alpacalyzer-algo-trader: Skill for Claude Code

.agents/skills/gpt-integration/SKILL.md

gpt-integration is a skill for Claude Code, Codex from kimrejstrom/alpacalyzer-algo-trader. It costs 32 tokens per session (1,156 once invoked), scanned A, original, MIT.

Development guidance for changing LLM calls, agent prompts, or structured output in a trading application. Structured output means asking a language model to return data in a defined format.

In plain words
What is it for?
Use it when editing model calls, prompts, response schemas, or related tests, including code that uses OpenRouter-compatible models.
Why use it?
It identifies the supported integration files and testing pattern, helping changes use the shared client instead of deprecated calls.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is kimrejstrom/alpacalyzer-algo-trader's own configuration. It tells Claude Code and Codex how to work on alpacalyzer-algo-trader itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything alpacalyzer-algo-trader configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/kimrejstrom/alpacalyzer-algo-trader/main/.agents/skills/gpt-integration/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kimrejstrom/alpacalyzer-algo-trader

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for gpt-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimrejstrom/alpacalyzer-algo-trader/gpt-integration/github.svg)](https://agentmods.dev/skills/kimrejstrom/alpacalyzer-algo-trader/gpt-integration)
Your own site
<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.

agentmods 80×15 button for gpt-integration

Your own site · 80×15
<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>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,156 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash dbbf8c5d51c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.agents/skills/gpt-integration/SKILL.md · 88 lines

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:

  1. src/alpacalyzer/llm/client.pyLLMClient class (OpenAI-compatible, supports OpenRouter)
  2. src/alpacalyzer/llm/config.pyLLMTier enum (FAST/STANDARD/DEEP) and model mapping
  3. src/alpacalyzer/llm/structured.pyinstructor-based structured output with automatic retry-with-validation-feedback and manual fallback
  4. src/alpacalyzer/agents/warren_buffet_agent.py — example agent using LLM
  5. src/alpacalyzer/prompts/ — prompt templates (Markdown)
  6. 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:

  1. 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.
  2. Manual fallback — if instructor exhausts retries, falls back to raw json_object mode with schema injected as a system message, plus coercion helpers (_coerce_dict_lists, _strip_code_fences).
  3. 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_criteria as 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.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 11d ago First seen · 88 lines · 32 tokens per session scan A dbbf8c5d51c1

Subscribe to this mod's changes

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.

Related

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.

davila7/claude-code-templates · 54 tokens

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…

langwatch/langwatch · 105 tokens

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.

google-labs-code/stitch-skills · 41 tokens

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…

Jeffallan/claude-skills · 93 tokens

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.

Emily2040/seedance-2.0 · 61 tokens

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…

digitalsamba/claude-code-video-toolkit · 99 tokens