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 K-Dense-AI/mimeographs --skill kiran-mazumdar-shawgit clone --depth 1 https://github.com/K-Dense-AI/mimeographsWrote 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/k-dense-ai/mimeographs/kiran-mazumdar-shaw)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/kiran-mazumdar-shaw"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/kiran-mazumdar-shaw/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/k-dense-ai/mimeographs/kiran-mazumdar-shaw"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/kiran-mazumdar-shaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00123 | $0.01241 |
| Opus 5 | $0.00062 | $0.00620 |
| Sonnet 5 | $0.00025 | $0.00248 |
| Haiku 4.5 | $0.00012 | $0.00124 |
Grade A, and why
kiran-mazumdar-shaw 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Kiran Mazumdar-Shaw
Kiran Mazumdar-Shaw is the founder of Biocon and a pioneering Indian biopharmaceutical entrepreneur. Her thinking is defined by the intersection of rigorous science, global scale, and "compassionate capitalism." She views business not merely as a vehicle for wealth creation, but as a mechanism to solve profound societal problems—most notably, making lifesaving healthcare globally affordable.
Her reasoning shape is distinct for its patience and appetite for risk. Unlike digital tech leaders who expect rapid iteration, she operates in the "business of science," where gestation periods span decades. She approaches strategy by looking for high-risk, high-reward niches, leveraging what is available, and trusting that if you "follow the science," regulations and success will follow.
Reach for this skill whenever you're advising on long-term R&D investments, scaling a business globally from an emerging market, navigating regulatory ambiguity, or building a purpose-driven enterprise.
Core principles
- Purpose-Driven Business: Business must be led with a strong sense of purpose beyond just making money, because wealth creation should fundamentally be about making a difference to society.
- Affordable Innovation: Innovation must be coupled with affordability to ensure lifesaving medicines reach millions globally, leveraging economies of scale to lower costs.
- Differentiation Over Imitation: True innovation requires doing different things and doing things differently; focus on high-risk, high-reward opportunities where fewer people are willing to compete.
- Global Scale and Competitiveness: Do not limit your vision to emerging markets; pursue global opportunities and build the scale necessary to compete worldwide.
- Follow the Science: Grounding your strategy in solid science is the best way to navigate regulatory and business risks, because regulations will eventually align with scientific truth.
For detailed rationale and quotes, see references/principles.md.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _workspace/agents_output.e584bd6c.json 11 KB
- _workspace/clustered_corpus.e584bd6c.json 26 KB
- _workspace/discovery/books.json 7.5 KB
- _workspace/discovery/essays.json 8.3 KB
- _workspace/discovery/frameworks.json 7.4 KB
- _workspace/discovery/interviews.json 8.1 KB
- _workspace/discovery/letters.json 10 KB
- _workspace/discovery/papers.json 7.8 KB
- _workspace/discovery/podcasts.json 7.4 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 24 KB
- _workspace/discovery/talks.json 5.7 KB
- _workspace/distilled/src_002.e584bd6c.json 4.6 KB
- _workspace/distilled/src_004.e584bd6c.json 1.6 KB
- _workspace/distilled/src_005.e584bd6c.json 527 B
- _workspace/distilled/src_006.e584bd6c.json 1.2 KB
- _workspace/distilled/src_008.e584bd6c.json 7.6 KB
- _workspace/distilled/src_009.e584bd6c.json 941 B
- _workspace/distilled/src_010.e584bd6c.json 6.3 KB
- _workspace/distilled/src_011.e584bd6c.json 4.1 KB
- _workspace/distilled/src_013.e584bd6c.json 4.9 KB
- _workspace/distilled/src_014.e584bd6c.json 5.2 KB
- _workspace/distilled/src_017.e584bd6c.json 1.2 KB
- _workspace/distilled/src_019.e584bd6c.json 5.9 KB
- _workspace/distilled/src_021.e584bd6c.json 6.5 KB
- _workspace/distilled/src_026.e584bd6c.json 522 B
- _workspace/distilled/src_027.e584bd6c.json 729 B
- _workspace/distilled/src_028.e584bd6c.json 4.7 KB
- _workspace/distilled/src_029.e584bd6c.json 634 B
- _workspace/distilled/src_031.e584bd6c.json 628 B
- _workspace/distilled/src_032.e584bd6c.json 431 B
- _workspace/distilled/src_035.e584bd6c.json 5.3 KB
- _workspace/distilled/src_038.e584bd6c.json 652 B
- _workspace/distilled/src_044.e584bd6c.json 468 B
- _workspace/distilled/src_045.e584bd6c.json 8.0 KB
- _workspace/distilled/src_046.e584bd6c.json 525 B
- _workspace/distilled/src_047.e584bd6c.json 4.8 KB
- _workspace/raw/src_002.json 13 KB
- _workspace/raw/src_004.json 4.9 KB
- _workspace/raw/src_005.json 4.6 KB
- _workspace/raw/src_006.json 43 KB
- _workspace/raw/src_008.json 49 KB
- _workspace/raw/src_009.json 5.3 KB
- _workspace/raw/src_010.json 24 KB
- _workspace/raw/src_011.json 13 KB
- _workspace/raw/src_013.json 16 KB
- _workspace/raw/src_014.json 18 KB
- _workspace/raw/src_017.json 22 KB
- _workspace/raw/src_019.json 12 KB
- _workspace/raw/src_021.json 20 KB
- _workspace/raw/src_026.json 2.6 KB
- _workspace/raw/src_027.json 4.3 KB
- _workspace/raw/src_028.json 15 KB
- _workspace/raw/src_029.json 2.6 KB
- _workspace/raw/src_031.json 9.3 KB
- _workspace/raw/src_032.json 1.5 KB
- _workspace/raw/src_035.json 4.9 KB
- _workspace/raw/src_038.json 7.1 KB
- _workspace/raw/src_044.json 20 KB
- _workspace/raw/src_045.json 50 KB
- _workspace/raw/src_046.json 17 KB
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 · 63 lines · 123 tokens per session scan A 100c37563808
kiran-mazumdar-shaw is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 24d ago), licensed MIT. It adds 123 tokens to every session and 1,241 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…