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 agentmods add skills/nodnarbnitram/claude-code-extensions/ha-apinpx skills add nodnarbnitram/claude-code-extensions --skill ha-apigit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWhat 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 | $0.00062 | $0.05756 |
| Opus 5 | $0.00031 | $0.02878 |
| Sonnet 5 | $0.00012 | $0.01151 |
| Haiku 4.5 | $0.00006 | $0.00576 |
Grade A, and why
ha-api scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X GET "${HA_URL}/api/states" \ How it starts
The opening of the file, as written. The whole thing — 880 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Assistant API Integration
Master Home Assistant's REST and WebSocket APIs for external integration, state management, and real-time communication.
⚠️ BEFORE YOU START
This skill prevents 5 common API integration errors and saves ~30% token overhead.
| Aspect | Details |
|---|---|
| Common Errors Prevented | 5+ (auth, WebSocket lifecycle, state format, error handling) |
| Token Savings | ~30% vs. manual API discovery |
| Setup Time | 2-5 minutes vs. 15-20 minutes manual |
Known Issues This Skill Prevents
- Incorrect authentication headers - Bearer tokens must be prefixed with "Bearer " in Authorization header
- WebSocket lifecycle management - Missing auth_required handling or improper state subscription
- State format mismatches - Confusing state vs. attributes; incorrect JSON payload structure
- Error response handling - Not distinguishing between 4xx client errors and 5xx server errors
- Service call domain/service mismatch - Incorrect routing to service endpoints
Quick Start
Step 1: Authentication Setup
# In Home Assistant UI:
# Settings → My Home → Create Long-Lived Access Token
# Store token securely (never commit to git)
export HA_TOKEN="eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
export HA_URL="http://192.168.1.100:8123"
Why this matters: All API requests require Bearer token authentication. Creating a dedicated token for external apps allows you to revoke access without changing your password.
Step 2: Test REST API Connectivity
# Get all entity states
curl -X GET "${HA_URL}/api/states" \
-H "Authorization: Bearer ${HA_TOKEN}" \
-H "Content-Type: application/json"
Why this matters: Verifies your Home Assistant instance is accessible and your token is valid before building complex integrations.
Step 3: Choose API Type
- REST API: For one-time requests, state queries, service calls (HTTP polling)
- WebSocket API: For real-time events, continuous subscriptions, lower latency (~50ms vs. seconds)
What ships with it
1 file 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.
- 2d ago First seen · 880 lines · 62 tokens per session scan A 2deb0892389c
ha-api is a skill published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 5,756 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…