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 HybridAIOne/hybridclaw --skill huegit clone --depth 1 https://github.com/HybridAIOne/hybridclawWrote 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/hybridaione/hybridclaw/hue)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/hue"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/hue/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/hybridaione/hybridclaw/hue"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/hue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 37 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 38 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00032 | $0.04416 |
| Opus 5 | $0.00016 | $0.02208 |
| Sonnet 5 | $0.00006 | $0.00883 |
| Haiku 4.5 | $0.00003 | $0.00442 |
Grade A, and why
hue 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Philips Hue
Use this skill for Philips Hue Bridge lighting inspection and guarded control. The primary path is local HTTPS to the Hue Bridge CLIP v2 API. Use the Hue Remote API only when the operator explicitly needs off-LAN control or local bridge access is unavailable.
Safety Rules
- Use
skills/hue/hue.cjsfor every supported Hue request shape. Do not handcraft CLIP v2 URLs or JSON bodies when the helper supports the action. - Read current light, room, zone, and scene state before changing lights.
- Treat local reads as green, local light/group/scene/behavior changes as amber, off-LAN Remote API calls as amber, and bridge configuration writes as red.
- For amber/red operations, use the helper to build the request shape, explain
the target and expected effect, and stop for explicit operator approval
before sending the emitted
httpRequestthrough the gateway. - Include the target light, grouped light, room, scene, behavior, bridge id, action, and expected physical effect in approval text.
- Never paste the Hue application key, OAuth client secret, or remote token
into chat. The helper emits
secretHeadersor<secret:...>placeholders for gateway-side resolution. - Hue Bridge certificates are self-signed by default. The helper marks local
bridge HTTPS requests with a scoped
allowSelfSignedTlsflag for the gatewayhttp_requestproxy. Do not use a blanket insecure TLS bypass. - If a live call returns
401orunauthorized_user, stop after that first failed call and re-link the bridge with the link-button flow. - In chat sessions, do not diagnose Hue runtime config by running
hybridclaw env list,hybridclaw secret list, or other local CLI commands frombash; those commands can inspect the wrong runtime or fail because of the host Node version. Use gatewayhttp_requesterrors and any/env showor/secret listoutput the operator provides. - If
HUE_BRIDGE_HOSTis configured andHUE_APPLICATION_KEYis missing, say only that the application key is missing. Do not ask the operator to find the bridge IP again. Ask them to press the physical link button, then buildnode skills/hue/hue.cjs --format json bridge link --app-name hybridclaw --instance-name lab, send the emittedhttpRequest, and store the returned Hue credential secret through the helper-emittedcaptureResponseFields. - When linking after the operator presses the bridge button, run
bridge statusfirst. If the live status result reportslinkbutton: true, immediately runbridge linkwithout--host. If it reportslinkbutton: false, tell the operator that the configured bridge did not report an active button press and ask them to press and release the physical link button once, then retry immediately. Iflinkbuttonis absent, do not treat that as proof the button is inactive; modern bridge config responses can omit the field. - When running the link request itself, do not pass
--hostunless the operator explicitly provides a new override URL in the same turn. The default link request must use<env:HUE_BRIDGE_HOST>so the gateway resolves the env-store value. - If the operator shows
/env show HUE_BRIDGE_HOST, treat that value as the current configured bridge URL. If a failed request used any other host, report that the helper was called with the wrong host and retry the same operation with no--hostoverride. - If
HUE_BRIDGE_HOSTis missing, first reuse an exact Hue Bridge URL from current context or workspace memory when one is present. Ask the operator to find the bridge IP only when no exact URL is available. - If a gateway
http_requesterror saysStored secret HUE_APPLICATION_KEY is not set, treatHUE_BRIDGE_HOSTas already resolved for that request. Do not say the bridge host may be missing, do not tell the operator to runhybridclaw env set, and do not repeat the same read calls. Switch directly to the link-button setup path in rule 10. - If a private-host or gateway policy denial blocks a local bridge request, first inspect the current workspace network policy. Managed read-only LAN access already allows GET reads to RFC1918 hosts, and managed read-write LAN access allows the supported methods. If either managed LAN mode covers the attempted Hue request, report that mismatch as a gateway policy-evaluation bug instead of adding another rule. Do not edit policy by hand, do not add broad bridge rules, and do not tell the operator a gateway restart is required; workspace network policy is read per request.
- If a local Hue request fails with a certificate verification or
self-signed TLS error, do not ask for
HUE_BRIDGE_HOSTagain, do not suggest plain HTTP on port 80, and do not invent a URL auth route or workspace policy setting for TLS. Re-run the exact helper-emittedhttpRequestwithallowSelfSignedTls: true; if that field is absent, rebuild the request withskills/hue/hue.cjs.
What ships with it
1 file 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.
- 11d ago First seen · 383 lines · 32 tokens per session scan A b99dca9a383a
hue is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 4,416 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 2026-08-30.
Other skills, from other repositories
ai-sdk
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…
scope-creep-detector
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too…
status
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…