FLUJO: Instructions file for Codex

AGENTS.md

FLUJO AGENTS.md is an instructions file for Codex, OpenCode from mario-andreschak/FLUJO. It costs 408 tokens per session, scanned A, a copy of civitai AGENTS.md, MIT.

A repository instruction file for a specific FLUJO project that tells coding agents where to find the project's Next.js documentation and how to handle generated changes.

In plain words
What is it for?
It guides code changes in this repository, especially when checking its installed Next.js version and keeping generated agent instructions consistent.
Why use it?
It prevents an agent from relying on outdated Next.js knowledge or removing files that the project recreates automatically.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is mario-andreschak/FLUJO's own configuration. It tells Codex and OpenCode how to work on FLUJO itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything FLUJO configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mario-andreschak/FLUJO. 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/mario-andreschak/FLUJO/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mario-andreschak/FLUJO

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.

agentmods badge for FLUJO AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mario-andreschak/flujo/agents-md/github.svg)](https://agentmods.dev/instructions/mario-andreschak/flujo/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mario-andreschak/flujo/agents-md"><img src="https://agentmods.dev/badge/instructions/mario-andreschak/flujo/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.

agentmods 80×15 button for FLUJO AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mario-andreschak/flujo/agents-md"><img src="https://agentmods.dev/badge/instructions/mario-andreschak/flujo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 408 This file is loaded in full into every session.
When invoked 408 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 100% copy Near-identical to another mod 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 5.1 $0.00408 $0.00408
Opus 5.5 $0.00163 $0.00163
Sonnet 5.5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured 6d ago against content hash ee2c966713ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

FLUJO 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 6d 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.

Origin

This is a copy

100% identical to civitai AGENTS.md — 26 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 36 lines

What it actually says

Repository hygiene

Keep generated run records, provider traces, screenshots used only as proof, agent handovers and media production projects outside this repository. Commit media only when a published page or maintained product guide uses it. Reuse existing screenshots rather than committing identical copies.

Perform cleanup and file deletions through the flujo-bash MCP. Keep the primary development checkout on main; remove temporary branches after delivery.

Resilience over refusal

FLUJO is a long-running desktop app. Prefer degrading gracefully to failing closed:

  • Under pressure (busy slots, memory, locks), make callers wait with a bounded timeout instead of refusing at once. Retry transient I/O errors.
  • A failure must never block a conversation, workspace or slot until restart. Every fence, quarantine or counter must be released or healed automatically (on the next success, when its owner settles, or when its process is gone).
  • Do not add a fixed limit without saying how it recovers without a restart and without the user knowing an environment variable. Scale memory limits with the machine.
  • Keep work off the event loop, and fix the throughput cause (batching, fewer syscalls) rather than adding another admission gate.

This is NOT the Next.js you know

This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo root) before writing any code. Heed deprecation notices.

This block is written and re-added by next dev — verify at node_modules/next/dist/server/lib/generate-agent-files.js. Removing it from a diff only re-creates the uncommitted change; committing it with your work keeps the tree clean.

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. 6d ago Changed · +16 lines · +170 tokens per session ee2c966713ba
  2. 14d ago Changed · +10 lines · +84 tokens per session 853eb160f2aa
  3. 24d ago Changed 063098f6cb31
  4. 1mo ago First seen · 10 lines · 154 tokens per session scan A 63f2c50380ed

Subscribe to this mod's changes

FLUJO AGENTS.md is an instructions file published in the GitHub repository mario-andreschak/FLUJO (673 stars, last pushed yesterday), licensed MIT. It adds 408 tokens to every session, about $0.0016 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to civitai AGENTS.md, differing in 26 lines, and is treated as a copy.

Related

FLUJO AGENTS.md compared with instructions from other repositories

FLUJO AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
FLUJO AGENTS.mdmario-andreschak/FLUJOInstructions file673yesterdayMITA408Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode