What is flow CLAUDE.md?

A set of instructions for coding agents working on Flow, a self-hosted task manager similar to ClickUp or Asana. They describe the project’s architecture, rules, layout and commands.

Use them when modifying the Flow codebase, especially when working with its shared data contract, Cloudflare services, database storage, real-time updates or agent interfaces.

They give an agent the project context and constraints needed to make compatible changes. The input does not describe a standalone feature or tool.

How joelborch/flow configures Claude Code

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/CLAUDE.md

Clone the repo

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

Made for: Claude Code.

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

Your own site

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

Per session 860 This file is loaded in full into every session.

When invoked 860 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	$0.00860	$0.00860
Opus 5.5	$0.00344	$0.00344
Sonnet 5.5	$0.00172	$0.00172
Haiku 4.5	$0.00086	$0.00086

Measured 16d ago against content hash b6dc9a81c4b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flow CLAUDE.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 16d 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.

CLAUDE.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow

A fast, minimal, agent-first task manager (self-hosted ClickUp/Asana replacement). Everything runs on Cloudflare: one Worker (apps/api) serving the SPA, REST, MCP at /mcp, and WebSockets at /ws; one Durable Object (packages/core) holding the entire workspace in SQLite; R2 for attachments; Queues for outbound side effects. Full agent contract: AGENTS.md.

Ground rules

packages/shared is the contract. All entity shapes, mutation inputs, delta events, WS protocol, LIMITS, and MCP tool names live there as Zod schemas with inferred types. Import from it; never redeclare its types. If the contract must change, make the smallest compatible change and flag it prominently.
One workspace, one DO instance. The DO is the only writer; REST/MCP handlers call its RPC methods (WorkspaceRpc) and never touch SQL.
Every mutation appends a Delta with a monotonic seq; WS clients receive patches and replay on reconnect. Never build a "refetch the board" path.
Automations evaluate inline in the DO mutation turn (depth cap 5). Outbound side effects (webhook/email) go through the SIDE_EFFECTS queue, never inline. Email respects EMAIL_DRY_RUN (default true): log, don't send.
Subtasks are Asana-style: done/not-done + optional assignee/dueDate. They do NOT have statuses.
API keys (flow_ bearer tokens) impersonate a real user; the audit trail records the key id.
TypeScript strict everywhere. pnpm workspaces. No new runtime deps without a strong reason. Current runtime deps: hono, zod, the MCP SDK and postal-mime (email intake parsing) in the Worker; preact, @preact/signals, chrono-node, and TipTap + tiptap-markdown (lazy-loaded in its own chunk) in the web app.
UI: clean, minimal, Linear-ish. Tailwind v4. Fast: optimistic mutations, CSS transforms for drag, no full-board re-renders.
Email intake (apps/api/src/email-intake.ts, the Worker's email() handler) turns mail to <alias>@EMAIL_INTAKE_DOMAIN into tasks. Authorize only on the envelope sender against the list's allowlist, never the From header, and keep dedupe plus threading inside the single ingestEmail DO turn. Never log message bodies.
Never commit secrets or real config values; placeholders only (flow.example.com, [email protected]). Local values go in apps/api/.dev.vars.

Read the full file on GitHub · 62 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.

16d ago Changed · +7 lines · +124 tokens per session b6dc9a81c4b5
2mo ago First seen · 55 lines · 736 tokens per session scan A d294ee33abb1

Subscribe to this mod's changes

flow CLAUDE.md is an instructions file published in the GitHub repository joelborch/flow (0 stars, last pushed 2d ago), licensed MIT. It adds 860 tokens to every session, about $0.0034 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 CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
flow CLAUDE.mdjoelborch/flow	Instructions file	0	2d ago	MIT	A	860	Claude Code
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 Claude Code