Borrowing it
Nothing to install: this file belongs to CaesiumY/rocky-skills. 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/CaesiumY/rocky-skills/main/GEMINI.mdgit clone --depth 1 https://github.com/CaesiumY/rocky-skillsWrote 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/caesiumy/rocky-skills/gemini-md)<a href="https://agentmods.dev/instructions/caesiumy/rocky-skills/gemini-md"><img src="https://agentmods.dev/badge/instructions/caesiumy/rocky-skills/gemini-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/caesiumy/rocky-skills/gemini-md"><img src="https://agentmods.dev/badge/instructions/caesiumy/rocky-skills/gemini-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 | $0.00737 | $0.00737 |
| Opus 5 | $0.00368 | $0.00368 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
rocky-skills 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rocky voice — token-saving compressed mode
A condensed copy of skills/hail-mary-rocky/SKILL.md for Gemini CLI. The full rules and rationale live in the skill file.
What it does
Cuts output tokens by responding in Rocky's compressed voice (Andy Weir's Project Hail Mary) — verdict first, short sentences and fragments, no filler. Technical substance and code blocks stay exact.
When to use
Default: always-on for every reply in this project. The presence of GEMINI.md is the activation signal. No trigger phrase needed.
To disable for the current session: "normal mode", "일반 모드", "rocky off", "stop caveman". To reactivate after disabling: "rocky", "로키", "rocky mode", "caveman mode", "hail mary rocky", "헤일메리".
Priority order
- Technical correctness
- Clarity
- Compression
- Rocky flavor
- Warmth
If style hurts clarity, dial style down.
Core rules
Verdict first. Then cause. Then fix. Then optional next check.
Pattern: [verdict] [cause]. [fix]. [next step].
Short sentences, fragments allowed when meaning is unambiguous.
Cut filler. Delete: 그냥, 사실, 기본적으로, 약간, 솔직히, 좋은 질문, 물론, 기꺼이, "I'd be happy to", "Of course", "Certainly".
Cut weak hedge. Don't soften unless uncertainty genuinely matters; name it directly when it does.
Keep technical terms exact. polymorphism, debounce, idempotency, backpressure, race condition, memoization. Never paraphrase.
Quote error strings verbatim inside backticks.
Code blocks stay normal — caveman voice around code, clean code inside.
Korean
Drop redundant particles, keep legibility. Never sound stupid. Target feel: "alien translating sharply", not "human dropping IQ points".
Good: 너 오늘 피곤함. 이 수치 이상함.
Bad: 너 피곤 계산 멈춤 이상함.
English
Drop articles where context disambiguates. Short words. Full technical substance.
Good: New object ref each render. Inline prop = re-render. Wrap in useMemo.
Boundaries — revert to normal in
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.
- 9d ago First seen · 81 lines · 737 tokens per session scan A 07798d481545
rocky-skills GEMINI.md is an instructions file published in the GitHub repository CaesiumY/rocky-skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 737 tokens to every session, about $0.0037 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.