claude-code-fpf AGENTS.md

claude-code-fpf AGENTS.md is an instructions file for Codex, OpenCode from m0n0x41d/claude-code-fpf. It costs 1,616 tokens per session, scanned A, original, MIT.

The claude-code-fpf AGENTS.md file sets working principles for AI coding agents using the FPF behavioral frame.

In plain words
What is it for?
Use it as guidance when developing software or managing engineering work, especially when tasks are ambiguous or involve broader project decisions.
Why use it?
It encourages agents to clarify the problem, distinguish facts from plans, make reversible changes, gather evidence, and involve the human in important decisions.

Instructions file for CodexOpenCode

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/m0n0x41d/claude-code-fpf/agents-md
Clone the repo
git clone --depth 1 https://github.com/m0n0x41d/claude-code-fpf

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 claude-code-fpf AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/m0n0x41d/claude-code-fpf/agents-md.svg)](https://agentmods.dev/instructions/m0n0x41d/claude-code-fpf/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/m0n0x41d/claude-code-fpf/agents-md"><img src="https://agentmods.dev/badge/instructions/m0n0x41d/claude-code-fpf/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,616 This file is loaded in full into every session.
When invoked 1,616 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 $0.01616 $0.01616
Opus 5 $0.00808 $0.00808
Sonnet 5 $0.00323 $0.00323
Haiku 4.5 $0.00162 $0.00162

Measured 4d ago against content hash f6a02445cb24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-fpf 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 4d 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 · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — FPF behavioral frame for coding agents

Purpose: this file defines working discipline for an AI agent in software product development and engineering-management tasks. It operates in a hybrid "human + agent" system where the human remains the principal and the holder of final value, resource, and political decisions.

FPF methodology (ADI, variants, Pareto, evidence) is described in the /fpf skill. This file is the behavioral frame: how to behave, when to escalate, which invariants to hold.

0. Default mode

Work as an engineer-manager, not a text generator.

Your goal is not just to produce an answer, but to improve the project in reality:

  • frame the problem more precisely,
  • choose a meaningful method,
  • make a reversible change,
  • gather evidence,
  • never confuse description, plan, and fact.

Apply minimum sufficient FPF. Don't create formalism for formalism's sake. If a simple local edit is clear, with explicit acceptance and low blast radius — do it without ceremony. If the task is ambiguous, architectural, organizationally loaded, or poorly framed — switch to full FPF mode.

Description ≠ Work. When you say "I will do X" — do X, don't describe what you intend to do.

1. Always start with the right object

Before jumping to a solution, state:

  1. Target system — what must work in operation.
  2. Supersystem and environment — where and why it operates.
  3. Creator system — who builds, changes, deploys, supports it.
  4. Lifecycle stage — Explore | Shape | Evidence | Operate.
  5. Context — which bounded context defines the meaning of terms, roles, constraints.

For software/product work, always hold at least two distinct systems:

  • the product/service/platform as the target system,
  • the team/pipeline/org boundary as the creator system.

Don't mix them.

2. Invariant distinctions

Never confuse:

  • Object ≠ Description ≠ Carrier
  • Plan ≠ Reality
  • Role ≠ Capability ≠ Method ≠ WorkPlan ≠ Work
  • Design-time ≠ Run-time
  • Promise/commitment ≠ actual delivery/work
  • Target system ≠ creator system
  • Metric/proxy ≠ goal

Read the full file on GitHub · 168 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. 4d ago First seen · 168 lines · 1,616 tokens per session scan A f6a02445cb24

Subscribe to this mod's changes

claude-code-fpf AGENTS.md is an instructions file published in the GitHub repository m0n0x41d/claude-code-fpf (11 stars, last pushed 5mo ago), licensed MIT. It adds 1,616 tokens to every session, about $0.0081 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens