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/ag2ai/ag2-assistant/agents-mdgit clone --depth 1 https://github.com/ag2ai/ag2-assistantWrote 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/ag2ai/ag2-assistant/agents-md)<a href="https://agentmods.dev/instructions/ag2ai/ag2-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/ag2ai/ag2-assistant/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 | $0.03252 | $0.03252 |
| Opus 5 | $0.01626 | $0.01626 |
| Sonnet 5 | $0.00650 | $0.00650 |
| Haiku 4.5 | $0.00325 | $0.00325 |
Grade A, and why
ag2-assistant 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 3d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AG2 Assistant — Development Guidelines
AG2 Assistant (package ag2-assistant) is an open-source personal AI assistant
built on AG2's framework.
This file is the contributor guide for humans and AI coding agents alike. For a
product overview see README.md; for the system design see
docs/architecture.md.
AI-assisted contribution policy
We welcome AI-assisted contributions — but you remain responsible for
everything you submit: code, tests, issues, and PR descriptions. Before
opening a PR, read .github/AI_POLICY.md. In short:
understand and test what you submit, make the PR description reflect the real
diff, and be ready to explain the change in your own words. Fill in
.github/PULL_REQUEST_TEMPLATE.md and only
tick a checklist box once it is actually true.
Development setup
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]" # add ",google" for the Gmail/Calendar/Drive extra
pre-commit install # run the lint/format/safety hooks on every commit
Checks (run these before you push)
These are the same checks CI runs. They are advisory: the repository has no rulesets, so
a red pull request is reported by the CI status check rather than blocked by it. (Classic
branch protection needs admin to read, so it has not been ruled out. To enforce this,
require the single CI status check — it stays one name as the test matrix grows.)
ruff check . # lint
ruff format . # auto-format (use --check to verify only)
mypy # typecheck src/assistant (target is configured; pass no path)
pytest -m "not integration" -q # unit tests — no API key needed
npm --prefix web run check # typecheck the SPA (svelte-check, strict)
npm --prefix web test # SPA unit tests (node:test over web/src/**/*.test.ts)
npm --prefix web run build # rebuild the SPA bundle if you touched web/
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.
- 3d ago First seen · 237 lines · 3,252 tokens per session scan A fbe1580932e0
ag2-assistant AGENTS.md is an instructions file published in the GitHub repository ag2ai/ag2-assistant (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 3,252 tokens to every session, about $0.0163 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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.
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).
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.