What is flow AGENTS.md?

A set of coding instructions for the Flow project, a self-hosted task manager similar to ClickUp or Asana. It explains the project’s mission, repository layout, architecture rules and standard workflow.

Use it when making changes to the Flow codebase, especially its shared package, Cloudflare Worker, Durable Object database, real-time updates, attachments, queues or agent interfaces.

It helps coding agents understand where shared data definitions live and how changes must preserve correctness, ordered updates and fast screen refreshes. The input does not describe a standalone software feature.

How joelborch/flow configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to joelborch/flow. 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/joelborch/flow/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/joelborch/flow

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/joelborch/flow/agents-md/github.svg)](https://agentmods.dev/instructions/joelborch/flow/agents-md)

Your own site

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

Per session 2,809 This file is loaded in full into every session.

When invoked 2,809 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	$0.02809	$0.02809
Opus 5.5	$0.01124	$0.01124
Sonnet 5.5	$0.00562	$0.00562
Haiku 4.5	$0.00281	$0.00281

Measured 2mo ago against content hash 364117c17c95, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flow 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 · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — working on the Flow codebase

Flow is agent-first in two senses. This file covers the first: coding agents making changes to this repo. The second — AI agents using a running Flow instance as a tool via MCP and API keys — is documented in docs/AGENTS_AND_MCP.md.

Mission

Flow is a self-hosted ClickUp/Asana replacement that runs entirely on Cloudflare: one Worker serving the SPA, REST API, MCP server, and WebSockets; one Durable Object holding the whole workspace in SQLite; R2 for attachments; Queues for outbound side effects. It is deliberately small — one workspace per deployment, a handful of entity types, ~5 runtime dependencies — and it stays fast because every architectural rule below protects either correctness (single writer, ordered deltas) or latency (no refetch, optimistic UI). Your job when changing it is to keep both.

Repo layout

Path	Package	What lives there
`packages/shared`	`@flow/shared`	The contract. Zod schemas for every entity, mutation input, delta event, WS message, webhook payload, notification, automation rule; the `MCP_TOOLS` name list; the `WorkspaceRpc` interface; the `LIMITS` size caps. Depends only on zod.
`packages/core`	`@flow/core`	The `Workspace` Durable Object: SQLite schema, all mutations, delta log, WS fanout, fractional positioning, search, visibility filtering, snooze, notifications, and the automation engine (`src/automation/`). Most unit tests live here.
`apps/api`	`@flow/api`	The Hono Worker: auth (Cloudflare Access JWT + `flow_` bearer keys), REST routes in `src/routes/`, MCP server at `/mcp` in `src/mcp/`, WS upgrade at `/ws`, queue consumer for webhooks/email in `src/side-effects/`, `wrangler.jsonc`. Serves the built web app as static assets.
`apps/web`	`@flow/web`	Preact + `@preact/signals` + Tailwind v4 SPA. `src/store/` holds the signal state, delta application, optimistic mutations, and the WS client; `src/board/`, `src/task/`, `src/shell/`, `src/settings/` are UI.
`apps/importer`	`@flow/importer`	Local-only (tsx, never deployed) extract → transform → load pipeline for migrating from ClickUp, with checkpoints and fixtures.

Read the full file on GitHub · 196 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 · 196 lines · 2,809 tokens per session scan A 364117c17c95

Subscribe to this mod's changes

flow AGENTS.md is an instructions file published in the GitHub repository joelborch/flow (0 stars, last pushed 2d ago), licensed MIT. It adds 2,809 tokens to every session, about $0.0112 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.

clickup-alternative cloudflare-workers durable-objects kanban mcp mcp-server

flow AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
flow AGENTS.mdjoelborch/flow	Instructions file	0	2d ago	MIT	A	2,809	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

flow: Instructions file for Codex