Borrowing it
Nothing to install: this file belongs to kimrejstrom/alpacalyzer-algo-trader. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kimrejstrom/alpacalyzer-algo-trader/main/.agents/skills/gpt-integration/SKILL.mdgit clone --depth 1 https://github.com/kimrejstrom/alpacalyzer-algo-traderWrote 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/kimrejstrom/alpacalyzer-algo-trader/gpt-integration)<a href="https://agentmods.dev/skills/kimrejstrom/alpacalyzer-algo-trader/gpt-integration"><img src="https://agentmods.dev/badge/skills/kimrejstrom/alpacalyzer-algo-trader/gpt-integration/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/kimrejstrom/alpacalyzer-algo-trader/gpt-integration"><img src="https://agentmods.dev/badge/skills/kimrejstrom/alpacalyzer-algo-trader/gpt-integration.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 | $0.00032 | $0.01156 |
| Opus 5 | $0.00016 | $0.00578 |
| Sonnet 5 | $0.00006 | $0.00231 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
gpt-integration 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 11d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Constraint
- LLM abstraction layer:
src/alpacalyzer/llm/(primary — use this) - Agent prompts:
src/alpacalyzer/prompts/(Markdown files) and inline in agent files - Legacy GPT calls:
src/alpacalyzer/gpt/call_gpt.py(deprecated — do not use for new code) - Tests must mock the LLM client (auto-mocked via
conftest.py)
Steps
1. Study the LLM integration
Read these files:
src/alpacalyzer/llm/client.py—LLMClientclass (OpenAI-compatible, supports OpenRouter)src/alpacalyzer/llm/config.py—LLMTierenum (FAST/STANDARD/DEEP) and model mappingsrc/alpacalyzer/llm/structured.py—instructor-based structured output with automatic retry-with-validation-feedback and manual fallbacksrc/alpacalyzer/agents/warren_buffet_agent.py— example agent using LLMsrc/alpacalyzer/prompts/— prompt templates (Markdown)tests/conftest.py— auto-mocking setup
Key patterns: agents define a system prompt (investment philosophy), call LLMClient.complete_structured() with a Pydantic response model and an LLMTier, and return results that update LangGraph state. Every call emits an LLMCallEvent for observability.
Structured output pipeline
complete_structured() uses a three-layer approach:
- instructor (
Mode.JSON,max_retries=2) — wraps the OpenAI client, validates the response against the Pydantic model, and if validation fails, feeds the error back to the LLM and retries automatically. - Manual fallback — if instructor exhausts retries, falls back to raw
json_objectmode with schema injected as a system message, plus coercion helpers (_coerce_dict_lists,_strip_code_fences). - Model-level hardening — Pydantic models themselves have
field_validators that tolerate common LLM mistakes (e.g.risk_reward_ratio: "1:1.47"→1.47,entry_criteriaas string → list). This means most LLM output parses on the first try without needing retries.
2. Modify or create prompts
System prompts should have: clear identity, investment philosophy/principles, analysis framework, and output expectations. Keep prompts concise — token limits vary by model tier.
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.
- 11d ago First seen · 88 lines · 32 tokens per session scan A dbbf8c5d51c1
gpt-integration is a skill published in the GitHub repository kimrejstrom/alpacalyzer-algo-trader (2 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 1,156 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…