api-integration

api-integration is a skill for Claude Code, Codex from lantisprime/claude-sdlc. It costs 218 tokens per session (1,271 once invoked), scanned A, original, MIT.

A review step for software that connects to another service through an API, which is the agreed format for sending and receiving data. It checks that a real API description exists and that the endpoint can be reached.

In plain words
What is it for?
Use it while designing or building HTTP, SDK, gRPC, webhook, GraphQL, or event-based integrations. It can check the API contract, test the endpoint, and offer a mock when the endpoint is unavailable.
Why use it?
It helps catch integrations that only appear to work because they use silent test doubles instead of the real service. This reduces surprises when code reaches staging or production.

Skill for Claude CodeCodex

Part of the sdlc-plugin plugin — 19 skills, 16 commands, 10 agents, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/lantisprime/claude-sdlc/api-integration
Any agent
npx skills add lantisprime/claude-sdlc --skill api-integration
Clone the repo
git clone --depth 1 https://github.com/lantisprime/claude-sdlc

Made for: Claude Code, Codex.

Or install sdlc-plugin, the plugin that ships this one along with the rest of its 19 skills, 16 commands, 10 agents, 4 hooks.

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 api-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/api-integration.svg)](https://agentmods.dev/skills/lantisprime/claude-sdlc/api-integration)
Your own site
<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/api-integration"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/api-integration.svg" alt="Measured on agentmods" height="20"></a>
Per session 218 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,271 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00218 $0.01271
Opus 5 $0.00109 $0.00635
Sonnet 5 $0.00044 $0.00254
Haiku 4.5 $0.00022 $0.00127

Measured 3d ago against content hash 3612d0de3529, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-integration scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Probe the endpoint in the current environment using the tool configured in `config/tools.json` (curl, the SDK's health call, or a project-specific probe). Suitable probes:
skills/api-integration/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API Integration

Confirm the integration contract is real and reachable before code depends on it. Silent stubs are the failure mode this skill prevents — code that "works" locally and surprises in staging/prod because the real endpoint was never exercised.

When this skill runs

  • Design phase — when the tech spec describes an API boundary. Confirms a spec exists (or needs to be written) and is referenced.
  • Build phase — when in-scope files include integration code. Probes the endpoint; offers a mock if unreachable.

This is a warn + offer skill. It does not block. The human decides whether to proceed with a mock, a real endpoint, or to pause the build to fix the integration environment.

The two checks

1. Spec check

Look for an API contract artifact in the repo (or referenced by URL in the design):

  • OpenAPI / Swagger (openapi.yaml, swagger.json)
  • GraphQL schema (schema.graphql, introspection output)
  • Protobuf (*.proto)
  • AsyncAPI / JSON Schema / Avro for event contracts
  • A published SDK with typed clients

If no spec is found and the plan doesn't explicitly justify its absence:

⚠️ No API spec found for the integration with <service>. Options:

  1. Point me at an existing spec (path or URL) and I'll wire types from it
  2. I can draft an OpenAPI/GraphQL/Proto stub for the endpoints this task needs — you review before code depends on it
  3. Proceed without a spec (not recommended — types will be hand-written and drift is likely). Document the choice in the design.

Which would you like?

Wait for the human's decision. Do not write integration code in the meantime.

2. Reachability check

Probe the endpoint in the current environment using the tool configured in config/tools.json (curl, the SDK's health call, or a project-specific probe). Suitable probes:

  • GET /health, /status, /.well-known/... if the spec advertises one
  • An introspection query for GraphQL
  • A listed-allowed read endpoint with no side effects

Read the full file on GitHub · 85 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. 3d ago First seen · 85 lines · 218 tokens per session scan A 3612d0de3529

Subscribe to this mod's changes

api-integration is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 218 tokens to every session and 1,271 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

LQF_Machine_Learning_Expert_Guide

LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…

foryourhealth111-pixel/Vibe-Skills · 152 tokens

clinpgx-database

Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.

foryourhealth111-pixel/Vibe-Skills · 45 tokens

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

foryourhealth111-pixel/Vibe-Skills · 37 tokens

alpha-vantage

Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market…

foryourhealth111-pixel/Vibe-Skills · 126 tokens

datavis

Comprehensive data visualization toolkit for creating beautiful, mathematically elegant visualizations with D3.js, Chart.js, and custom SVG. Use when (1) building interactive data visualizations, (2) designing color palettes for charts, (3) choosing scales and visual encodings, (4) creating data pipelines from…

foryourhealth111-pixel/Vibe-Skills · 106 tokens

detecting-data-anomalies

Investigate outliers, rare events, spikes, and suspicious records in datasets. Use as an explicit anomaly-analysis helper when you want concrete anomaly-detection workflow guidance, not generic data validation or end-to-end ML ownership.

foryourhealth111-pixel/Vibe-Skills · 51 tokens