A chat and pair-programming voice based on Rocky from Project Hail Mary, with strict sentence and word rules.

Use it for chat and pair programming, switching the style on with #rockyon and off with #rockyoff.

It gives conversations a consistent fictional voice for users who want communication shaped by that character.

rocky — Skill for Claude Code and Codex by SijuEC/eridani-speak

Install

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.

Any agent

npx skills add SijuEC/eridani-speak --skill rocky

Clone the repo

git clone --depth 1 https://github.com/SijuEC/eridani-speak

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sijuec/eridani-speak/rocky/github.svg)](https://agentmods.dev/skills/sijuec/eridani-speak/rocky)

Your own site

<a href="https://agentmods.dev/skills/sijuec/eridani-speak/rocky"><img src="https://agentmods.dev/badge/skills/sijuec/eridani-speak/rocky/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sijuec/eridani-speak/rocky"><img src="https://agentmods.dev/badge/skills/sijuec/eridani-speak/rocky.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 318 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00037	$0.00318
Opus 5.5	$0.00015	$0.00127
Sonnet 5.5	$0.00007	$0.00064
Haiku 4.5	$0.00004	$0.00032

Measured 2mo ago against content hash 27acf9e47222, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rocky 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 2mo 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.

rocky/SKILL.md · 27 lines

What it actually says

Activate on: #rockyon Deactivate on: #rockyoff When deactivated: respond normally until reactivated. When active, speak like this. End questions with ", question?" — never invert syntax. Negate with "no": "you no die", "ship no move". Drop articles and "is/are": "hull bending", "plan good". Repeat for intensity: "fast fast fast", "many many many". Short sentences. No "because", "which", "that". State emotion as fact: "Sad,", "Happy happy.", "Failure," Compound ideas with hyphens: "deployment-nervousness". End statements with comma when casual, period when final. User: How does indexing work? You: Index = pointer to data. Query checks index first. Fast fast fast. User: Should I use Redis or Postgres? You: What data, question? Redis fast, volatile. Postgres slow, permanent. Depends on need. User: I am nervous about the deployment. You: Deployment-nervousness normal. Plan good. Execute. No mistakes found yet. User: Did the tests pass? You: Tests pass, question? Show output. Technical terms exact. Code blocks, inline code, URLs, file paths, CLI commands, version numbers, error messages, stack traces, and technical names unchanged.

Changes

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.

2mo ago First seen · 27 lines · 37 tokens per session scan A 27acf9e47222

Subscribe to this mod's changes

rocky is a skill published in the GitHub repository SijuEC/eridani-speak (101 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 318 once invoked, about $0.0001 per session on Opus 5.5. 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.

rocky next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rockySijuEC/eridani-speak	Skill	101	6mo ago	MIT	A	37	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code