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 commands/nodnarbnitram/claude-code-extensions/ha-blueprint-creategit 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 | $0.00009 | $0.01823 |
| Opus 5 | $0.00005 | $0.00911 |
| Sonnet 5 | $0.00002 | $0.00365 |
| Haiku 4.5 | $0.00001 | $0.00182 |
Grade A, and why
ha-blueprint-create 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 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.
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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Home Assistant Blueprint
Convert an existing Home Assistant automation into a reusable blueprint: $ARGUMENTS
Your Task
Transform the specified automation into a parameterizable blueprint by analyzing its structure and identifying which values should become inputs with appropriate selectors.
Step 1: Analyze the Automation
Location: The argument can be:
- An automation file path (e.g.,
/path/to/automation.yaml) - An automation ID from
automations.yaml(we'll help you locate it) - A direct YAML automation configuration
Analysis checklist:
-
Identify all hardcoded values (entity IDs, timeouts, thresholds, scenes, etc.)
-
Determine which values should be parameterized (user-configurable inputs)
-
Recognize selector types appropriate for each input:
entity: Single entity ID (default device/area/domain filtering)device: Device selection with driver supportarea: Home Assistant area selectionnumber: Numeric input with min/max/unit_of_measurementtext: Free-form text input (domain, name, label)boolean: True/false toggleselect: Predefined list of optionsobject: Complex structured datatemplate: Jinja2 template as input
-
Document automation structure:
- Trigger type(s) (state, numeric_state, time, time_pattern, sun, event, mqtt, device, etc.)
- Condition(s) if present (state, numeric_state, time, template, etc.)
- Action(s) (service call, script, automation trigger, etc.)
- Mode (single, restart, queued, parallel)
Step 2: Design Blueprint Schema
Create the blueprint's input section with appropriate selector types:
Principles:
- Use most specific selector (entity > object)
- Entity inputs should filter by domain when possible (light:, climate:, etc.)
- Numeric inputs should include min, max, step, unit_of_measurement
- Text inputs should have maxlength and placeholder hints
- Boolean inputs should have clear icon/description labels
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 · 267 lines · 9 tokens per session scan A ce32df4489df
ha-blueprint-create is a command published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 1,823 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
observe
部屋を能動的に観察する。3つの基本ブロックを自由に選びながらループし、受動的なスナップショットではなく発見のある観察を行う。.
model
Check if an AI model fits on your GPU before downloading.
tapeout
Produce a complete, fab-ready export bundle for a routed board — or refuse loudly. Superset of /kct:manufacturing-readiness: runs the three sign-off pre-gates, then adds a BOM part-number-resolution gate, a per-rule warning-review gate (assembly-affecting warnings block unless explicitly acknowledged), schematic +…
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
rvcsi-calibrate
Learn a v0 per-subcarrier baseline (mean amplitude) from a .rvcsi capture.
iot
This API allows you to manage your IoT hubs and devices.