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 instructions/hallyaus/ovo_aus_api/agents-mdgit clone --depth 1 https://github.com/HallyAus/OVO_Aus_apiWrote 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/instructions/hallyaus/ovo_aus_api/agents-md)<a href="https://agentmods.dev/instructions/hallyaus/ovo_aus_api/agents-md"><img src="https://agentmods.dev/badge/instructions/hallyaus/ovo_aus_api/agents-md.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 5.1 | $0.02256 | $0.02256 |
| Opus 5 | $0.01128 | $0.01128 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00226 | $0.00226 |
Grade A, and why
OVO_Aus_api AGENTS.md 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OVO Energy Australia (HA integration) — agent brief
Home Assistant custom integration that pulls OVO Energy Australia usage/billing/EV data via
OVO's GraphQL API and exposes it as sensors. Installed by real strangers through HACS.
Status: live — public repo HallyAus/OVO_Aus_api, latest release v4.9.0 (2026-08-27) · verified 2026-08-27
What a mistake costs
Every release lands in strangers' Home Assistant installs. A bad one breaks their dashboards, their Energy Dashboard history, or their login — and they cannot roll back easily. The integration handles a cleartext MyOVO password and account PII (NMI, address, account ID, VIN, GPS). Leaking any of it into logs, entity attributes, or diagnostics is the worst outcome here; Recorder persists attributes to disk forever. Renaming or deleting an entity silently breaks user dashboards and long-term statistics. Referral income is the only funding, so repo reputation matters.
Stack
- Python 3.11+,
aiohttp+PyJWTonly.PyJWT>=2.13,<3is pinned — 3.x breaks the API surface. - Home Assistant 2026.8.3 minimum. A 2026.6.2 Container installation could not resolve the pinned PyJWT requirement; upgrading to 2026.8.3 fixed setup (#81).
- Auth is Auth0 OAuth2 + PKCE scraping the HTML login form, not a public API. See archived notes for the 6-step flow.
- EV data comes from a separate Kaluza/Firebase token chain, account-scoped — NOT the MyOVO access token.
- Tests mock the entire
homeassistantpackage intests/conftest.py. HA is not installed;pip install homeassistantis unnecessary. ruff(line-length 120, E501 ignored) +mypy+pre-commitwithdetect-secrets.- Distribution is HACS, which installs from the latest GitHub release tag — never from
main.
Run it
python -m pytest tests/ -q # 169 tests, no HA needed
python -m pytest tests/test_analytics.py -v -k name
ruff check custom_components/ovo_energy_au/
mypy custom_components/ovo_energy_au/
pre-commit run --all-files
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 Changed · +10 lines · +126 tokens per session 74d2d58012dd
- 5d ago First seen · 113 lines · 2,130 tokens per session scan A fab05f78b2cf
OVO_Aus_api AGENTS.md is an instructions file published in the GitHub repository HallyAus/OVO_Aus_api (23 stars, last pushed today), licensed MIT. It adds 2,256 tokens to every session, about $0.0113 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 instructions, from other repositories
ha-mcp AGENTS.md
AGENTS.md instructions for homeassistant-ai/ha-mcp, covering agents.md, instruction structure, repository structure, worktree workflow and project overview.
ha-selora-ai CLAUDE.md
Claude Code instructions for SeloraHomes/ha-selora-ai, covering selora ai — home assistant integration, what this is, architecture, project structure and key conventions.
ecowitt_local CLAUDE.md
Claude Code instructions for alexlenk/ecowitt_local, covering claude.md, project overview, ⚠️ critical: entity creation pipeline issues, development commands and local environment.
hacs.integration_blueprint AGENTS.md
Instructions for jpawlowski/hacs.integration_blueprint, covering ai agent instructions, which repository is this?, project overview, where the rules live and routing table.
hass-mcp-server AGENTS.md
AGENTS.md instructions for ganhammar/hass-mcp-server, covering working on this integration, calling into home assistant, before replacing a private call with a service, anything left in category 2 or 3 and conventions.
haggle AGENTS.md
AGENTS.md instructions for NaanyaBiz/haggle, covering agents.md — haggle integration guide, dev loop, install deps (once, or after pyproject.toml changes), run tests and lint + format.