API VS Selfhost Skill — AI skill for Claude Code
Anthropic-standard Skill — decide API-vs-self-host LLM costs and fine-tune ROI from any agent context (Claude Code, Cursor, Codex).
How to install API VS Selfhost Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open artvandelay/api-vs-selfhost-skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What API VS Selfhost Skill does
Anthropic-standard Skill — decide API-vs-self-host LLM costs and fine-tune ROI from any agent context (Claude Code, Cursor, Codex). Live GPU+API prices, deterministic local math.
Alternatives in AI
- Fine Tuning — ai-research-skills Axolotl, LLaMA-Factory, PEFT, Unsloth 5.4k ★
- Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
- Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
README
api-vs-selfhost-skill
Decide API-vs-self-host LLM economics and fine-tuning ROI from inside Claude Code, Cursor, Codex, or any agent harness with a shell + a web-fetch tool.
[](https://github.com/artvandelay/api-vs-selfhost-skill/actions/workflows/test.yml) [](LICENSE) [](#requirements) [](https://agentskills.io/) [](https://github.com/artvandelay/api-vs-selfhost-skill/stargazers)
**Works with** [](https://docs.claude.com/en/docs/claude-code/skills) [](https://cursor.com/docs/skills) [](https://developers.openai.com/codex/concepts/customization) [](https://github.com/google-gemini/gemini-cli) [](https://antigravity.dev/)
The agent reads your code, PRDs, or billing screenshots; fetches live GPU and API prices; runs deterministic VRAM and dollar math via `scripts/calc.py`; and writes a short markdown report with cited sources.
Not in an agent? **[Use the web calculator →](https://artvandelay.github.io/should-i-self-host-llm/)**
Install
A skill is just a folder with a `SKILL.md`, placed where your agent looks for skills. Install = clone this repo into that folder. Requires **Python 3.10+** (standard library only —
Related Skills
Evolve Skill
SPIKE — GEPA/DSPy-style offline A/B evolution of ONE prompt-only skill's SKILL.md body against a small fixture
OmniGlyph
Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-
TurboLLM
Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Cl
Byokey
Turn AI subscriptions into standard API endpoints. OpenAI & Anthropic compatible gateway — for Amp Code, Curso
Nudge
Manage AI agent fleets (Codex, Claude Code, Gemini) running in tmux. Dashboard over monitored sessions, add/pa
Gestao De Projetos PM IA BSC DashBoard
🧭 Stop paying for AI in the dark. Turn ChatGPT/Claude/Copilot spend into auditable ROI: LLM observability → 7
Related Agents
Aiml Engineer
AI/ML integration specialist. Designs model pipelines (inference, fine-tuning, LoRA adapters), selects infrast
Sdl Game Helper
SDL2/SDL1 game port specialist for AmigaOS. Knows the libSDL2-amigaos3 fast-path traps, blitter mode tradeoffs
Price Comparison
Compares prices across vendors and markets, calculates markups, and factors in import costs (shipping, VAT, cu