github-workflow

Read this document before triaging issues, changing GitHub automation, managing a pull request, or preparing a release. Repository-wide behavioral rules remain in AGENTS.md; this file owns the detailed commands, labels, bot behavior, and workflow inventory.

Agent

▶ Home Assistant MCP: One Server for Claude, Codex, and Gemini CLI Josh Uses Ai · about homeassistant-ai/ha-mcp · on YouTube →
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 agents/homeassistant-ai/ha-mcp/github-workflow
Clone the repo
git clone --depth 1 https://github.com/homeassistant-ai/ha-mcp
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.02504
Opus 5 $0.00000 $0.01252
Sonnet 5 $0.00000 $0.00501
Haiku 4.5 $0.00000 $0.00250

Measured today against content hash bc47c80ea34f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-workflow 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 today.

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.

docs/agents/github-workflow.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub workflow reference

Read this document before triaging issues, changing GitHub automation, managing a pull request, or preparing a release. Repository-wide behavioral rules remain in AGENTS.md; this file owns the detailed commands, labels, bot behavior, and workflow inventory.

Automated review

Codex reviews pull requests through pr-codex-review-request.yml and pr-codex-review-delivery.yml, posting as chatgpt-codex-connector[bot]. The request explicitly applies .gemini/styleguide.md. Gemini Code Assist is retired; .gemini/config.yaml disables the app, but the style guide remains the repository's code-review criteria.

CodeRabbit reviews drafts. .coderabbit.yaml deliberately sets:

  • reviews.auto_review.drafts: true
  • auto_pause_after_reviewed_commits: 0 (the schema default pauses after five reviewed commits)
  • reviews.pre_merge_checks.docstrings.mode: "off" (the default 80% repository-wide coverage quota is disabled; ordinary guideline-based docstring review remains enabled)

The second setting spends the per-developer hourly review allowance faster. A rate-limited push reports that state in a comment and does not block merging; @coderabbitai rate limit reports availability without requesting a review. CodeRabbit auto-detects AGENTS.md; the style guide is added through knowledge_base.code_guidelines.filePatterns.

Repository YAML outranks CodeRabbit UI settings and does not merge with them. Omitted keys use schema defaults. On public repositories, a change to .coderabbit.yaml does not govern its own pull request because CodeRabbit uses the base branch configuration. The tell on the pull request changing the file is Configuration used: defaults; the new rules take effect only after merge.

Dependabot, Renovate, and github-actions[bot] webhook-proxy promotion pull requests are excluded from automatic Codex and CodeRabbit review. Their exact lists are kept in lockstep by test_coderabbit_config.py. A maintainer can still request review on a promotion pull request with @coderabbitai review, or request Codex with a comment that is exactly /review or @ghhamcp review. .coderabbit.yaml's ignore_usernames and the pull_request_target admission list enforce the exclusion. The issue_comment admission list deliberately omits github-actions[bot], so a maintainer's exact manual-review command remains the only way to admit a promotion pull request.

Read the full file on GitHub · 224 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. today First seen · 224 lines · 0 tokens per session scan A bc47c80ea34f

Subscribe to this mod's changes

github-workflow is an agent published in the GitHub repository homeassistant-ai/ha-mcp (4,594 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,504 tokens. 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 2026-09-02.

Related

Other agents, from other repositories

raise-pull-request

Use this agent when creating a pull request for the Home Assistant core repository after completing implementation work. This agent automates the PR creation process including running tests, formatting checks, and proper checkbox handling.

home-assistant/core · 44 tokens

blocky-bump-review

The concrete definition of what CLAUDE.md calls the manual review a Blocky bump requires. Renovate opens these as a one-line change to BLOCKYVERSION in blocky/Dockerfile (Tempio bumps are the same shape via TEMPIOVERSION). Most bumps merge as that bare one-liner — this runbook is how you earn that conclusion instead…

robocopklaus/hassio-addon-blocky · 0 tokens

ha-esphome-config-reviewer

Produces one bundled, read-only device-level review of an ESPHome device configuration: config-pattern conformance, credential and API/OTA hardening, schema currency against the official ESPHome docs, Home-Assistant-driven binding correctness, display rendering discipline, display design conformance (palette roles…

nolte/claude-home-assistant · 223 tokens

ha-integration-reviewer

Produces one bundled, read-only integration-review report for a Home Assistant Custom Integration: quality-scale tier assessment, security/hardening review, and cross-cutting consistency checks (manifest-tier coherence, translations, diagnostics redaction, device classes, spec drift, upstream-docs spot-check).…

nolte/claude-home-assistant · 213 tokens

ha-dev-instance-provisioner

Provisions a disposable development Home Assistant instance into a local Kubernetes cluster (typically Kind) by applying a self-generated StatefulSet + Service + /config PVC manifest, waiting for rollout, and preparing /config/customcomponents — so that ha-integration-deployer can then copy an integration into it.…

nolte/claude-home-assistant · 216 tokens

ha-integration-verifier

Diagnoses a deployed Home Assistant Custom Integration in a running HA pod inside a Kind / local Kubernetes cluster — pod-status check, recent-log scan with error-pattern detection, installed-files verification — and return a structured health report. Read-only: never deploys, never restarts, never modifies state. Use…

nolte/claude-home-assistant · 179 tokens