What is AutomatiQ AGENTS.md?

Repository instructions for AutomatiQ, an open-source toolkit that records browser actions and network traffic, then helps turn that captured data into Python scripts for web automation.

Use them when developing or debugging AutomatiQ, especially when working with its Chrome DevTools Protocol recorder, generated Python automation scripts, or proxy configuration.

They give a coding agent the project background, package layout, important commands, and rules for handling proxy-related work.

How StoneSteel27/AutomatiQ configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to StoneSteel27/AutomatiQ. 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/StoneSteel27/AutomatiQ/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/StoneSteel27/AutomatiQ

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/stonesteel27/automatiq/agents-md/github.svg)](https://agentmods.dev/instructions/stonesteel27/automatiq/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/stonesteel27/automatiq/agents-md"><img src="https://agentmods.dev/badge/instructions/stonesteel27/automatiq/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/stonesteel27/automatiq/agents-md"><img src="https://agentmods.dev/badge/instructions/stonesteel27/automatiq/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,304 This file is loaded in full into every session.

When invoked 1,304 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	$0.01304	$0.01304
Opus 5.5	$0.00522	$0.00522
Sonnet 5.5	$0.00261	$0.00261
Haiku 4.5	$0.00130	$0.00130

Measured 9d ago against content hash 186e8f17434a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AutomatiQ 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines

Project Map

src/automatiq/mcp/ - MCP server: FastMCP stdio server (server.py), runtime, annotation, logging_setup, vision, status_log. Every module stays under 700 lines.
src/automatiq/core/ - Recorder engine: config, events, cancel_standard, browser_manager, bin_manager, telemetry, and recorder/ (with cdp/, compile/, extension/ subpackages).
tests/ - Pytest suite: 16 modules, 101 tests.
Legacy CLI (record/run/agent/resume/feedback), LLM investigator agent, IPython sandbox, telemetry server backend, and banner scripts live only on the legacy/v0.3.x branch - do not port them back without explicit instruction.

Daily Commands

uv sync
uv run pytest -q
uv run ruff check src tests

Use uv strictly. Do not use pip or poetry.
Run tests regularly with uv run pytest -q.

Doctrine

Recorder changes are test-first. Fake CDP events fed to real handlers; new CDP event types, attributes, or output artifacts come with factories in conftest.py, handler tests, and compile tests in the same change.
Tests never touch the network, a real browser, or a real LLM. Use fake CDP events and monkeypatch seams - e.g. patch automatiq.mcp.runtime.vision_preflight - instead of live services.
The MCP surface stays five tools (start_recording, stop_recording, wait_for_completion, get_status, annotate_user_interactions). New capabilities extend existing tools or the per-session README, not MCP resources.
Never log or echo recorder_api_key values.
Recordings under automatiq_sessions/ are unredacted secrets - never commit them. Same for .env.

Config

Precedence: AUTOMATIQ_* env > ~/.automatiq/config.toml > defaults.

Models: never hardcode model names. The model comes from [models] recorder config (a litellm string) only. The vision key comes ONLY from [models] recorder_api_key in ~/.automatiq/config.toml (keyless base_url local endpoints need none); provider env vars are never consulted as a key source and are overwritten by the config key when present; the key is read fresh per recording.

Read the full file on GitHub · 107 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 Changed · +2 tokens per session 186e8f17434a
13d ago Changed 1d27d425b8c8
2mo ago Changed · +4 lines · -367 tokens per session 08f9c24a1f44
2mo ago First seen · 103 lines · 1,669 tokens per session scan A 6dd6affece36

Subscribe to this mod's changes

AutomatiQ AGENTS.md is an instructions file published in the GitHub repository StoneSteel27/AutomatiQ (178 stars, last pushed 10d ago), licensed MIT. It adds 1,304 tokens to every session, about $0.0052 per session on Opus 5.5. 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.

Python ai-agents browser-automation data-extraction web-scraping webscraping

AutomatiQ AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AutomatiQ AGENTS.mdStoneSteel27/AutomatiQ	Instructions file	178	10d ago	MIT	A	1,304	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

AutomatiQ: Instructions file for Codex