agentmods.dev

flow AGENTS.md

Repository instructions for Flow, a toolkit for organizing software work through project context, written plans, and task worksheets. They explain where task state lives and how agents should invoke Flow.

In plain words
What is it for?
Use them to initialize Flow, find the relevant project knowledge and worksheet, execute one planned task at a time, verify the result, and commit approved local changes.
Why use it?
They prevent agents from treating Flow as a command-line program or making changes outside the project’s documented workflow.

Instructions file for CodexOpenCode

16 2d ago A scan 202 tokens original Apache-2.0
View the source file cofin/flow
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cofin/flow/agents-md
Clone the repo
git clone --depth 1 https://github.com/cofin/flow

Made for: Codex, OpenCode.

Per session 202 This file is loaded in full into every session.
When invoked 202 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00202 $0.00202
Opus 5 $0.00101 $0.00101
Sonnet 5 $0.00040 $0.00040
Haiku 4.5 $0.00020 $0.00020

Measured yesterday against content hash 228094a11f96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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 · 19 lines

What it actually says

Flow Project Context

Flow is a toolkit for context-driven development. It has no flow executable; invoke the Flow skill or a /flow:* command.

Planning and task state live under .agents/bundles/specs/<flow_id>/. Task worksheets are the authority for task state and commits. Route lifecycle work through the Flow router, and use the state contract for mutations.

Initialize with the setup guide, then use its bundle index, .agents/bundles/knowledge/workflow.md, and recursively relevant .agents/bundles/knowledge/patterns/**/*.md chapters.

Execute one worksheet per invocation, preserve unrelated work, stage exact paths, and commit locally only after the declared verification passes. Never create or mutate tags. Pushes and hosted repository writes require fresh, target-specific user permission.

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.

  1. yesterday First seen · 19 lines · 202 tokens per session scan A 228094a11f96

Subscribe to this mod's changes

flow AGENTS.md is an instructions file published in the GitHub repository cofin/flow (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 202 tokens to every session, about $0.0010 per session on Opus 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.

Git and workflowPlanningagent-skillsai-agentsbeadsclaude-codecodexcontext-driven-development
Related

Other instructions, from other repositories

scaffold AGENTS.md

Instructions for zigrivers/scaffold, covering agent instructions, quick reference, scaffold releases and landing the plane (session completion).

zigrivers/scaffold · 626 tokens

foolery CLAUDE.md

Instructions for acartine/foolery, covering agent instructions, codex configuration, repository overrides, git worktree policy (hard override) and worktree dependency bootstrap.

acartine/foolery · 2,131 tokens

foolery AGENTS.md

Instructions for acartine/foolery, covering agent instructions, codex configuration, repository overrides, git worktree policy (hard override) and worktree dependency bootstrap.

acartine/foolery · 1,289 tokens

looper_rust AGENTS.md

Instructions for quangdang46/looper_rust, covering looper rust — ai agent guidelines, build, test, lint and workspace members.

quangdang46/looper_rust · 539 tokens

bd-explore GEMINI.md

Gemini CLI instructions for halaprix/bd-explore, covering gemini.md - gemini / antigravity guide for bd-explore, context & guidelines, running verification tests and structure.

halaprix/bd-explore · 345 tokens

scaffold CLAUDE.md

Instructions for zigrivers/scaffold, covering claude.md, core principles, project overview, structure and source of truth.

zigrivers/scaffold · 9,300 tokens