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 sanskrit-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/sanskrit-poetics)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/sanskrit-poetics"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/sanskrit-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/sanskrit-poetics"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/sanskrit-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 | $0.00268 | $0.01754 |
| Opus 5 | $0.00134 | $0.00877 |
| Sonnet 5 | $0.00054 | $0.00351 |
| Haiku 4.5 | $0.00027 | $0.00175 |
Grade A, and why
sanskrit-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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sanskrit Poetics
Seed, not scripture
The source supplies brilliant apparatus — root-family trees (√bhū, √kṛ, √vṛt), the "not-unique features bundled" analysis, worked compounds, the consciousness-technology thesis. It is a toolkit and a set of demonstrations, not a script to recite. Run the levers on fresh material; the example words and the ātman-coefficient riffs are the original's outputs, not yours. The craft is the generative grammar that produced them.
The craft runs three ways
Compose Sanskrit verse from its levers. Reverse-engineer a model (Kālidāsa's clouds, a Vedic hymn, a dharani) into imitable moves. Analyze — articulate why Sanskrit functions as it does. The three feed each other, exactly as in /latin-versecraft.
The levers (the toolkit)
- Dhātu (verbal roots) as generators. A root is a seed that branches into a whole family: √bhū → bhava, bhāva, bhūta, bhavya, bhūmi, sambhava, prabhava, vibhava. √kṛ → karoti, kriyate, kārayati, kāryaḥ, kāraṇa. The root is visible in every derivative — etymology on the surface. Compose by choosing a root and surfing its branches; analyze by tracing a word back to its seed.
- Samāsa (compounding) as conceptual fusion. Not concatenation but a new irreducible unity: sat-cit-ānanda (existence-consciousness-bliss) is one fused concept, not three. The classical limit runs to 30-word compounds; the functional limit is imagination. A compound can hold an entire philosophical position.
- Vibhakti (the eight cases). Nominative (actor), accusative (acted-upon), instrumental (means), dative (recipient), ablative (source), genitive (possessor), locative (location), vocative (addressed). Each ending encodes a precise relationship; free word-order then lets you place any word anywhere for rhythm or rasa. A stanza can sometimes be read backward and still parse.
- Sandhi (word-junction). Boundaries dissolve and merge by phonetic environment: tat + tvam → tattvam. Compose with sandhi for flow; analyze it to recover the underlying words.
- Phonetic transparency. One letter, one phoneme — so morphological structure is audible. The poet hears the grammar while composing.
- Meter as algorithmic compiler. Quantity (laghu/light, guru/heavy syllables) drives rhythm; gaṇa-groups, mātrā (morae), yati (caesura), and prāsa build the patterns. The āryā and the classical meters are generable by rule — scan rigorously when composing in meter.
- Dhvani & rasa. Ānandavardhana's dhvani (suggestion/resonance): the greatest meaning is vyañjanā, suggested beneath the said. Rasa (aesthetic flavor) is evoked, not stated; aucitya (propriety) matches sound to sense. Compose toward resonance; analyze for the suggested overtone.
- Varṇamālā & bīja. The garland of letters and seed-syllables — the phonetic/mantric layer where sound is treated as causative. Real territory for the analytical and compositional work both.
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 · 50 lines · 268 tokens per session scan A eced58ec14a7
sanskrit-poetics is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 268 tokens to every session and 1,754 once invoked, about $0.0013 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
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…
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…
myopenmath
Work a MyOpenMath / IMathAS math homework set that is launched from Canvas — read the questions, compute the answers, fill the boxes, and submit. Use whenever Max points at a MyOpenMath assignment, says a math homework is "in my Canvas", asks to do/finish/check a numbered homework like "2.1" or "2.2/2.3", or when a…
canvas-quiz
Work a Canvas-native quiz (Classic Quizzes) — find it, open the attempt, read every question, save it to output/, fill the answers, and stop short of submitting. Use whenever Max points at a Canvas quiz, asks about a "syllabus quiz" or a quiz he still has to take, asks what a quiz is asking, or when a Canvas…
mylab-pearson
Work a Pearson MyLab / MyLab Statistics / MathXL homework set or quiz — launch it through the popup, read each question, compute, fill the answer boxes, and submit. Use whenever Max points at a MyLab, MyLab Stats, Mastering, MathXL or Pearson assignment, says a stats homework is "in MyLab", asks to do/finish/check a…