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/zamarrowski/claudemon/claude-mdgit clone --depth 1 https://github.com/zamarrowski/claudemonWrote 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.
[](https://agentmods.dev/instructions/zamarrowski/claudemon/claude-md)<a href="https://agentmods.dev/instructions/zamarrowski/claudemon/claude-md"><img src="https://agentmods.dev/badge/instructions/zamarrowski/claudemon/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.07681 | $0.07681 |
| Opus 5 | $0.03841 | $0.03841 |
| Sonnet 5 | $0.01536 | $0.01536 |
| Haiku 4.5 | $0.00768 | $0.00768 |
Grade A, and why
claudemon CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 800 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Guidelines
This document provides instructions for AI agents working on the claudemon codebase.
claudemon is a terminal Pokémon game driven by Claude Code activity: plain ESM Node, no build step, no runtime dependencies, rendered as ANSI lines into a terminal.
These rules are the house style. Where existing code contradicts them, the existing code is wrong and gets brought in line as it is touched — do NOT copy a violation because the file next to you has one, and do NOT cite existing code as precedent against a rule here.
Project shape
bin/claudemon entry point, argument parsing, boot
src/ the engine (battle, capture, exp, state, queue, sound, update)
src/ui/ rendering primitives (screen, ansi, sprite, grass, widgets)
src/ui/views/ one file per screen, each exporting draw() and onKey()
scripts/ Claude Code hook handlers and the status line
tools/ dev-time scripts (fetch data, fetch sprites, preview, capture, install)
test/ test suites
data/ generated dataset, checked in — never hand-edited
Everything is ESM, .mjs, Node >= 20.19. The runner is Vitest. Prettier owns
formatting (no semicolons, single quotes, 80 columns) — write the code and run
npm run format, never hand-align anything.
General Guidelines
General Rules
NO COMMENTS: NEVER add comments to the code. Code should be self-documenting and
clear without them. If a block needs explaining, extract it into a named function
instead. The only comments allowed anywhere are tooling directives
(// prettier-ignore, // eslint-disable-next-line).
NAMING CONVENTIONS: Always use camelCase for naming variables, functions and files. Module-level constants use SCREAMING_SNAKE_CASE.
ARROW FUNCTIONS: Declare functions as arrows assigned to a const, and export the
const. NEVER use function declarations.
// ✅ GOOD
export const partyIsWipedOut = (save) => {
return save.party.length > 0 && save.party.every(isFainted)
}
// ❌ BAD
export function partyIsWipedOut(save) {
return save.party.length > 0 && save.party.every(isFainted)
}
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.
- 4d ago First seen · 800 lines · 7,681 tokens per session scan A 8fb696fc0f8a
claudemon CLAUDE.md is an instructions file published in the GitHub repository zamarrowski/claudemon (59 stars, last pushed 7d ago), licensed MIT. It adds 7,681 tokens to every session, about $0.0384 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
quick-question AGENTS.md
Instructions for tykisgod/quick-question, covering agents.md, refactoring authority, default engineering bias, trust levels and execution environment split.
claude-pokemon-pet CLAUDE.md
Instructions for junoh-bg/claude-pokemon-pet, covering claude.md — claude-pokemon-pet, architecture (v0.4.0+), hard rules, testing and code review.
game-design-lenses AGENTS.md
Instructions for EthanM2025/game-design-lenses, covering how to install (codex / generic), integration block (copy this into your project's agents.md), game design lens review (game-design-lenses) and notes.
godot-superpowers CLAUDE.md
Instructions for Simone-Tarantino/godot-superpowers, covering claude.md, what this repo is, layout, editing rules for this repo and developing this plugin.
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).
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.