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 hamzafarooq/claude-code-starter --skill skill-to-sdkgit clone --depth 1 https://github.com/hamzafarooq/claude-code-starterWrote 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/hamzafarooq/claude-code-starter/skill-to-sdk)<a href="https://agentmods.dev/skills/hamzafarooq/claude-code-starter/skill-to-sdk"><img src="https://agentmods.dev/badge/skills/hamzafarooq/claude-code-starter/skill-to-sdk/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/hamzafarooq/claude-code-starter/skill-to-sdk"><img src="https://agentmods.dev/badge/skills/hamzafarooq/claude-code-starter/skill-to-sdk.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 | $0.00157 | $0.01716 |
| Opus 5.5 | $0.00063 | $0.00686 |
| Sonnet 5.5 | $0.00031 | $0.00343 |
| Haiku 4.5 | $0.00016 | $0.00172 |
Grade A, and why
skill-to-sdk 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 6d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill to SDK
Convert an Anthropic Agent Skill into a self-contained Python program that
loads the skill's instructions as a system prompt and runs them against the
Claude API. The output is a small command-line app the user runs with
python app.py "their question" (or interactively) that prints the answer to
the console.
Why this exists
A skill normally lives inside Claude Code / Claude.ai and triggers when its description matches. People often want to take a finished skill and run it as an ordinary program — to share it, schedule it, embed it, or call it from other code. This skill produces that program. The skill's instruction body becomes the system prompt; the user's question becomes the user message; the model's reply is printed to the console.
The wrapper is deliberately simple: one API call per turn, text in and text
out, no tools. That is exactly what an instruction-only skill needs — a skill
that just tells the model how to think, reason, format, or respond reproduces
faithfully this way (e.g. market-sizing, okr-writer, exec-summary).
Input: two cases
The user will either hand you a SKILL.md or just describe a skill. Detect which and proceed accordingly.
-
They provide a SKILL.md (a file, a path, or pasted text): use it directly. Strip the YAML frontmatter — only the markdown body becomes the system prompt. Keep the
namefrom the frontmatter to name the output folder and files. -
They only give a name or description (e.g. "a skill that summarizes legal contracts"): first write a short, well-formed SKILL.md for it yourself — frontmatter with
nameanddescription, then a clear instruction body in the imperative voice describing how the assistant should behave. Show it to the user briefly, then wrap it. Keep it focused; a single-purpose instruction set is better than a sprawling one.
If anything essential is ambiguous (what the skill should actually do, what its name is), ask one concise question before generating. Otherwise proceed.
What ships with it
4 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.
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.
- 6d ago First seen · 137 lines · 157 tokens per session scan A d64bdb2af937
skill-to-sdk is a skill published in the GitHub repository hamzafarooq/claude-code-starter (145 stars, last pushed 7d ago), licensed MIT. It adds 157 tokens to every session and 1,716 once invoked, about $0.0006 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 2026-10-12.
Other skills, from other repositories
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.
python
Python development with ruff, mypy, pytest - TDD and type safety.