agent-skills AGENTS.md

Project instructions for TypeFox Agent Skills, a collection of Markdown skill definitions for open-source technologies. They describe the Python scripts, tests, conventions, and restrictions around running skill evaluations.

In plain words
What is it for?
Use them when working on the skill definitions, running ordinary tests, or preparing the repository for separate skill-evaluation sessions.
Why use it?
They keep agents from contaminating evaluations with injected project instructions and clarify how the skill collection is maintained.

Instructions file for CodexOpenCode

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/typefox/agent-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/TypeFox/agent-skills

Made for: Codex, OpenCode.

Per session 1,025 This file is loaded in full into every session.
When invoked 1,025 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.

ModelPer sessionOnce invoked
Fable 5 $0.01025 $0.01025
Opus 5 $0.00513 $0.00513
Sonnet 5 $0.00205 $0.00205
Haiku 4.5 $0.00103 $0.00103

Measured 2d ago against content hash 8f88e3c3bf96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TypeFox Agent Skills

A collection of agent skills in the agentskills.io format for open source technologies maintained at TypeFox. The product is the Markdown skill definitions under skills/ — there is no application to build. Scripts are Python 3.8+, stdlib-only; pytest is the only test dependency.

STOP — before running any skill evaluation

If your task is to run a skill evaluation (skill-evals, or any with-skill vs. baseline comparison): stop immediately — do not start. The harness injects this file and CLAUDE.md into every subagent's context, cached at session start, so eval runs launched from this session are contaminated — this file even describes the eval fixtures, an answer key for baselines — and removing the files mid-session does not help. Remove AGENTS.md and CLAUDE.md first, run the evaluation in a fresh session started without them, and restore both afterwards with git checkout -- AGENTS.md CLAUDE.md.

A session that already started with these files in context can still orchestrate: remove AGENTS.md and CLAUDE.md, then launch every eval run and grader as its own fresh headless session (claude -p) — a separate process assembles project memory from disk at its own start, so nothing is injected while the files are absent. In-process subagents (Agent/Workflow) stay contaminated regardless. Verify, don't assume: grep each child session transcript's first turn for injected AGENTS.md content, and restore the files only after the last child (including retries and graders) has finished.

Commands

pytest skills/agent-experience/scripts/test_check_docs.py -q         # check_docs unit tests (the only script tests so far), <1s
pytest skills/agent-experience/scripts/test_check_docs.py -k NAME    # single test by keyword
python3 skills/agent-experience/scripts/check_docs.py --exclude 'skills/*/evals/*' .   # doc-freshness check, <1s

Installing skills for end use is npx skills add TypeFox/agent-skills (see README) — not needed for development.

Read the full file on GitHub · 45 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.

  1. 2d ago First seen · 45 lines · 1,025 tokens per session scan A 8f88e3c3bf96

Subscribe to this mod's changes

agent-skills AGENTS.md is an instructions file published in the GitHub repository TypeFox/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 1,025 tokens to every session, about $0.0051 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.

Related

Other instructions, from other repositories

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

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 · 5,182 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

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens