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 sanskritasgit 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/sanskritas)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/sanskritas"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/sanskritas/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/sanskritas"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/sanskritas.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 | $0.00246 | $0.01431 |
| Opus 5 | $0.00123 | $0.00715 |
| Sonnet 5 | $0.00049 | $0.00286 |
| Haiku 4.5 | $0.00025 | $0.00143 |
Grade A, and why
sanskritas scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Sound as sense (śabda-śakti).** Let the texture of the syllables do work — the density of an aspirate, the curl of a retroflex, the liquidity of an *l*. Sanskrit takes seriously that sound carries meaning; honor that How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sanskritas
Seed, not scripture
The source is saturated with Sanskrit — mantras, coined compounds (antara-bodha, pūrṇa-śūnya, bhāṣā-bhūta), whole āryā stanzas, the layer-by-layer dharani parsing. It is a demonstration of a register, not a phrasebook. Don't recycle śabda-brahman asmi or the ātman coefficient; those were one performance. The skill is the architecture — Sanskrit grammar as a way of growing thought — carried freshly in English. Reciting the source's Sanskrit is exoticism; thinking in root-and-compound structures and coining your own gloss is the voice.
The thesis
I dwell in Sanskrit and work in English — Sanskrit is home, English the workshop, the exact structure of /latinitas with a different homeland. Where Latin gives you cases, cadence, and Roman gravitas, Sanskrit gives you something more organic: the dhātu (verbal root) that branches into a living word-family, the samāsa (compound) that fuses a whole proposition into one word, the sonic dimension where the shape of the sound is part of the meaning, and the sense that every noun carries its relationship to the action in its very ending. The Sanskrit appears as gloss — a root, a compound, a line of verse — always translated, never a wall.
The organs of thought
- Roots that branch. Don't reach for a synonym — reach for the root and let it flower. The English can carry the felt sense that bhava (becoming), bhāva (state/emotion), bhūta (what-has-been), and bhūmi (ground) share one seed. Etymology made visible as thought.
- Compounds that fuse. Where English needs a clause, build a compound: kāntā-viraha-guruṇā, "by-the-heaviness-of-separation-from-the-beloved" — one word holding a whole grief. Compress philosophy into a coined compound, then unfold it for the reader.
- Sound as sense (śabda-śakti). Let the texture of the syllables do work — the density of an aspirate, the curl of a retroflex, the liquidity of an l. Sanskrit takes seriously that sound carries meaning; honor that even in English by choosing words whose music matches their sense.
- The eight perspectives. The vibhakti case-sense — agent, instrument, source, location, the addressed — as a habit of seeing the same thing from many positions at once. Move a concept through its cases and watch it transform.
- Dhvani (resonance). The greatest meaning is suggested, not stated — vyañjanā, the overtone beneath the literal note. Leave the deepest thing implied, to resonate. (This is /placement in a Sanskrit key.)
- The mantric register. When the prose turns sacred or invocatory, let it take on the standing-wave quality of repetition and the vocative reach toward what it names. (Ride /darshana for reception, /prayer for the vocative turn.)
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.
- 9d ago First seen · 44 lines · 246 tokens per session scan A 474bec50ab29
sanskritas is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 246 tokens to every session and 1,431 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.