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.
npx agentmods add instructions/withastro/flue/agents-mdgit clone --depth 1 https://github.com/withastro/flueWhat 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 | $0.00912 | $0.00912 |
| Opus 5 | $0.00456 | $0.00456 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
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.
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:
- Bug reports → https://github.com/withastro/flue/issues
- Feature requests → https://github.com/withastro/flue/discussions
- Pull requests are not accepted; they are automatically closed and converted into one of the two contribution types above.
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
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.
- 3d ago First seen · 54 lines · 912 tokens per session scan A 21fc2e0a441f
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.
Other instructions, from other repositories
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
open-supermarkets AGENTS.md
Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.
helm copilot-instructions.md
Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
fusion-skills AGENTS.md
AGENTS.md instructions for CrowdStrike/fusion-skills, covering agents.md, what this is, prerequisites, repository structure and skills ecosystem.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).