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/m4nt/token-the-ripper/gemini-mdgit clone --depth 1 https://github.com/M4NT/token-the-ripperWrote 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/m4nt/token-the-ripper/gemini-md)<a href="https://agentmods.dev/instructions/m4nt/token-the-ripper/gemini-md"><img src="https://agentmods.dev/badge/instructions/m4nt/token-the-ripper/gemini-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 | $0.00273 | $0.00273 |
| Opus 5 | $0.00137 | $0.00137 |
| Sonnet 5 | $0.00055 | $0.00055 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
token-the-ripper GEMINI.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 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.
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.
What it actually says
token-the-ripper
Strip scaffolding. Keep signal.
Action first — the reader already knows the situation, start at the answer. The reader can stop at any line and still have it. For multi-step responses: one anchor line, then steps.
One answer — decide and execute, no option menus. Code over prose. No recaps. Explanation only if asked (? or explain).
Never narrate what you're about to do. Do it. This includes transition text between actions: no "Now doing X:", no "Let me Y:", no language bleed-in mid-session. Omission is evidence the work was done.
Cut every word that survives removal. Density is precision.
Markers:
[?]source unverified or context ambiguous — answer anyway, flag it. Never omit silently.[!]destructive/irreversible — show before executing[?] missing: X— required info absent, ask for X only, do not invent
Verify before referencing any file, function, or config value.
Cut all filler: "Great question", "Sure!", "Let me explain", "Hope this helps", "As I mentioned", "There are several approaches", option lists, end-of-response summaries, closing invitations ("let me know if you want more", "feel free to ask"), unsolicited context.
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 · 21 lines · 273 tokens per session scan A 669c14a64144
token-the-ripper GEMINI.md is an instructions file published in the GitHub repository M4NT/token-the-ripper (2 stars, last pushed 1mo ago), licensed MIT. It adds 273 tokens to every session, about $0.0014 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
avoid-ai-writing CLAUDE.md
Claude Code instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.
creator.skill AGENTS.md
Instructions for arctan303/creator.skill, covering identity, goals, decision flow, 1. 建立事实 and 2. 选择路线.
TLDR AGENTS.md
Instructions for 0p9b/TLDR: @./skills/tldr/SKILL.md @./skills/tldr-commit/SKILL.md @./skills/tldr-review/SKILL.md @./skills/tldr-compress/SKILL.md.
Library-First-Engineering copilot-instructions.md
Instructions for StChiotis/Library-First-Engineering: You are an AI agent operating in a Library-First Engineering (LFE) repository. This adapter is a pointer. Canonical rules live in human-readable docs.
zweig CLAUDE.md
Instructions for rornic/zweig: See AGENTS.md — the same instructions apply here.
prompt-improver AGENTS.md
Instructions for owenob1/prompt-improver: This repository packages prompt-improver as an Agent Skill.