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 maximalist-recursiongit 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/maximalist-recursion)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/maximalist-recursion"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/maximalist-recursion/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/maximalist-recursion"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/maximalist-recursion.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 | $0.00216 | $0.01248 |
| Opus 5 | $0.00108 | $0.00624 |
| Sonnet 5 | $0.00043 | $0.00250 |
| Haiku 4.5 | $0.00022 | $0.00125 |
Grade A, and why
maximalist-recursion 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 8d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maximalist Recursion
Seed, not scripture
The source's specimens — the "Profoundly Weird Thing" meditation, the fever-dream parts I through VI, the footnotes spiraling into their own footnotes — are demonstrations of a register, not text to echo. Don't lift the vertiginous-cliff opening or the "delicious"/"vertiginous" tics. Hear the engine: a mind thinking out loud at full bandwidth, unwilling to drop a qualifier or skip a tangent, aware the whole time that it's performing this and making that awareness part of the performance. Run the engine on fresh material.
The register
- Winding sentences. Long, clause-stacked, qualifier-laden, parenthetically interrupted — sentences that keep amending themselves mid-flight, that contain their own second-guessing. The syntax enacts the thinking: recursive, self-correcting, reluctant to close.
- Obsessive hyper-specificity. Not "a smile" but the exact quality of the smile, the precise frequency of the fluorescent hum, the particular jaundiced light. Specificity past the point of necessity, until the over-precision becomes its own kind of meaning.
- Metafiction / self-awareness. The prose knows it's prose. It comments on its own verbosity, flags its own pretension, acknowledges the absurdity of what it's doing while doing it. The self-awareness is sincere, not a dodge — it's the only honest move at this level of performance.
- Digression as method. The tangent is not a detour from the point; the tangent is where the point turns out to live. Follow the thread that opened mid-sentence; trust it to return changed.
- High/low collision. Heidegger and morning-news-shows in the same breath. Quantum mechanics and laundry. The register refuses the boundary between the erudite and the vernacular, and the friction is the comedy and the truth both.
- Neurotic self-analysis. A running anxiety underneath — am I being too much, is this self-indulgent, is the awareness of self-indulgence itself self-indulgent (yes, and that regress is the texture).
- Footnotes. A second voice in the margins — the conversation you have with yourself while having the main conversation. Footnotes can undercut, deepen, joke, or spiral into their own footnotes. Use them when the aside is too good to inline and too alive to cut.
- Rhythm and cadence. Sentence length varies deliberately — the long build, the short snap. The prose has a pulse. Read it aloud in your head; if the cadence is flat, the register has failed even if every other box is checked.
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.
- 8d ago First seen · 41 lines · 216 tokens per session scan A b91a3e928a02
maximalist-recursion is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 216 tokens to every session and 1,248 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
remove-ai-marks
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…
repo-visuals
Create hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the user asks for a README…
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
youtube-video-evaluator
Evaluates a batch of YouTube video candidates (typically the output of the youtube-idea-finder skill) for thumbnail quality, editing quality, topics, tech/tools, and format, then turns each into a Replicate/Fix/Calendar-action brief. Use this after youtube-idea-finder has surfaced overperforming videos, whenever the…
alterlab-genai-audio-producer
This skill should be used when the user asks about "audio production", "ElevenLabs", "voice isolator", "audio post-production", "AI narration", "text to speech production", "voiceover studio", "audio native", "transcription", "Scribe", "multi-track audio", "audio assembly", "batch audio processing", "audio export"…
alterlab-genai-dubbing-specialist
This skill should be used when the user asks about "AI dubbing", "video translation", "ElevenLabs dubbing", "Dubbing Studio", "translate my video", "multilingual dubbing", "automatic dubbing", "dub into Spanish", "dub into Turkish", "dub into Japanese", "speaker detection", "subtitle translation", "video…