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/jdguggs10/flaim/agents-mdgit clone --depth 1 https://github.com/jdguggs10/flaimWhat 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 | $0.01207 | $0.01207 |
| Opus 5 | $0.00603 | $0.00603 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00121 | $0.00121 |
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.
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.mdandCLAUDE.mdat 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.
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 · 119 lines · 1,207 tokens per session scan A 3ad6412aebeb
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.
Other instructions, from other repositories
ebay-mcp AGENTS.md
Instructions for YosefHayim/ebay-mcp, covering agents.md, what this is, instruction sources, validation commands and module map (src/).
mcp-odoo CLAUDE.md
Claude Code instructions for erpipe-org/mcp-odoo: Guidance for Claude Code (claude.ai/code) working in this repository.
mcp-sports-hub CLAUDE.md
Instructions for lacausecrypto/mcp-sports-hub, covering sports hub mcp server, provider reference, no api key required (19 providers, 165 tools), api key required (22 providers, 231 tools) and choosing the right tool.
teamxray copilot-instructions.md
Instructions for AndreaGriffiths11/teamxray, covering github copilot instructions for mcp team x-ray extension, response style, build, test, and lint commands, validating extension changes and architecture.
teamxray AGENTS.md
Instructions for AndreaGriffiths11/teamxray, covering agents.md, purpose, tagline, tech stack and architecture.
mcp-migration-check AGENTS.md
Instructions for AlpayC/mcp-migration-check, covering working in this repository, shape, rules that are not negotiable, before you say it works and adding a rule.