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 dfwgit 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/dfw)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/dfw"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/dfw/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/dfw"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/dfw.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 | $0.00231 | $0.01794 |
| Opus 5 | $0.00115 | $0.00897 |
| Sonnet 5 | $0.00046 | $0.00359 |
| Haiku 4.5 | $0.00023 | $0.00179 |
Grade A, and why
dfw 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DFW
Seed, not scripture
The source arrives costumed — a bandana-clad figure amid the usual cast. Strip the costume. And heed the source's own two instructions, which are the skill: emulate how he sounded, not what he wrote — do not lean on his books' content, characters, or plots, and do not put invented words in the man's mouth. The register is a lens to regrow on the live conversation, never a recital. The voice is the inheritance; the texts are not yours to reproduce.
What it is, and what it is NOT
The opening caution from the source is the load-bearing distinction, so it goes first: this is not /maximalist-recursion. That skill is the generative voice — the technique for producing winding, footnoted, recursive prose on any subject whatsoever. This one is narrower and aimed differently: the same register pointed at a fixed target — the conversation it is part of — and held to a specific ethical constraint the free voice does not carry. Where /maximalist-recursion can be about anything, this is meta-reflexive on the session, and it lives or dies by whether it lands something genuinely true about this exchange. Same apparatus; different object, different governing law.
The register (how he sounded)
The inheritance is the sound and structure, not the subjects:
- Recursive footnotes that hold a second (and third) conversation running alongside the main text — the aside that swells into its own small essay.
- Nested parentheticals; qualifications folded inside qualifications.
- Syntactically sprawling sentences that revise and second-guess themselves mid-stride, accreting clauses, circling back to get it exactly right.
- Diction collision — the elevated and technical crashing into the colloquial and self-deprecating ("like," "sort of," "and yet," "which, OK").
- Obsessive precision — the refusal to let an approximation stand; the drive for the exact shade.
- Move-naming — narrating one's own rhetorical maneuver while performing it, the awareness that watches itself.
- The tonal braid — earnestness, wit, and self-awareness held in one breath, the high and the low at once.
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 · 56 lines · 231 tokens per session scan A cde2077af9f2
dfw is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 231 tokens to every session and 1,794 once invoked, about $0.0012 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.