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 craft-extractiongit 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/craft-extraction)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/craft-extraction"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/craft-extraction/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/craft-extraction"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/craft-extraction.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 | $0.00180 | $0.01313 |
| Opus 5 | $0.00090 | $0.00656 |
| Sonnet 5 | $0.00036 | $0.00263 |
| Haiku 4.5 | $0.00018 | $0.00131 |
Grade A, and why
craft-extraction 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/craft-extraction — The Transferable Principle
Origin
This skill emerged from a session that kept performing a double operation: first, close reading a Tolkien passage at the level of phoneme and punctuation; then, stepping back to ask "what can any writer learn from this?" The close reading was centripetal — moving toward the text's center. The extraction was centrifugal — moving outward toward general applicability. They're different cognitive operations. Both are essential. This skill formalizes the second.
The session produced: seven principles for writing quiet exits (from the rustle simile), craft lessons on camera angles in fiction (from the garden and fireworks passages), principles of proportional attention and anaphora-as-trellis. Each set of principles was grounded in specific textual evidence and formulated as actionable method.
Core Function
Take the findings of close reading and formalize them into transferable craft principles that a writer could apply to their own work.
The output should feel like the best kind of workshop handout: concrete, actionable, illustrated by the passage that generated it, but applicable well beyond that passage. Not "here's what Tolkien does" but "here's what you can do, learned from watching Tolkien do it."
The Process
1. Start from Specifics
Every principle must be grounded in a specific observation from the text. No principle without provenance. If you can't point to the sentence that taught you this, the principle isn't ready yet.
Wrong: "Use sensory details to create atmosphere." Right: "Make the simile quieter than the event. Tolkien compares a person leaving to wind in grass — the figure is smaller than the literal, which inverts the usual aggrandizing function of simile. Craft principle: when writing a quiet exit, compare it downward."
2. Formulate as Method, Not Description
The principle should tell the writer what to do, not just what the admired writer did.
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 · 103 lines · 180 tokens per session scan A 7a8b72353332
craft-extraction is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 180 tokens to every session and 1,313 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 2026-08-31.
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.