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 skills add nolte/claude-home-assistant --skill ha-config-flow-augmentgit clone --depth 1 https://github.com/nolte/claude-home-assistantWrote 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/skills/nolte/claude-home-assistant/ha-config-flow-augment)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-config-flow-augment"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-config-flow-augment/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.
<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-config-flow-augment"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-config-flow-augment.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00145 | $0.02162 |
| Opus 5 | $0.00072 | $0.01081 |
| Sonnet 5 | $0.00029 | $0.00432 |
| Haiku 4.5 | $0.00015 | $0.00216 |
Grade A, and why
ha-config-flow-augment 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Config Flow Augment
Spec: spec/claude/ha-config-flow-augment/en.md (EN canonical) / spec/claude/ha-config-flow-augment/de.md (DE translation).
Why this is a skill, not an agent
- Mid-flow approval is the contract (decisive): augmenting a live config flow edits an existing integration; the pattern choice and the plan are confirmed with the operator before any write, and follow-up corrections continue in the same thread.
- Context access: which integration, which flow pattern, and which existing conventions apply comes from the open conversation and repo state, not from a self-contained input.
- Counter-dimension considered: applying one known pattern is a well-defined unit (agent bias), but losing the approval gate in a fire-and-forget agent would let structural flow changes land unreviewed — interactivity outweighs.
When this skill activates
Use this skill when the user wants to:
- retrofit a tenant / account selection step after the auth step
- retrofit zeroconf discovery into a config flow that did not initially carry it
- retrofit a reauth flow
- retrofit a reconfigure flow
- add OAuth as a parallel auth path next to the existing API-key path
When NOT to activate
- greenfield integration scaffolding →
ha-integration-scaffold - pure schema edits (rename a field, change a default) → manual code edit
- destructive refactors (remove a step, rewrite a step) → manual code edit with explicit user approval
- schema migration of
entry.dataacross versions →ha-config-entry-migrate - DHCP/SSDP/USB/HomeKit/MQTT discovery (any transport other than Zeroconf) →
ha-discovery-augment; this skill'szeroconfpattern owns only the mDNS/Zeroconf retrofit
Hard rules
- Never overwrite existing flow steps. Augment is additive. If the requested pattern already exists in
config_flow.py, abort with "pattern already present". - Never touch unrelated modules. Allowed targets:
config_flow.py,strings.json,translations/<lang>.json,tests/test_config_flow.py, and (for zeroconf)manifest.json. Theoauthpattern additionally writes a registration block in__init__.py, addsapplication_credentialstomanifest.json:dependencies, and scaffoldsapplication_credentials.py(async_get_authorization_server) — modern HA OAuth is Application-Credentials-based. - Never split the augment. Code, strings, translations, manifest entry (where applicable), and tests land together in a single commit-ready state. Half augments where code exists but strings are missing are forbidden.
- Never invent backend specifics. For
oauth, the skill scaffolds the flow skeleton — token endpoint, authorize endpoint, scopes, client ID/secret stay user-fed. Surface them in the output as an explicit checklist. - Always state the quality-scale impact. The output names which Quality Scale tier the augment unlocks (Bronze → Silver for reauth, Silver → Gold for reconfigure, …).
- Verify HA internals against the official docs. Don't reproduce HA API signatures, lifecycle hooks, conventions, or schemas from memory — when uncertain, consult the official docs before generating or relying on it: Developer docs
developers.home-assistant, architecture/blueprint/YAML docshome-assistant.io(seespec/ha/upstream-docs-verification/en.md).
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.
- 11d ago First seen · 135 lines · 145 tokens per session scan A c6d417ce442a
ha-config-flow-augment is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 2,162 once invoked, about $0.0007 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.
Other skills, from other repositories
embedded-iot
Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…