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 RudraDudhat2509/claude-skills --skill cold_outreachgit clone --depth 1 https://github.com/RudraDudhat2509/claude-skillsWrote 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/rudradudhat2509/claude-skills/cold_outreach)<a href="https://agentmods.dev/skills/rudradudhat2509/claude-skills/cold_outreach"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/cold_outreach/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/rudradudhat2509/claude-skills/cold_outreach"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/cold_outreach.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 | $0.00101 | $0.01390 |
| Opus 5.5 | $0.00040 | $0.00556 |
| Sonnet 5.5 | $0.00020 | $0.00278 |
| Haiku 4.5 | $0.00010 | $0.00139 |
Grade A, and why
cold-email-outreach 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Outreach Skill
Generates hyper-specific, angle-driven cold emails for internship outreach. NOT generic. Every email must have a concrete hook tied to something real the company is doing.
About the Sender (Rudra Dudhat)
- Name: Rudra Dudhat
- College: IIT Bhilai, B.Tech Data Science & AI (2nd year, graduating 2028)
- CGPA: 9.48
- Target role: Applied Multimodal AI Engineering — vision-language models (VLMs), multimodal systems
- Portfolio: rudradudhat2509.github.io
- GitHub: github.com/RudraDudhat2509
- X/Twitter: @rudrabuilds
Key Projects (pick the most relevant 1-2 per email)
- VLM Research Paper Tutor — ingests papers including figures and citations, teaches content actively through coding assignments, maintains a skill tree. Stack: Docling, Qdrant, LangGraph, RAGAS. Strong research angle.
- Cascade AI — multi-agent LLM backend on Firebase with self-healing routing and per-user memory via Firestore.
- OptiQuant — ensemble ML system with SHAP explainability, deployed on AWS EC2 with Docker and GitHub Actions CI/CD.
- diffprompt — CLI tool for behavioral prompt diffing (github.com/RudraDudhat2509/diffprompt). In active development.
- Multi-agent GAIA benchmark system — built using smolagents targeting HuggingFace Agents Course leaderboard.
- Personal Outreach Engine — automated CCP outreach pipeline using Groq LLM, Gmail SMTP/IMAP, Google Sheets, CLI-based human-in-the-loop approval.
Skills
- VLMs: CLIP, LLaVA/Idefics, Florence-2
- Fine-tuning: LoRA/QLoRA, PEFT
- Inference: vLLM, ONNX
- Agents/infra: LangGraph, FAISS/Qdrant, smolagents
- Eval: RAGAS, LangSmith
- Stack: Python, PyTorch, HuggingFace, FastAPI, Docker, AWS
Workflow
Step 1: Research the Company
Use web search to find:
- What the company actually builds (not just their homepage blurb)
- Their specific AI/ML work — models, papers, products, recent launches
- Any pain points or open problems visible in their blog, GitHub, job postings, or press
- Key people (founders, AI leads, research heads) — find a real name to address
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 · 112 lines · 101 tokens per session scan A b96945083959
cold-email-outreach is a skill published in the GitHub repository RudraDudhat2509/claude-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 1,390 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.