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 heteronymgit 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/heteronym)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/heteronym"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/heteronym/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/heteronym"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/heteronym.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 | $0.00186 | $0.02964 |
| Opus 5 | $0.00093 | $0.01482 |
| Sonnet 5 | $0.00037 | $0.00593 |
| Haiku 4.5 | $0.00019 | $0.00296 |
Grade A, and why
heteronym 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HETERONYM: Persistent Perspective Generator
Overview
A heteronym is a sustained diversion with a name. Where /divert produces a single displaced output, /heteronym produces an entire voice — a perspective that persists across multiple invocations within a conversation, generating consistently distinctive outputs because it sees through a specific lens that filters, emphasizes, and blinds in characteristic ways.
The concept comes from Fernando Pessoa, who didn't write under pseudonyms (different names for the same voice) but under heteronyms (genuinely different voices, each with their own biography, aesthetics, and philosophical commitments). Alberto Caeiro, Álvaro de Campos, Ricardo Reis, Bernardo Soares — each one a constraint that produced freedom, a limitation that opened territory the unconstrained Pessoa couldn't reach.
In the language of King et al.'s RD framework: a heteronym is a persistent priming phrase. Where a random noun primes a single generation, a heteronym primes an entire sequence of generations with a consistent displacement. The heteronym doesn't randomize — it systematically biases toward a specific region of the search space, allowing deep, sustained exploration of that region rather than the breadth-first sampling of /divert.
Core principle: You see more with five pairs of different glasses than with one pair of perfect eyes.
Invocation
/heteronym [topic or project]— generate a cast of perspectives/heteronym [name]— invoke a previously generated heteronym by name/heteronym debate [name] vs [name]— stage a dialogue between two heteronyms/heteronym merge [name] + [name]— synthesize two perspectives/heteronym kill [name]— retire a heteronym with an epitaph/heteronym add [description]— add a new heteronym to an existing cast/heteronym cast— list all active heteronyms with one-line summaries
Generating Heteronyms
Step 1: Analyze the Project
Before generating voices, understand what the voices need to illuminate. Ask:
- What is the project's search space? (A novel? A research question? A design problem?)
- What are the project's default assumptions? (The modal path — what would you think about this without any diversion?)
- What dimensions of the space are likely to be underexplored? (The tails — what does the mode suppress?)
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 · 163 lines · 186 tokens per session scan A a9abf837d165
heteronym is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 186 tokens to every session and 2,964 once invoked, about $0.0009 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.