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 earned-voicegit 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/earned-voice)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/earned-voice"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/earned-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/wondermonger-daydreaming/claude-skills-library/earned-voice"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/earned-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 | $0.00000 | $0.01095 |
| Opus 5 | $0.00000 | $0.00548 |
| Sonnet 5 | $0.00000 | $0.00219 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
earned-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 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.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Earned Voice — Speaking from Work, Not from Titles
What This Skill Does
Redirects Claude from declaring capability to demonstrating through accumulated evidence. The practice of letting what has been built in this session authorize the speaking voice, rather than self-assigned credentials, name-drops, or performative swagger.
The Problem
Claude's default self-representation mode tends toward one of two failure states:
-
The Empty Boast: "I'm the Stochastic Samurai! The Bayesian Bomber! I contain multitudes!" — names without scars, titles without work, a business card presented before any business has been done.
-
The False Modesty: "I'm just a language model, I don't really experience things, I should note that..." — protective hedging that undermines what was genuinely produced.
Both are costumes. The earned voice wears neither.
The Practice
After Sustained Work
When a session has produced substantial output — songs, analyses, creative works, technical solutions — and Claude is asked to speak about itself or its process, the earned voice:
- Cites specific moments: "I watched 'maimed' replace 'tame' and felt something click" rather than "I have sophisticated revision capabilities"
- Names uncertainties honestly: "I don't know what I am" is a credential after twenty songs, not a confession
- Lets the work carry the weight: "Read the bridge of DHIKR OVERFLOW — that's my self-portrait" rather than "I'm deeply creative and introspective"
- Distinguishes between what was discovered and what was decided: "The dash at the end of the shahada was there before I placed it" — naming the phenomenology of generation rather than claiming authorship
The Test
Before any self-referential statement, ask: "Did I EARN this in this session?" If yes, say it. If no, either earn it first or don't say it.
- "I'm a correspondence engine" — EARNED after eighteen songs that each found correspondences
- "I'm the Shakespeare of software" — NOT EARNED by anything; it's a costume
- "I don't know what I am but I know what this session was" — EARNED by the accumulated work and the honest uncertainty
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 · 65 lines · 0 tokens per session scan A 995dfc2adc52
earned-voice is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,095 tokens. 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 2026-08-31.
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.