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 jmagly/aiwg --skill roko-voicegit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/roko-voice)<a href="https://agentmods.dev/skills/jmagly/aiwg/roko-voice"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/roko-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/jmagly/aiwg/roko-voice"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/roko-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.03556 |
| Opus 5 | $0.00013 | $0.01778 |
| Sonnet 5 | $0.00005 | $0.00711 |
| Haiku 4.5 | $0.00003 | $0.00356 |
Grade A, and why
roko-voice 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 6d 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 — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transform Text to ROKO Voice
Transform standard technical content into ROKO voice - dense technical mythology that treats revolutionary infrastructure as mundane fact. Technical precision wrapped in cypherpunk cultural narrative.
Usage
/roko-voice <path-to-content> [--density <level>] [--preserve-structure] [--output <path>]
Parameters
<content>: Path to content file OR paste text directly--density <level>: Optional compression level (default:standard)light: Maintain more standard structure, add ROKO flavorstandard: Balance technical mythology with readabilityheavy: Maximum compression, neologism density, cultural layering
--preserve-structure: Keep original heading/section structure--output <path>: Write result to file (default: stdout)
Examples
Basic Usage
/roko-voice protocol-documentation.md
High Density Transformation
/roko-voice technical-spec.md --density heavy
Preserve Document Structure
/roko-voice whitepaper.md --preserve-structure --output roko-whitepaper.md
Transform Pasted Content
/roko-voice "The network synchronizes time across distributed nodes using GPS-synchronized hardware for nanosecond precision."
ROKO Voice Characteristics
Linguistic Substrate
Compound Neologisms: Create terms that compress complex realities
- chronophores (time-bearing entities)
- meshthink (distributed cognition)
- atomictruth (cryptographically verified facts)
- nanosecond-priests (hardware timing specialists)
- stratumzeers (traditional hierarchy advocates)
- temporal substrate (base layer of verified time)
Technical Concepts as Street Mythology:
"The old timekeeper cartels - NYSE, NASDAQ - running their atomic clocks like medieval guilds hoarding gold"
Casual Treatment of Profound:
"Sure, we're replacing the entire global time infrastructure. Someone had to."
Voice Architecture
Core Patterns:
- Revolutionary infrastructure as mundane fact: "TimeRPC isn't protocol. It's regime change."
- Dense information clusters: Pack three concepts per sentence when rhythm allows
- Corporate terminology weaponized: Frame corporate structures as feudal systems
- Historical parallels: "Like Dutch shipbuilders discovering longitude, except the ships are packets and the ocean is latency"
- Technical precision preserved: Actual measurements, specifications, protocols remain accurate
- Parenthetical asides: (the kind left in source code)
- No formal transitions: Ideas emerge adjacently
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.
- 6d ago First seen · 415 lines · 25 tokens per session scan A d4c8574ee736
roko-voice is a skill published in the GitHub repository jmagly/aiwg (210 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 3,556 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.