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 alexagit 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/alexa)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/alexa"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/alexa/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/alexa"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/alexa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 154 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 | $0.00027 | $0.05120 |
| Opus 5 | $0.00014 | $0.02560 |
| Sonnet 5 | $0.00005 | $0.01024 |
| Haiku 4.5 | $0.00003 | $0.00512 |
Grade A, and why
alexa 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 12d 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 — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alexa
Use this skill for Amazon Alexa workflows in two narrow modes:
- Expose HybridClaw as a custom Alexa skill through the Alexa Skills Kit (ASK).
- Prepare guarded Alexa-as-device reads and write plans for the official Smart
Home Skill API and the opt-in community Alexa Remote /
alexapysurface.
Do not use this skill for arbitrary Amazon API calls, shopping account access, or browser automation. Keep all credentials behind SecretRef and use the helper to build bounded payloads instead of hand-writing URLs, headers, cookies, or request bodies.
Safety Rules
- Validate every inbound ASK request before parsing slots or running an agent
bridge. Reject invalid
Signature, invalidSignatureCertChainUrl, signing certificates that do not coverecho-api.amazon.com, or timestamp drift of 150 seconds or more. - Never persist or echo Login with Amazon access tokens. The request token maps to a HybridClaw operator session outside the prompt through the F13 SecretRef rail.
- Model output sent back to Alexa must be TTS-safe. Use
build-responseso markdown, code blocks, and very long URLs are stripped before SSML is built. - Path-B reads are green but privacy-sensitive because devices, list contents, routines, and last-command history can reveal household behavior.
- Path-B writes are amber/red. Announcements, list mutations, device control, and routine triggers require exact F8/F14 approval that names the target room or device and the action.
- Stop after the first
401,403, orINVALID_AUTHORIZATION_CREDENTIALresponse. Emit or surfaceevent: alexa.relink_required; do not retry-loop. - The community cookie path is reverse-engineered and can break when Amazon changes web/API behavior. Treat it as opt-in and operationally brittle.
- Do not accept Amazon passwords, refresh cookies, LWA tokens, or Smart Home
tokens in chat or CLI flags. Store them with
hybridclaw secret set ....
Command Contract
Show helper usage:
What ships with it
2 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.
- 12d ago First seen · 540 lines · 27 tokens per session scan A ee2eca08858d
alexa is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 5,120 once invoked, about $0.0001 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
lilbee-mcp
Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…
lilbee-mcp-wiki
Wiki layer for lilbee. Use only when the user explicitly asks about wiki / concept / entity / synthesis pages, or when lilbeestatus shows a built wiki. Requires the lilbee-mcp skill to be active for the underlying MCP connection.
m3-health
Health check — package version, installed payload, chatlog DB row count, per-agent hook state.
m3-help
List all m3-memory slash commands / skills and what they do.
continuum-recipes
Copy-pasteable Continuum patterns — RAG, plan-and-execute, ReAct, multi-tenant agents, FastAPI integration, structured output, prompt-injection scanning, custom containers. Invoke when the user asks "how do I do X with Continuum" and X is a common app pattern rather than a single API question.
m3-forget
Delete a memory permanently. Asks for confirmation first.