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 GetPercept/percept --skill percept-voice-cmdgit clone --depth 1 https://github.com/GetPercept/perceptWrote 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/getpercept/percept/percept-voice-cmd)<a href="https://agentmods.dev/skills/getpercept/percept/percept-voice-cmd"><img src="https://agentmods.dev/badge/skills/getpercept/percept/percept-voice-cmd.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 | $0.00000 | $0.00482 |
| Opus 5 | $0.00000 | $0.00241 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
percept-voice-cmd 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 6d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
percept-voice-cmd
Voice command detection and action execution for OpenClaw agents.
What it does
Detects wake words in ambient speech and routes voice commands to your OpenClaw agent for execution. Supports email, text, reminders, search, calendar, notes, and custom commands.
When to use
- User says a wake word ("Hey Jarvis", "take notes", or custom)
- User wants hands-free control of their agent
- User asks to set up voice commands or wake words
Requirements
- percept-listen skill installed and running
- OpenClaw agent accessible via CLI
Supported actions
| Action | Example |
|---|---|
| "Hey Jarvis, email Rob saying the report is ready" | |
| Text | "Hey Jarvis, text David that I'm running late" |
| Reminder | "Hey Jarvis, remind me in 30 minutes to call the dentist" |
| Search | "Hey Jarvis, look up the weather in San Francisco" |
| Calendar | "Hey Jarvis, what's on my calendar today?" |
| Note | "Hey Jarvis, take a note that the server password changed" |
| General | "Hey Jarvis, [anything]" → forwarded to OpenClaw |
Wake word configuration
Default wake words: hey jarvis, take notes, send an email
Configure via Percept dashboard (port 8960) → Settings → Wake Words, or directly in the database.
How it works
- Percept buffers incoming transcript segments
- Wake word detected → extends buffer by 5 seconds for full command capture
- 10-second continuation window after wake word (catches follow-up without repeating wake word)
- Two-tier intent parsing: fast regex first, LLM fallback for complex commands
- Contact resolution from address book (
percept/data/contacts.json) - Command dispatched to OpenClaw CLI for execution
Speaker authorization
Only approved speakers can trigger voice commands. Configure in:
percept/data/speakers.json— map speaker IDs to names- Dashboard → Settings → Speakers → toggle approved/owner
Unapproved speakers are logged but commands are not executed.
Links
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.
- 6d ago First seen · 58 lines · 0 tokens per session scan A 4f4da8f87cf4
percept-voice-cmd is a skill published in the GitHub repository GetPercept/percept (8 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 482 tokens. 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.