flue AGENTS.md

Project instructions for Flue, a TypeScript framework for building AI agents that can keep conversations and recover work across restarts. They explain its terminology, project structure, and contribution rules.

In plain words
What is it for?
Use them when developing Flue applications, agent routes, persistence adapters, provider integrations, channels, SDK clients, or contributor documentation.
Why use it?
They help agents understand how Flue agents, tools, storage, channels, clients, and deployment fit together before making changes.

Instructions file for CodexOpenCode

▶ Flue vs Claude Code vs Mastra — Which Agent Framework Wins? DIY Smart Code · about withastro/flue · on YouTube →
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/withastro/flue/agents-md
Clone the repo
git clone --depth 1 https://github.com/withastro/flue

Made for: Codex, OpenCode.

Per session 912 This file is loaded in full into every session.
When invoked 912 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 $0.00912 $0.00912
Opus 5 $0.00456 $0.00456
Sonnet 5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 3d ago against content hash 21fc2e0a441f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flue 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 3d 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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flue

Flue is a TypeScript framework for building autonomous AI agents and running them anywhere. An agent is a plain exported function: hooks in its body compose its capabilities — model (useModel), tools, skills, sandboxes, state — and its return value is its instruction. Agents live in durable conversations: accepted input survives crashes, restarts, and redeploys, and interrupted work recovers to a deterministic state. Applications build with Vite (the flue() plugin plus an explicit app.ts route map) and deploy to Node.js or Cloudflare Workers from the same source, with persistence adapters (SQLite, Postgres, MySQL, MongoDB, Redis, and more), channels that turn provider webhooks (Slack, GitHub, Telegram, ...) into agent conversations, and clients — the Flue Agent SDK (@flue/sdk), @flue/react, and the flue CLI — for driving conversations over HTTP or from code. The model layer is Pi's provider protocol, used directly.

Contributing

See CONTRIBUTING.md for the full picture. In short:

Terminology

Agent                         — a capitalized, exported plain function; Flue Hooks in its body attach
                                tools, instructions, and state, and its returned string is its
                                instruction; the function name (or its `agentName` string-literal
                                static) is the agent's durable identity
Agent module                  — a source file whose first statement is the `'use agent'` directive;
                                every capitalized exported function in it is an agent
└─ AgentInstance              — URL `<id>`; the agent's durable identity, independent of authoring
   └─ Harness                 — runtime-initialized agent environment; defaults to name `"default"`
      └─ Session              — one `harness.session(name?)`; defaults to `"default"`
         └─ Operation        — one `session.prompt` / `skill` / `task` / `shell` call
            └─ Turn          — one LLM round-trip inside pi-agent-core

Read the full file on GitHub · 54 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.

  1. 3d ago First seen · 54 lines · 912 tokens per session scan A 21fc2e0a441f

Subscribe to this mod's changes

flue AGENTS.md is an instructions file published in the GitHub repository withastro/flue (8,114 stars, last pushed 6d ago), licensed Apache-2.0. It adds 912 tokens to every session, about $0.0046 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.