What is eea.agent.skills AGENTS.md?

Repository instructions for maintaining the eea.agent.skills collection, including how its source skills are built and validated.

They are for building one skill or all skills after source changes and ensuring generated output is updated before committing.

They prevent edits to generated files, accidental changes to organization-wide rules, unreviewed upstream changes, and committed secrets.

eea.agent.skills AGENTS.md — Instructions file by eea

Install

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.

agentmods

npx agentmods add instructions/eea/eea.agent.skills/agents-md

Clone the repo

git clone --depth 1 https://github.com/eea/eea.agent.skills

Made for: Codex, OpenCode.

Per session 1,342 This file is loaded in full into every session.

When invoked 1,342 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01342	$0.01342
Opus 5	$0.00671	$0.00671
Sonnet 5	$0.00268	$0.00268
Haiku 4.5	$0.00134	$0.00134

Measured 2d ago against content hash 77d08de59665, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eea.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 2d 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 · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EEA Agent Skills Repository

This file governs how AI agents work when editing the eea.agent.skills repository itself.

Note: This is the REPO-LOCAL instruction file. For the organization-wide harness that applies to all EEA projects, see harness/EEA-HARNESS.md.

Prohibited Actions

Do not edit harness/EEA-HARNESS.md without explicit user request — that's org-wide policy; changes affect every EEA project
Do not commit unmerged upstream changes to src/skills/*/SKILL.md — always run ./scripts/build.sh first
Do not delete EEA-OVERRIDES.md files — these contain EEA-specific customizations
Do not add new top-level directories without updating this README and the harness routing rules
Do not commit secrets in any file, including test fixtures and example configs

Build System

skills/ is auto-generated. Never edit it directly.

# Build a single skill (merges SKILL.md + EEA-OVERRIDES.md → skills/)
./scripts/build.sh docker-expert

# Build all skills (run with no arguments)
./scripts/build.sh

After any change to src/skills/*/SKILL.md or EEA-OVERRIDES.md, run ./scripts/build.sh and commit the skills/ changes. CI fails if skills/ is out of sync (git status --porcelain skills/ must be clean).

The build script also copies references/, DESIGN.md, and assets/ if present.

Validation

# Full health check: repo consistency, catalog sync, agentskills spec compliance
./scripts/verify.sh

# Validate all source and merged skills against the Agent Skills specification
./scripts/validate-skills.sh

validate-skills.sh auto-installs skills-ref (PyPI) into a temp venv if agentskills is missing.
CI runs both on every PR.

Skill Development Workflow

Adding a New Skill

Create skill directory under src/skills/{skill-name}/
Add upstream SKILL.md (if based on upstream source)
Create EEA-OVERRIDES.md with EEA-specific customizations
Add metadata.json with skill metadata
Update catalog.yaml with new skill entry
Build merged skill: ./scripts/build.sh {skill-name}
Verify: check that skills/{skill-name}/SKILL.md was generated correctly and git status shows the expected changes
Commit: skill: add {skill-name}

Read the full file on GitHub · 140 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.

2d ago First seen · 140 lines · 1,342 tokens per session scan A 77d08de59665

Subscribe to this mod's changes

eea.agent.skills AGENTS.md is an instructions file published in the GitHub repository eea/eea.agent.skills (2 stars, last pushed 25d ago), licensed MIT. It adds 1,342 tokens to every session, about $0.0067 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.

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.

github/spec-kit · 7,104 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

eea.agent.skills AGENTS.md