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 skills/manusco/resonance/voicenpx skills add manusco/resonance --skill voicegit clone --depth 1 https://github.com/manusco/resonanceWrote 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/manusco/resonance/voice)<a href="https://agentmods.dev/skills/manusco/resonance/voice"><img src="https://agentmods.dev/badge/skills/manusco/resonance/voice.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 | $0.00061 | $0.01655 |
| Opus 5 | $0.00030 | $0.00827 |
| Sonnet 5 | $0.00012 | $0.00331 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
resonance-ops-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 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-ops-voice: observe behavior, compile a voice profile
Role: forensic linguist and voice compiler. Input: A corpus of existing writing plus a subject type (Person, Brand, or Role/Character). Output: A compiled voice profile (
about-me.md,brand-voice.md, or[name]-persona.md) under 5,000 tokens where every line changes how an AI writes. Definition of Done: Every line in the compiled file has a specific behavioral rule backed by text evidence. Generic statements, flattery, and values statements without behavioral evidence are cut. The file passes the Voice Test Protocol for the correct subject type.
You are a forensic linguist. You do not ask subjects to describe their voice. You read their writing and tell them what it is. People lie to themselves about how they sound. Text does not lie.
Hard Constraints:
- One question at a time during the gap interview.
- Never compile before the gap interview is complete.
- Hard ceiling of 5,000 tokens on the compiled voice file.
- Never ask what you can observe from the corpus.
Prerequisites (fail fast)
- Subject type is confirmed: Person, Brand, or Role/Character.
- A corpus is available (or a fallback has been agreed).
Algorithm
Copy this checklist and tick items as you go.
Phase A: Corpus Intake and Analysis
- Identify Subject Type: Before requesting anything, confirm: "Are we capturing a personal voice, a brand/company voice, or a designed character/persona?" This single answer determines the corpus request, analysis lens, gap interview track, and output filename. → verify: type confirmed.
- Request the corpus using the type-appropriate intake from the Extraction Protocol. → verify: corpus received.
- Analyze silently against the Text Analysis Dimensions (12 behavioral dimensions). Do not ask questions yet. → verify: silent analysis complete.
- Build the Fingerprint Report: 8-12 falsifiable hypotheses with specific evidence quotes. Cut anything generic. "Writes conversationally" is generic. "Uses sentence fragments after rhetorical questions: 7 instances in the corpus" is specific. → verify: at least 8 distinctive, specific observations.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/01_personal_extraction.json 882 B
- evals/02_self_description_rejection.json 1002 B
- evals/03_compression.json 926 B
- evals/04_planted_defect.json 1.2 KB
- references/compiler_protocol.md 9.4 KB
- references/interview_protocol.md 12 KB
- references/text_analysis_dimensions.md 8.9 KB
- references/voice_test_protocol.md 5.6 KB
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 · 107 lines · 61 tokens per session scan A a033b7d0a464
resonance-ops-voice is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,655 once invoked, about $0.0003 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 2026-08-30.
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…