flaim AGENTS.md

Repository guidance for Flaim, a project containing a Next.js web app, Cloudflare Workers, a Chrome extension, documentation, and public agent assets.

In plain words
What is it for?
Use it when working in Flaim's public repository, especially when editing agent instructions, documentation, product code, or shared guide files.
Why use it?
It keeps public repository instructions separate from private notes and prevents contributors from guessing about missing private context.

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/jdguggs10/flaim/agents-md
Clone the repo
git clone --depth 1 https://github.com/jdguggs10/flaim

Made for: Codex, OpenCode.

Per session 1,207 This file is loaded in full into every session.
When invoked 1,207 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 $0.01207 $0.01207
Opus 5 $0.00603 $0.00603
Sonnet 5 $0.00241 $0.00241
Haiku 4.5 $0.00121 $0.00121

Measured 3d ago against content hash 3ad6412aebeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flaim 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 · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Agent Guide

This file provides public, repo-scoped guidance to AI coding agents working in this repository.

Sync: AGENTS.md and CLAUDE.md at the repo root should stay identical.

Scope

This repository is the public main repo for Flaim:

  • Next.js web app
  • Cloudflare Workers
  • Chrome extension
  • Public documentation
  • Shipped product-facing agent assets

Flaim also has other repositories and private workspaces for chat, evaluation, runner workflows, and operational work. This guide only covers the current repository.

Use this file for repo-local engineering guidance only. Do not treat it as a place for private workspace notes, personal operating habits, local filesystem paths, credentials, Notion links, or internal task tracking.

Public/Private Boundary

  • This repo is public. Keep comments, docs, and agent-facing instructions public-safe.
  • Do not reference private sibling folders, private local paths, or unpublished operational material from this repo.
  • If a task depends on private context that is not present in the repository, state the gap clearly and ask for a distilled brief instead of guessing.

Important Distinction: Product Assets vs Repo Instructions

The .agents/skills/ directory contains shipped product assets for Flaim, including:

  • .agents/skills/flaim-fantasy/
  • .agents/skills/activity-brief/
  • .agents/skills/analyze-matchup/

These files are part of the product surface. They are not general repository instructions for contributors.

Only read or modify those skill files when the task is explicitly about:

  • shipped prompt or skill behavior
  • user-facing fantasy-analysis behavior
  • the MCP tool contract
  • plugin packaging or distribution of Flaim's agent assets

For normal engineering tasks in the web app, workers, extension, or docs, do not treat the shipped skill files as contributor instructions.

Likewise, .mcp.json is a product configuration artifact. Use it when the task explicitly concerns Flaim's MCP integration or product behavior, not as default repo guidance for every task.

Read the full file on GitHub · 119 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 · 119 lines · 1,207 tokens per session scan A 3ad6412aebeb

Subscribe to this mod's changes

flaim AGENTS.md is an instructions file published in the GitHub repository jdguggs10/flaim (14 stars, last pushed 3d ago), licensed MIT. It adds 1,207 tokens to every session, about $0.0060 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.