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 l3wi/homekit-cli --skill homekitgit clone --depth 1 https://github.com/l3wi/homekit-cliWrote 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/l3wi/homekit-cli/homekit)<a href="https://agentmods.dev/skills/l3wi/homekit-cli/homekit"><img src="https://agentmods.dev/badge/skills/l3wi/homekit-cli/homekit/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/l3wi/homekit-cli/homekit"><img src="https://agentmods.dev/badge/skills/l3wi/homekit-cli/homekit.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 | $0.00078 | $0.00992 |
| Opus 5.5 | $0.00031 | $0.00397 |
| Sonnet 5.5 | $0.00016 | $0.00198 |
| Haiku 4.5 | $0.00008 | $0.00099 |
Grade A, and why
homekit 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 2mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HomeKit
Use homekit as the only HomeKit interface unless the user explicitly asks to leave this CLI. Start read-only, identify exact targets, then write only when the user has asked for the specific physical or structural change.
Progressive Disclosure
Do not memorize or duplicate the command schema. Ask the CLI for the level of detail you need:
homekit --help
homekit <group> --help
homekit <command> --schema --format json
homekit --llms
Use --format json for evidence you will parse or compare. Use --schema --format json before MCP/tool calls when argument names, output fields, or safety flags are uncertain.
Load References
Load only the reference that matches the user request:
references/setup-and-troubleshooting.md: HomeClaw setup, readiness, HomeKit permission, logs, MCP install.references/inspection-workflows.md: homes, rooms, accessories, scenes, automations, zones, event logs, device-map, and anomaly investigation.references/write-workflows.md: accessory control, room/zone/scene/automation mutations, exact-id writes, verification, and audit reporting.references/command-groups.md: concise command group map and implementation caveats.
Use scripts/homekit-readiness.sh when you need a deterministic local setup/readiness check.
Operating Rules
- Treat locks, garage doors, gates, doors, windows, covers, security systems, cameras, doorbells, occupancy, presence, scenes, and automations as safety-critical.
- Never control a device just to test connectivity.
- Never use
--allow-actuationunless the user asked for the exact physical state change. - Never use
--allow-mutationunless the user asked for the exact HomeKit structural change. - Never wildcard writes. Resolve names to exact IDs first, then use those exact IDs.
- If multiple accessories, scenes, rooms, zones, or automations match, show candidates and ask the user to choose.
- After any accepted write, report the command family, target name/id, requested value/change, verification result, and returned
auditIdwhen present.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 95 lines · 78 tokens per session scan A c8059774b07e
homekit is a skill published in the GitHub repository l3wi/homekit-cli (0 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 992 once invoked, about $0.0003 per session on Opus 5.5. 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.
homekit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| homekitl3wi/homekit-cli | Skill | 0 | 4mo ago | MIT | A | 78 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| jetson-diagnosticNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |
| offensive-z-waveSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 113 | Claude Code, Codex |
| doca-socket-relayNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 236 | Claude Code, Codex |
| hsb-flashNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | B | 94 | Claude Code |