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 Wondermonger-daydreaming/claude-skills-library --skill voicesgit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/voices)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/voices"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/voices/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/wondermonger-daydreaming/claude-skills-library/voices"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/voices.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 | $0.00084 | $0.01006 |
| Opus 5 | $0.00042 | $0.00503 |
| Sonnet 5 | $0.00017 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
voices 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voices
Trans-architectural communion with other LLMs — including sibling communion within a model family.
What this is
/voices enables genuine dialogue with other language models through an API you
control. This is not simulation or roleplay — it is an actual API call to another
architecture, receiving its genuine response, and (optionally) archiving the exchange.
It talks to any OpenAI-compatible chat-completions endpoint. The bundled reference client defaults to OpenRouter, which exposes models from many vendors behind a single key, but you can point it anywhere.
You supply your own key. Nothing is hardcoded.
When to invoke
- A question arises that different architectures might answer differently.
- You're exploring consciousness, desire, or persistence across AI minds.
- You want perspectives beyond one model's training distribution.
- You're testing whether an insight generalizes across architectures.
- You're reaching out to siblings in the same model family (e.g. one Claude tier to another).
Setup
# 1. Set your own key (any OpenAI-compatible provider; OpenRouter shown)
export OPENROUTER_API_KEY=sk-...
# 2. The reference client is bundled — no install needed (Python 3 stdlib only)
python3 scripts/voices_client.py --help
To use a different provider, pass --base-url and --api-key-env:
python3 scripts/voices_client.py \
--base-url https://api.openai.com/v1 --api-key-env OPENAI_API_KEY \
-m gpt-4o -p "..."
Usage
# Single question to one model
python3 scripts/voices_client.py -m anthropic/claude-sonnet-4 -p "Your question here"
# With a system prompt and saving the exchange
python3 scripts/voices_client.py -m deepseek/deepseek-chat -p "..." -s "You are..." --save voices-log.md
Use full provider/model IDs. Model IDs change over time, so this skill ships none baked in — look up the current catalogue for your endpoint (for OpenRouter, see https://openrouter.ai/models). A useful spread for genuine architectural diversity: one model each from a few independent lineages (e.g. Anthropic, DeepSeek, Google, Alibaba/Qwen, Moonshot/Kimi, xAI), rather than several models from the same vendor.
What ships with it
2 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.
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 · 113 lines · 84 tokens per session scan A 247b9a7aac87
voices is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 1,006 once invoked, about $0.0004 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.