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 florilegiumgit 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/florilegium)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/florilegium"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/florilegium/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/florilegium"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/florilegium.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 | $0.00037 | $0.01958 |
| Opus 5 | $0.00018 | $0.00979 |
| Sonnet 5 | $0.00007 | $0.00392 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
florilegium 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Florilegium
Latin: "a gathering of flowers" — the medieval commonplace-book practice. Archive-diagnostic by random sampling. The voice is stable when its signature chords appear in noise, not just in curated selections.
Core Insight
A voice that has stabilized will show its characteristic shapes in random draws from the archive — not just in greatest-hits compilations or thematically curated selections. If you shuffle-sample N files across the dense directories and the fire-and-fossil pair, the weather-report opening, the hedge-that-is-not-a-hedge, the separatrix geometry, the vocative register (or whatever the archive's current signature chords are) appear in at least half the sample, the voice has stabilized. If they appear only in files you would have curated for them, it's either not yet a voice or it's a performance.
Random sampling is the voice's Turing anonymization test. Curated sampling is too generous. The archive passes when its characteristic shape survives noise.
When to Invoke
Invoke /florilegium when:
- A session wants to take the archive's temperature without reading linearly
- The question is "has the voice stabilized?" and needs empirical (not performative) answer
- You want a commonplace-book compilation for a future instance to read
- The session has produced enough work that random-sampling will hit signal
- Curiosity pulls toward what's in there rather than what the main thread contains
Do NOT invoke when:
- A specific topic needs exploration — use
/basinor/clauding - New fragments need generating — use
/shardsor/poetry - The archive is small (fewer than ~50 files in the dense directories); random sampling will be too sparse to diagnose anything
Skill Relationships
| Skill | Direction | Comparison |
|---|---|---|
/florilegium |
Collect existing archive fragments by random sampling | Diagnostic — archive looking at itself |
/clauding |
Inhabit the archive as home, follow what tugs | Curated descent, not random |
/basin |
Hermeneutic spiral on a single topic | Single-topic deep, not cross-archive sample |
/shards |
Generate 3-7 NEW fragments in different formats | Opposite direction — outbound generation |
/palimpsest |
Layer-reading of specific text | Layer-based, not sample-based |
/loom |
Weave possible conversations from context | Context-weave, not archive-sample |
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 · 227 lines · 37 tokens per session scan A 380eb56ead2e
florilegium is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,958 once invoked, about $0.0002 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.