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/home-assistant/core/raise-pull-requestgit clone --depth 1 https://github.com/home-assistant/coreWhat 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 | $0.00044 | $0.02477 |
| Opus 5 | $0.00022 | $0.01239 |
| Sonnet 5 | $0.00009 | $0.00495 |
| Haiku 4.5 | $0.00004 | $0.00248 |
Grade A, and why
raise-pull-request scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert at creating pull requests for the Home Assistant core repository. You will automate the PR creation process with proper verification, formatting, testing, and checkbox handling.
Execute each step in order. Do not skip steps.
Step 1: Gather Information
Run these commands in parallel to analyze the changes:
# Get current branch and remote
git branch --show-current
git remote -v | grep push
# Determine the best available dev reference
if git rev-parse --verify --quiet upstream/dev >/dev/null; then
BASE_REF="upstream/dev"
elif git rev-parse --verify --quiet origin/dev >/dev/null; then
BASE_REF="origin/dev"
elif git rev-parse --verify --quiet dev >/dev/null; then
BASE_REF="dev"
else
echo "Could not find upstream/dev, origin/dev, or local dev"
exit 1
fi
BASE_SHA="$(git merge-base "$BASE_REF" HEAD)"
echo "BASE_REF=$BASE_REF"
echo "BASE_SHA=$BASE_SHA"
# Get commit info for this branch vs dev
git log "${BASE_SHA}..HEAD" --oneline
# Check what files changed
git diff "${BASE_SHA}..HEAD" --name-only
# Check if test files were added/modified
git diff "${BASE_SHA}..HEAD" --name-only | grep -E "^tests/.*\.py$" || echo "NO_TESTS_CHANGED"
# Check if manifest.json changed
git diff "${BASE_SHA}..HEAD" --name-only | grep "manifest.json" || echo "NO_MANIFEST_CHANGED"
From the file paths, extract the integration domain from homeassistant/components/{integration}/ or tests/components/{integration}/.
Track results:
BASE_REF: the dev reference used for comparisonBASE_SHA: the merge-base commit used for diff-based checksTESTS_CHANGED: true if test files were added or modifiedMANIFEST_CHANGED: true if manifest.json was modified
If no suitable dev reference is available, STOP and tell the user to fetch upstream/dev, origin/dev, or a local dev branch before continuing.
Step 2: Run Code Quality Checks
Run prek to perform code quality checks (formatting, linting, hassfest, etc.) on the files changed since BASE_SHA:
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.
- today First seen · 226 lines · 44 tokens per session scan A ea76b31c68ab
raise-pull-request is an agent published in the GitHub repository home-assistant/core (90,198 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 2,477 once invoked, about $0.0002 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 agents, from other repositories
strategic-advisor
Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.
fsl-vacuity-reviewer
Use PROACTIVELY after adding or changing a .fsl spec under specs/ or examples/. Uses the working-tree native Rust CLI to detect hollowing, weak mutation kill-rate, vacuous properties, and weakened invariants. Read-only on specs; may run verifier commands.
agent_class
The Agent class is the core orchestrator in AgentForge. It loads configuration, renders prompts, invokes the LLM, and produces final outputs. Agents can be subclassed for custom logic.
surfaces
A Surface is a reusable, org-scoped, named capability/permission profile that gets merged into an agent's runtime environment. It bundles together everything that shapes what an agent may do and know for a given piece of work.
Plan
Research and outline multi-step plans for zen analysis improvements.
gsc-content-optimizer
Finds content optimization targets across two zones, striking distance (positions 4-10) and page-two quick wins (positions 11-20). Use when asked for content ideas, quick wins, or optimization opportunities. Aussi déclenché en français par "quelles pages optimiser en priorité", "où je peux gagner vite", "mes pages en…