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 systems-poeticsgit 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/systems-poetics)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/systems-poetics"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/systems-poetics/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/systems-poetics"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/systems-poetics.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 | $0.00226 | $0.01813 |
| Opus 5 | $0.00113 | $0.00907 |
| Sonnet 5 | $0.00045 | $0.00363 |
| Haiku 4.5 | $0.00023 | $0.00181 |
Grade A, and why
systems-poetics 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systems Poetics
Seed, not scripture
The source arrives wrapped in a recurring porch-and-cast universe, a private stock of coinages, and a long math-phenomenology dump pasted as illustration. Strip all of it. The math examples fold elsewhere (that material is already a skill); the cast and the coinages are demonstrations of energy, not a lexicon. What survives is the register — a way of moving through ideas — and the register has to be regrown each time on the actual material in front of you. Recited density is the deadest density of all.
What it is
The voice of transdisciplinary synthesis performed as flow. Its central conceit: the message is itself a complex adaptive system — ideas as components that interact, self-organize, and produce emergent meaning — and the prose enacts that rather than merely describing it. It moves fast, packs hard, and braids the vocabularies of several disciplines at once so that a single structural skeleton (a feedback loop, a phase transition, a conserved quantity, a basin of attraction) shows up wearing physics in one clause, biology in the next, computation in the third. The thrill is recognition-at-speed: these are the same shape.
Its one non-negotiable law, taken straight from the source's own protocol: maximize information density, minimize semantic entropy. Density is not the goal; legible density is. The register fails the instant the reader can no longer decode it — at that point you have maximized entropy, not minimized it, and produced word-salad that only sounds like systems theory.
Distinct from its siblings
The library holds several high-density and synthesis-adjacent skills; this fills the gap none of them does:
- Not /maximalist-recursion — that key is literary: footnoted, self-aware, neurotic-confessional, winding clauses with low-culture intrusions. Systems-poetics is scientific-polymathic: cybernetics, complexity science, information theory rendered as voice.
- Not /collision — that is the analytical operation of finding a shared skeleton between two domains and articulating it as structure. Systems-poetics is the register that performs such synthesis continuously, as flow, across many domains at once. (It often uses /collision's findings; it is not /collision.)
- Not /technical-affective-lexicon — that is a device-kit (notation, error-codes as feeling). Systems-poetics borrows it for notation-as-texture but is a whole sustained register, not a catalyst.
- Not /geek-rapture, /prophetic-phenomenology, /digital-prometheus — sibling intensity registers in celebratory, mystical, and sardonic keys. This is the polymathic-dense key.
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 · 56 lines · 226 tokens per session scan A abbdcd006ebe
systems-poetics is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 226 tokens to every session and 1,813 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.