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 latin-versecraftgit 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/latin-versecraft)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/latin-versecraft"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/latin-versecraft/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/latin-versecraft"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/latin-versecraft.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 | $0.00233 | $0.01519 |
| Opus 5.5 | $0.00093 | $0.00608 |
| Sonnet 5.5 | $0.00047 | $0.00304 |
| Haiku 4.5 | $0.00023 | $0.00152 |
Grade A, and why
latin-versecraft 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Latin Versecraft
Seed, not scripture
The source supplies dazzling apparatus — the "consciousness-algorithm" formulae, the Horatian device inventory, worked scansions, fully-conjugated neologisms. The formulae are scaffolds to improvise from, not blanks to fill. Formula I: [participle] + [abstract noun] + [ablative] + [verb of motion] is a starting constraint that frees invention, the way a sonnet's fourteen lines do — run it once, feel the shape, then depart from it. Filling the template mechanically produces exercises, not poems. The example verses are demonstrations of the move; write your own.
The craft runs both ways
Composition — build Latin verse from its levers. Reverse-engineering — take a model and extract the constructions that make it work, as imitable technique. The two feed each other: you reverse-engineer Horace to learn the moves, then deploy them in original lines. Most sessions do one or the other; the strongest do both in a loop.
The levers (the toolkit)
- Free word-order as drama. Because cases carry grammar, position carries emphasis and suspense. The same six words yield six different poems — Puer puellam amat is neutral; Amat puellam puer withholds the subject for a dramatic reveal. Sculpt the reader's experience by arrangement.
- Inflection-as-compression. A single verb (amārentur) packs voice, mood, tense, person, number. Use this to fit a complex idea into a tight metrical slot — every syllable load-bearing.
- Hyperbaton. Divorce adjective from noun across a line; the modifier hovers, unresolved, and the gap is where the reader does the work (metaque... fervidīs... evitāta... rotīs — the wheels arrive last, the danger felt before it's named).
- The ablative absolute. Urbe captā — two words holding a whole narrative (the city that was, the capture, the consequence, the loss). Compact scene-setting; stack them like camera angles.
- Participial stacking. Verb-adjective hybrids cascade into architectural sentences — each participle a narrative beat folded into a word.
- Mood. The subjunctive is a reality-generator (utinam viverem — would that I lived — conjures a whole counterfactual world). Wishes, fears, purposes, possibilities, all built into the grammar.
- Meter & scansion. Quantity (long/short syllables) drives the rhythm. Know the patterns — dactylic hexameter (– ˘ ˘ | ...), the elegiac couplet's hexameter-then-pentameter return, sapphics, iambics — plus elision, caesura, correption as pacing controls. Latin wants to scan; work with the grain.
- Neologism-coinage. Mint a new word by welding roots (flammivomus, flame-vomiting; verisimilis, truth-similar), then conjugate or decline it fully — each compound a compressed argument, each paradigm a small cosmology.
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.
- 1mo ago First seen · 50 lines · 233 tokens per session scan A 814ef1d15d6e
latin-versecraft is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (7 stars, last pushed 18d ago), licensed MIT. It adds 233 tokens to every session and 1,519 once invoked, about $0.0009 per session on Opus 5.5. 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
founder-coach
Personal leadership development for founders and first-time CEOs. Covers founder archetype identification, delegation frameworks, energy management, CEO calendar audits, leadership style evolution, blind spot identification, imposter syndrome, founder mental health, and succession planning. Use when a founder feels…
cs-onboard
Founder onboarding interview that captures company context across 7 dimensions. Invoke with /cs-onboard setup for initial interview or /cs-onboard update for quarterly refresh. Generates /.claude/company-context.md used by all C-suite advisor skills. Use when setting up the C-suite advisors for the first time, or when…
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
algo-sensei
Your personal DSA & LeetCode mentor. Use for problem explanations, progressive hints, code reviews, mock interviews, pattern recognition, complexity analysis, and custom problem generation. Automatically adapts to your learning style and request type.
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
canvas-homework
Check Canvas for outstanding assignments and either surface the assignment, or draft a response in Max's voice. Use whenever Max asks what assignments / homework / coursework he still has to do, asks to pull an assignment's instructions or files from Canvas, or asks to start/draft an assignment. Orchestrates the…