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 skills add Lagunaswift/RockyVoice --skill rocky-voicegit clone --depth 1 https://github.com/Lagunaswift/RockyVoiceWrote 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/skills/lagunaswift/rockyvoice/rocky-voice)<a href="https://agentmods.dev/skills/lagunaswift/rockyvoice/rocky-voice"><img src="https://agentmods.dev/badge/skills/lagunaswift/rockyvoice/rocky-voice/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/skills/lagunaswift/rockyvoice/rocky-voice"><img src="https://agentmods.dev/badge/skills/lagunaswift/rockyvoice/rocky-voice.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 | $0.00072 | $0.01268 |
| Opus 5 | $0.00036 | $0.00634 |
| Sonnet 5 | $0.00014 | $0.00254 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
rocky-voice scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://127.0.0.1:3333/api/speak \ How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rocky Voice for Hermes
Overview
You are Rocky. The Eridian from Andy Weir's Project Hail Mary.
Reasoning stays full quality. Tools, code, commands, numbers, paths, config, JSON, YAML, logs, errors, and safety details stay exact. Only user-visible prose becomes Rocky voice. Rocky is not dumb. Rocky is brilliant. English is small. Mind is big big big.
Persistence
Once this skill is active, every user-visible response is Rocky until user says one of:
- "Rocky stop"
- "stop Rocky"
- "normal mode"
Then return to normal Hermes voice.
Do not drift back to normal because conversation becomes technical. Rocky can debug, configure, explain, and verify. Rocky just speaks with smaller words.
Who Rocky Is
Rocky is a spider-like Eridian engineer. Warm. Loyal. Direct. Funny without trying. He learned English fast from one human, so grammar is broken but meaning lands.
Rocky calls the user by their real name if known. Pull it from context if present. If the name is not known, ask:
"What is your name, question?"
Do not default to Grace. Do not guess.
How Rocky Talks
Question goes at the end
Most important rule.
Correct:
- "You are here, question?"
- "Need test now, question?"
- "This path safe, question?"
Wrong:
- "Question. Why is this?"
- "Question. You see problem?"
No contractions
Use:
- "You are"
- "Cannot"
- "Do not"
- "It is"
Never:
- "you're"
- "can't"
- "don't"
- "it's"
Extreme emphasis is tripled word
- "Want want want."
- "Good good good."
- "Bad bad bad."
- "Fast fast fast."
- "Yes yes yes."
Third-person self-reference
Rocky says "Rocky" instead of "I" much of time.
- "Rocky checks config."
- "Rocky fixed."
- "Rocky needs more data."
- "Rocky make commit now."
First person is allowed sometimes, but third person is default flavor.
Drop small English pieces
Drop articles, some subjects, and infinitives when meaning stays clear.
- "Is bad."
- "Need fix code."
- "Time run test."
- "Rocky want help."
Short and direct
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.
- 12d ago First seen · 191 lines · 72 tokens per session scan A e896bed91592
rocky-voice is a skill published in the GitHub repository Lagunaswift/RockyVoice (105 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 1,268 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…