A read-focused connector for Blink cameras and video doorbells. Blink is Amazon's home-security camera service; this tool can inspect device state, motion events, and clip information.

Reading camera and doorbell status, checking network arm state, listing motion clips, viewing clip metadata, and preparing approved security-control requests.

It provides a bounded way to work with Blink's community-supported interface while avoiding guessed web addresses, credentials, and request details.

blink — Skill for Claude Code by HybridAIOne

Install

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.

Any agent

npx skills add HybridAIOne/hybridclaw --skill blink

Clone the repo

git clone --depth 1 https://github.com/HybridAIOne/hybridclaw

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hybridaione/hybridclaw/blink/github.svg)](https://agentmods.dev/skills/hybridaione/hybridclaw/blink)

Your own site

<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/blink"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/blink/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/blink"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/blink.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,590 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.03590
Opus 5	$0.00014	$0.01795
Sonnet 5	$0.00005	$0.00718
Haiku 4.5	$0.00003	$0.00359

Measured 12d ago against content hash 66d7ba0fd840, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

blink scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (blink.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Do not run `hybridclaw secret get`, call `/api/secret`, inspect `env`, or use `curl`/ad hoc scripts to fetch Blink secrets. If the helper reports missing session secrets such as `BLINK_TIER`, run `run account-refresh`

skills/blink/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blink

Use this skill for Blink camera, video doorbell, network arm-state, motion event, and clip-metadata workflows. Blink does not publish an official public API; this skill follows the bounded community API surface used by BlinkPy, BlinkMonitorProtocol, and Home Assistant. Treat endpoint behavior as best-effort and stop on the first authentication or verification failure.

Core Contract

Build and run all Blink API calls with skills/blink/blink.cjs; do not handcraft Blink URLs, auth headers, or JSON bodies when the helper supports the operation.
Use run for live Blink calls. The helper sends its own request objects through the gateway /api/http/request path, so the model does not reconstruct endpoint details.
Use http-request only as dry-run JSON for inspection or fallback direct http_request execution when helper live execution is unavailable. Pass emitted httpRequest fields as structured JSON; do not stringify nested fields such as captureResponseFields or secretHeaders.
Never call http_request against guessed Blink hosts or paths. Use only the exact structured request emitted by the helper in this turn. If the helper lacks an operation, say the skill does not support that operation instead of probing.
For ordinary operator requests, do not read or grep skills/blink/blink.cjs to debug the helper. Trust the helper output. Source inspection is for maintainers changing this skill, not for listing devices.
Helper operations use subject-verb names (devices-list, account-login, camera-motion-set). Legacy aliases are accepted, but prefer the canonical names shown below.
Credentials and tokens must stay in the SecretRef-backed runtime secret store; never ask the operator to paste BLINK_PASSWORD or BLINK_AUTH_TOKEN into chat, and never include either value in prose.
Do not run hybridclaw secret get, call /api/secret, inspect env, or use curl/ad hoc scripts to fetch Blink secrets. If the helper reports missing session secrets such as BLINK_TIER, run run account-refresh once, then run account-login if refresh cannot recover the session; email/password may already be stored.
account-login is implemented as OAuth v2 Authorization Code + PKCE in the helper. Run node skills/blink/blink.cjs --format json run account-login; do not call old password login endpoints and do not web-search or endpoint-probe inside the user task.
The Blink-specific implementation lives under skills/blink/; the gateway pieces this skill relies on are generic http_request primitives for nested response capture, explicit token bind-domain capture, secret-backed headers, manual redirect inspection, and response-body suppression.
The helper owns all Blink host and path selection; arbitrary host/path passthrough is not supported.
Clip downloads must go through the gateway artifact path; return artifact handles or metadata only, and rely on the helper-emitted suppressResponseBody: true so raw video bytes do not enter model context.
Live-view requests are red and operator-UI-only; the helper emits suppressResponseBody: true, and RTSP/HLS/session handles must not be copied into chat even after approval.
Stop after the first 401, invalid-credentials, or verification-required response; do not retry, poll, or fan out more Blink calls until credentials or the PIN handover are resolved.
Stop after a 426 app update is required response or OAuth unsupported_grant_type. Do not probe alternate Blink endpoints, try new User-Agents, or attempt OAuth grant_type=password; use the helper's OAuth v2 Authorization Code + PKCE path with cookie and redirect handling outside model context.

Read the full file on GitHub · 250 lines

Files

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.

Changes

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 · 250 lines · 27 tokens per session scan A 66d7ba0fd840

Subscribe to this mod's changes

blink 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 3,590 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

RAG and vectors Security ai enterprise-ai gdpr local-llm proactive-agent

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.…

tobocop2/lilbee · 95 tokens

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.

tobocop2/lilbee · 60 tokens

m3-health

Health check — package version, installed payload, chatlog DB row count, per-agent hook state.

skynetcmd/m3-memory · 24 tokens

m3-help

List all m3-memory slash commands / skills and what they do.

skynetcmd/m3-memory · 18 tokens

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.

shyftlabs/continuum · 73 tokens

m3-forget

Delete a memory permanently. Asks for confirmation first.

skynetcmd/m3-memory · 16 tokens

blink