What is floom AGENTS.md?

Project instructions for Floom, a self-hosted system for running AI workers in isolated environments. They describe setup, local development, testing, architecture, and required secrets.

Use them to set up Floom, start its backend and frontend, understand its structure, and follow its development and testing rules.

They give the coding agent the project's startup commands and safety rules, including when it must ask for credentials.

How floomhq/floom configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to floomhq/floom. 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/floomhq/floom/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/floomhq/floom

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/floomhq/floom/agents-md/github.svg)](https://agentmods.dev/instructions/floomhq/floom/agents-md)

Your own site

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

Per session 808 This file is loaded in full into every session.

When invoked 808 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	$0.00808	$0.00808
Opus 5.5	$0.00323	$0.00323
Sonnet 5.5	$0.00162	$0.00162
Haiku 4.5	$0.00081	$0.00081

Measured 2mo ago against content hash 5dab18ef9bea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

floom 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 2mo 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Floom

Self-hosted runtime for AI workers (script- or agent-mode jobs that run in E2B sandboxes). FastAPI + SQLite backend (apps/api), Next.js frontend (apps/web), MCP server (apps/mcp). Deeper docs: README.md, ARCHITECTURE.md, CONTRIBUTING.md.

Setup (once)

macOS/Linux: ./scripts/setup.sh · Windows: .\scripts\setup.ps1
Creates the backend venv, installs backend + frontend deps, scaffolds apps/api/.env.
Setup cannot complete without secrets only the user has. At minimum OPENAI_API_KEY + E2B_API_KEY (or Bedrock: WORKEROS_*_MODEL=bedrock/... plus AWS creds). Ask the user for these — never invent, guess, or commit them.

Run

macOS/Linux: ./scripts/dev.sh · Windows: .\scripts\dev.ps1
Starts backend (http://localhost:8000) + frontend (http://localhost:3000).
It blocks — it runs both servers in the foreground until Ctrl+C. If you are an agent, run it in the background, or start the two halves yourself: cd apps/api && ./venv/bin/python main.py (Windows: venv\Scripts\python.exe main.py) and cd apps/web && npm run dev.
No auth secret is needed for local dev; the first sign-in creates the account.

Test / lint

Backend: cd apps/api && ./venv/bin/python -m pytest tests/ -q
Frontend: cd apps/web && npm test (vitest) · npm run build · npm run lint

Hard rules (do not violate)

Never commit apps/api/.env, the root .env, or data/ — they hold API keys, secrets, OAuth tokens, sessions, and PATs. They are gitignored; keep it so.
No telemetry by default — never commit a key. The repo ships analytics wiring (PostHog) that is inert unless a key is set: with POSTHOG_API_KEY / NEXT_PUBLIC_POSTHOG_KEY unset, nothing is collected and no data leaves the instance — there is no key and no destination in the source. An operator who wants analytics sets their own PostHog project key (events route to their project). Keep it that way: never commit a key, and never send raw run input/output, secret names/values, connection tokens, or PII.
Don't let worker edits auto-push to this public repo. For real work point FLOOM_WORKERS_DIR / WORKEROS_WORKSPACE_DIR outside the checkout; the engine refuses to version into its own source tree by default.
No em-dashes (—) in web copy strings (npm run lint:emdash fails the build) or in .ps1 scripts (Windows PowerShell 5.1 mis-decodes them). Keep scripts ASCII.

Read the full file on GitHub · 49 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.

2mo ago First seen · 49 lines · 808 tokens per session scan A 5dab18ef9bea

Subscribe to this mod's changes

floom AGENTS.md is an instructions file published in the GitHub repository floomhq/floom (47 stars, last pushed 1mo ago), licensed MIT. It adds 808 tokens to every session, about $0.0032 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.

LLM agent-runtime ai-agents ai-skills ai-workers automation

floom AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
floom AGENTS.mdfloomhq/floom	Instructions file	47	1mo ago	MIT	A	808	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

floom: Instructions file for Codex