills add . --skill eu-ai-act-compliance -a cursor
Conventions
- Skills are in
skills/{category}/{skill-name}/SKILL.md - Each SKILL.md must have YAML frontmatter with: name, description, version, last-updated, platforms, dependencies
- Keep SKILL.md + references/ under 3K tokens total
- Write instructions in natural language (no tool-specific syntax)
- Include graceful degradation for platforms without terminal access
- Legal/regulatory skills must include a disclaimer
Structure
skills/{category}/{skill-name}/
├── SKILL.md # Core skill (cross-platform)
├── references/ # Schemas, checklists, templates
├── claude/ # Claude Code extensions (hooks, agents)
├── cursor/ # Cursor adaptations
└── tests/ # Test cases
Do NOT
- Reference platform-specific tools (Read, Write, Bash) in SKILL.md core
- Include copyrighted content (AFNOR standards, EN norms)
- Exceed 3K tokens per skill + references
- Skip the disclaimer on regulatory skills
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 · 44 lines · 317 tokens per session scan A 061488b19e92
agent-skills AGENTS.md is an instructions file published in the GitHub repository BuilderCed/agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 317 tokens to every session, about $0.0016 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
awesome-matematic-skills-pl AGENTS.md
Instructions for matematicsolutions/awesome-matematic-skills-pl, covering agents.md - awesome-matematic-skills-pl, project goal, matematic context (hard constraints), repo structure and build and test.
mpesa-mcp AGENTS.md
Instructions for gabrielmahia/mpesa-mcp, covering agents.md — mpesa-mcp, what this repo is, architecture, tool annotations (critical) and environment variables.
ai-act-skills AGENTS.md
Instructions for abk1969/ai-act-skills, covering agents.md — ai-act-skills, skill provided by this repository, recommended install location, how a codex / agents-aware host should activate the skill and tool-name mapping.
ai-act-skills GEMINI.md
Instructions for abk1969/ai-act-skills, covering gemini.md — ai-act-skills, skill exposed to gemini cli, activation contract, tool-name compatibility and install.
wapimaji-mcp AGENTS.md
AGENTS.md instructions for gabrielmahia/wapimaji-mcp, covering agents.md — wapimaji mcp, purpose, structure and key rules.
civic-agent-kit AGENTS.md
AGENTS.md instructions for gabrielmahia/civic-agent-kit, covering agents.md — civicagentkit, structure and rules.