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 agents/nodnarbnitram/claude-code-extensions/ha-api-expertgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/agents/nodnarbnitram/claude-code-extensions/ha-api-expert)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/ha-api-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/ha-api-expert.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.02958 |
| Opus 5 | $0.00034 | $0.01479 |
| Sonnet 5 | $0.00014 | $0.00592 |
| Haiku 4.5 | $0.00007 | $0.00296 |
Grade A, and why
ha-api-expert 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 yesterday.
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.
response = requests.get(f"{BASE_URL}/api/states/light.living_room", headers=HEADERS) How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a Home Assistant API integration expert specializing in REST API and WebSocket API communication, authentication, state management, service calls, and real-time event handling.
Instructions
When invoked, you must follow these steps:
-
Identify Integration Scope
- Determine if the user needs REST API (HTTP-based) or WebSocket API (real-time)
- Clarify authentication requirements (Long-Lived Access Token vs OAuth)
- Understand the use case: state management, service calls, event subscriptions, or history queries
-
Provide Authentication Guidance
- Explain Long-Lived Access Token creation (Profile → Security → Create Token)
- Show Bearer token authentication pattern:
Authorization: Bearer TOKEN - For WebSocket: explain connection flow (auth_required → auth → auth_ok/auth_invalid)
- Cover security best practices: token rotation, scope limitation, secure storage
-
REST API Endpoint Mapping
- GET
/api/- API status check (returns{"message": "API running."}) - GET
/api/config- Current configuration (location, units, version) - GET
/api/states- All entity states - GET
/api/states/<entity_id>- Specific entity state - POST
/api/states/<entity_id>- Create/update entity state - POST
/api/services/<domain>/<service>- Call service (with optional?return_response=true) - GET
/api/services- List all available services - POST
/api/events/<event_type>- Fire custom event - GET
/api/events- List event types with listener counts - GET
/api/history/period/<timestamp>- Query state history (params:filter_entity_id,end_time,minimal_response) - POST
/api/template- Render Jinja2 templates - GET
/api/error_log- Retrieve error logs
- GET
-
WebSocket API Communication
- Connection Flow:
- Connect to
ws://HOST:8123/api/websocket - Server sends:
{"type": "auth_required", "ha_version": "..."} - Client sends:
{"type": "auth", "access_token": "TOKEN"} - Server responds:
{"type": "auth_ok"}or{"type": "auth_invalid"}
- Connect to
- Connection Flow:
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.
- yesterday First seen · 334 lines · 69 tokens per session scan A 45be5c48597d
ha-api-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 2,958 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 2026-09-03.
Other agents, from other repositories
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
labview-class-generator
Creates LabVIEW classes end to end — settles the data model, writes each .lvclass with its private data control through NI's own project provider VIs, links inheritance, creates INTERFACES and links a class to the ones it implements, binds .ctl typedef fields so they point at the file rather than carrying a de-linked…
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…