What is ff-mcp AGENTS.md?

An AGENTS.md instruction set for setting up ff-mcp, a tool that connects an agent to Firefox. It defines setup steps, safety limits, and required user confirmations.

For guiding ff-mcp installation and Firefox setup while checking software versions, selecting a profile, and preserving security boundaries.

It prevents guessing the Firefox profile and helps avoid exposing tokens, changing system settings, or granting access without approval.

How complynx/ff-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to complynx/ff-mcp. 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/complynx/ff-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/complynx/ff-mcp

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/complynx/ff-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/complynx/ff-mcp/agents-md)

Your own site

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

Per session 870 This file is loaded in full into every session.

When invoked 870 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	$0.00870	$0.00870
Opus 5.5	$0.00348	$0.00348
Sonnet 5.5	$0.00174	$0.00174
Haiku 4.5	$0.00087	$0.00087

Measured 1mo ago against content hash 15d60f99a3c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ff-mcp 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 1mo 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent rules

Goal: set up local ff-mcp from repo. Full runbook: docs/agent-setup.md. User guide: docs/user-setup.md.

Hard limits

Need explicit user profile choice. Never guess profile.
Ask before system-software install, GUI launch, shell-startup edit, or client-config edit outside repo.
Firefox confirmation stays. Never sideload into profile or auto-grant capability.
Never bind MCP outside loopback. Tab grants belong to MCP sessions; persistent rules apply to all sessions.
Do not run ff-mcp serve. Firefox starts native host.

Setup

Check OS, Firefox 150+, Python 3.14, uv.
On Windows, follow Windows installation: use explicit UV_TOOL_DIR and UV_TOOL_BIN_DIR outside AppData. Register the host from an ordinary PowerShell opened outside Codex. Other platforms: uv tool install --force ..
If command missing: run uv tool dir --bin; use absolute binary. Ask before uv tool update-shell.
Run ff-mcp profiles --json.
Show profiles. Ask user for exact path.
Ask before Firefox launch.

Run:

ff-mcp setup --profile "/exact/profile/path" --install-addon --json

User confirms Firefox install. Extension listens automatically while enabled.
Snap/Flatpak may show portal prompt. User approves.
Run ff-mcp connection for the local URL; no token is needed.
Configure chosen client from runbook. Ask before external config write.
Verify tool list, browser_tabs, approved READ, then browser_revoke.

No profile found: user opens about:profiles, copies Root Directory, gives exact path.

Launch fails: run --download-addon; give XPI path. User installs through about:addons → gear → Install Add-on From File….

Checks

UV_CACHE_DIR=/tmp/ff-mcp-uv-cache uv sync --locked --group dev
UV_CACHE_DIR=/tmp/ff-mcp-uv-cache uv run ruff check .
UV_CACHE_DIR=/tmp/ff-mcp-uv-cache uv run ruff format --check .
UV_CACHE_DIR=/tmp/ff-mcp-uv-cache uv run pytest -q
node --test tests/background.test.js tests/content.test.js tests/policy.test.js tests/rule-model.test.js tests/popup.test.js tests/waits.test.js

Read the full file on GitHub · 70 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.

1mo ago Changed · +19 lines · +339 tokens per session 15d60f99a3c2
1mo ago Changed · -1 lines · -13 tokens per session 8e94102d66bf
2mo ago First seen · 52 lines · 544 tokens per session scan A 37add7c48350

Subscribe to this mod's changes

ff-mcp AGENTS.md is an instructions file published in the GitHub repository complynx/ff-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 870 tokens to every session, about $0.0035 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 2026-08-31.

Browser automation

ff-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ff-mcp AGENTS.mdcomplynx/ff-mcp	Instructions file	0	5d ago	MIT	A	870	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	yesterday	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

ff-mcp: Instructions file for Codex