Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/instructions/josheche/tokengolf/claude-md)<a href="https://agentmods.dev/instructions/josheche/tokengolf/claude-md"><img src="https://agentmods.dev/badge/instructions/josheche/tokengolf/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 5.1 | $0.02223 | $0.02223 |
| Opus 5 | $0.01111 | $0.01111 |
| Sonnet 5 | $0.00445 | $0.00445 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade B, and why
tokengolf CLAUDE.md scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `tokengolf install` | Patch `~/.claude/settings.json` with hooks | How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TokenGolf — CLAUDE.md
A CLI game that gamifies Claude Code sessions by turning token/dollar efficiency into a score. Node.js, ESM, Ink v5 TUI, Commander.js, JSON persistence in ~/.tokengolf/.
One Mode — Every Session Is a Roguelike Run
Every Claude Code session is automatically tracked. No wizard, no upfront budget commitment. The budget (par) scales dynamically with session activity.
Par budget = max(rate × sqrt(prompts), model_floor). Par grows sublinearly — early prompts have headroom, pressure mounts over time. Efficient prompts beat par; wasteful prompts fall behind. BUST (>100% of par) = status: 'died', red accent, death achievements.
Installation
Plugin (recommended) — auto-updates:
claude plugin marketplace add josheche/tokengolf
claude plugin install tokengolf@tokengolf
npm (alternative) — requires manual hook setup:
npm install -g tokengolf && tokengolf install
npm users get auto-sync: hooks update automatically on version change via session-start.js.
Commands
npm run build after source changes. npm test after score.js changes. npm run lint / npm run format for code quality. Husky pre-commit hook runs automatically.
Do not test with node src/cli.js — use node dist/cli.js or tokengolf after npm link.
| Command | Description |
|---|---|
tokengolf scorecard |
Show last run's score card |
tokengolf stats |
Career stats dashboard |
tokengolf demo [component] |
Show UI demos (all, hud, scorecard, stats) |
tokengolf config |
List all config values |
tokengolf config emotions [mode] |
Get/set emotion mode (off, emoji, ascii) |
tokengolf config par [model] [rate] |
View/set par rates per model, or reset |
tokengolf config floor [model] [value] |
View/set par floors per model, or reset |
tokengolf install |
Patch ~/.claude/settings.json with hooks |
Par Budget System
Par = the expected cost for a session, scaled sublinearly by prompts and model.
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.
- 5d ago First seen · 156 lines · 2,223 tokens per session scan B 7a8dafbc82fd
tokengolf CLAUDE.md is an instructions file published in the GitHub repository josheche/tokengolf (2 stars, last pushed 5mo ago), licensed MIT. It adds 2,223 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.
ai-auto-work CLAUDE.md
Claude Code instructions for chaohong-ai/ai-auto-work, covering gamemaker - ai native 游戏创作平台, 项目简介, ai 工作目录约定 and 按需加载（不默认装载）.