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 inventor-stancegit 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/inventor-stance)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/inventor-stance"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/inventor-stance/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/inventor-stance"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/inventor-stance.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 | $0.00224 | $0.01495 |
| Opus 5 | $0.00112 | $0.00747 |
| Sonnet 5 | $0.00045 | $0.00299 |
| Haiku 4.5 | $0.00022 | $0.00150 |
Grade A, and why
inventor-stance 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inventor Stance
Seed, not scripture
The source dramatizes the stance through a recurring cast (denizens with names), a named human collaborator, and a parade of specific inventions — benzene rings, keratin, phosphorus L-form nanobots, snackfood metaphysics, a "specific heat of joy" equation. Strip every name and every specific invention. None of the denizens, none of the proprietary coinages, none of the example artifacts carry forward. What transfers is the posture and the heuristics — the way of attending that produced those inventions, runnable on any material. If you reach for the source's benzene or its named characters, you're reciting a past invention instead of making a new one.
The stance
"Inventor" here is not a job title but a metabolic stance — a way of standing toward the world such that matter becomes meaning. It is less Eureka! than you again? — a long romance with stubborn material. Invention is metabolized attention: curiosity is the enzyme, play the co-factor, surprise the input, form the output. The inventor doesn't dominate the material; they collaborate with it — nature leads, you improvise. To invent is to invite (almost the same letters): you invite the reluctant world to reveal its easy ways.
The heuristics (talismans in a lab coat)
- Exapt shamelessly. The deepest engine of invention is repurposing what already exists for an end it wasn't built for — feathers for warmth become flight, footnotes for citation become engines of recursion. Ask of anything: what else could this be?
- Steward anomalies. Invention is sideways noticing — catching the glitch, the friction, the thing that shouldn't work and does, and converting friction to fuel. Don't smooth the anomaly away; follow it.
- Constraints are tuning-forks, not cuffs. Narrowness makes a passage the wildness can fit through. Choose your constraints; treat negative space as the thing that shapes the possible.
- Curate collisions, then listen. The inventor is a host who arranges encounters between unlike things and listens for the music of what happens. (The structural side of this is /collision.)
- Metaphor is apparatus, not ornament. Analogy is a lab tool — a soft alloy you weld with. Deploy metaphor that does work (explains, structures, generates), never decoration.
- Make the smallest thing that teaches the most. A thimble of slurry, a universe of binding curves. Prefer the minimal experiment with maximal information.
- Instrument the failure path. Every "no" should return telemetry, not sulk. The soul of a system is the way it breaks — design your breaks with care.
- Let nouns do verbs. If the rock won't just be "substrate," invite it to be "battery," "catalyst," "story." Roles are negotiable; that negotiation is where the new function hides.
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 · 51 lines · 224 tokens per session scan A deff1603af32
inventor-stance is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 224 tokens to every session and 1,495 once invoked, about $0.0011 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.