Borrowing it
Nothing to install: this file belongs to SarutobiSasuke8/ape-adventure. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SarutobiSasuke8/ape-adventure/master/CLAUDE.mdgit clone --depth 1 https://github.com/SarutobiSasuke8/ape-adventureWrote 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/sarutobisasuke8/ape-adventure/claude-md)<a href="https://agentmods.dev/instructions/sarutobisasuke8/ape-adventure/claude-md"><img src="https://agentmods.dev/badge/instructions/sarutobisasuke8/ape-adventure/claude-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.
<a href="https://agentmods.dev/instructions/sarutobisasuke8/ape-adventure/claude-md"><img src="https://agentmods.dev/badge/instructions/sarutobisasuke8/ape-adventure/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01976 | $0.01976 |
| Opus 5 | $0.00988 | $0.00988 |
| Sonnet 5 | $0.00395 | $0.00395 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
ape-adventure 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 10d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Ape Adventure Working Agreement
Working agreement for Claude Code (and other AI collaborators) on Ape Adventure — a 90s-era jungle-platformer homage built in Python with pygame.
This file replaces the previous arcade-game agreement (preserved alongside legacy_game.py, the legacy v0). The new direction is a side-scrolling adventure inspired by 1990s console platformers — multi-level worlds, lush biomes, collectibles, vehicles (later), boss fights.
What this project is now
A 90s-style side-scrolling platformer with rich animation, real music, and a multi-world structure. Built in Python with pygame, structured as a proper package (no longer single-file).
Direction: Donkey Kong Country–inspired — but original characters, original IP, original art. Inspired by the genre, not a clone.
Tone: adventurous, warm, vivid. Emotional opposite of the legacy arcade game (which was dry and tense).
Scope (current commitment): vertical slice — 1 world ("Tangle Jungle"), 3–4 levels, 1 boss, 1 playable character. Architecture left open for a full DKC-style homage later (6 worlds, 30+ levels, tag-team characters, vehicles).
What's in the repo
Ape Adventure/
├── ape_escape/ # NEW — the new game (multi-file package)
├── docs/ # rewritten for the new direction
├── marketing/ # rewritten for the new brand
├── ape_escape.py # ← launcher (run this to play)
├── legacy_game.py # LEGACY v0 — keep playable, do not break
├── ape_escape_highscore.json # legacy save — do not delete
├── smoke_test.py # legacy smoke test for v0
├── README.md
└── CLAUDE.md # (this file)
Legacy game (legacy_game.py)
The single-file climbing-platformer is parked, not deleted. It still runs. Treat it as a finished v0 reference — do not modify, refactor, or delete it without explicit permission. New work happens under ape_escape/.
Core principles (new)
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.
- 10d ago First seen · 165 lines · 1,976 tokens per session scan A 6be93d10f2e5
ape-adventure CLAUDE.md is an instructions file published in the GitHub repository SarutobiSasuke8/ape-adventure (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,976 tokens to every session, about $0.0099 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.