ESP-Claw is an AI agent framework that runs on Espressif IoT chips and lets people define device behavior through conversation. It handles local sensing, decision-making, and execution for connected devices, with support for event-driven actions, structured memory, and MCP communication.
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 agentmods add skills/espressif/esp-claw/cap_schedulernpx skills add espressif/esp-claw --skill cap_schedulergit clone --depth 1 https://github.com/espressif/esp-clawWrote 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/espressif/esp-claw/cap_scheduler)<a href="https://agentmods.dev/skills/espressif/esp-claw/cap_scheduler"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/cap_scheduler.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 | $0.00025 | $0.01599 |
| Opus 5 | $0.00013 | $0.00800 |
| Sonnet 5 | $0.00005 | $0.00320 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
cap_scheduler 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 7d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scheduler Management
Use this skill when the user needs to inspect or control timer-based schedule rules.
When to use
- The user asks to list current schedules.
- The user asks to add, update, or remove a schedule.
- The user asks to pause, resume, enable, disable, trigger, or reload a schedule.
- The user asks for a timer-based reminder, periodic check, timed automation, or scheduled agent wake-up.
Available capabilities
scheduler_list: list all scheduler entries and runtime state.scheduler_get: get one scheduler entry byid.scheduler_add: add one scheduler entry fromschedule_jsonstring.scheduler_update: update one scheduler entry fromschedule_jsonstring.scheduler_remove: remove one scheduler entry byid.scheduler_enable: enable one scheduler entry byid.scheduler_disable: disable one scheduler entry byid.scheduler_pause: pause one scheduler entry byid.scheduler_resume: resume one scheduler entry byid.scheduler_trigger_now: trigger one scheduler entry immediately.scheduler_reload: reload scheduler definitions from disk.
Calling rules
scheduler_addandscheduler_updateinput must be:
{
"schedule_json": "<JSON string of one scheduler entry object>"
}
schedule_jsonis a JSON string, not an object.- Use a stable, unique
id.scheduler_addfails if the id already exists.scheduler_updaterequires the id to already exist. scheduler_get,scheduler_remove,scheduler_enable,scheduler_disable,scheduler_pause,scheduler_resume, andscheduler_trigger_nowtake:
{
"id": "schedule_id"
}
schedule_json object fields
- Required fields:
id: schedule unique id.kind: one ofonce,interval, orcron.
enabled: whether the schedule is active. Defaults totrue.start_at_ms: absolute Unix epoch timestamp in milliseconds. Required foronce. Optional forinterval.end_at_ms: optional stop time in Unix epoch milliseconds foronceorinterval.interval_ms: interval period in milliseconds. Required forinterval.cron_expr: 5-field cron expression forcron, in the formminute hour mday month wday.event_type: event type published to the router. Defaults toschedule.event_key: logical key for router matching and tracing. Defaults toid.source_channel: event source channel. Defaults totime.chat_id: optional target chat id when downstream router actions need one.content_type: event content type. Defaults totrigger.session_policy: one oftrigger,chat,global,ephemeral,nosave. Defaults totrigger.text: optional event text payload. For agent wake-up rules, use this as the instruction text.payload_json: optional structured payload. Defaults to{}. It may be written either as a JSON string or as a JSON object in the item itself.max_runs: max trigger count.0means unlimited.
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.
- 7d ago First seen · 153 lines · 25 tokens per session scan A 0df40e2fdbe3
cap_scheduler is a skill published in the GitHub repository espressif/esp-claw (2,092 stars, last pushed 4d ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,599 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
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.