cap_scheduler

cap_scheduler is a skill for Claude Code, Codex from espressif/esp-claw. It costs 25 tokens per session (1,599 once invoked), scanned A, original, Apache-2.0.

A manager for timer-based schedule rules that control reminders, periodic checks, automations, or agent wake-ups.

In plain words
What is it for?
It helps list, inspect, add, update, remove, enable, disable, pause, resume, trigger, and reload schedules.
Why use it?
It lets users inspect and change scheduled work without manually editing schedule files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

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.

espressif/esp-claw · 2,092 stars · on GitHub · esp-claw.com

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.

agentmods
npx agentmods add skills/espressif/esp-claw/cap_scheduler
Any agent
npx skills add espressif/esp-claw --skill cap_scheduler
Clone the repo
git clone --depth 1 https://github.com/espressif/esp-claw

Made for: Claude Code, Codex.

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.

agentmods badge for cap_scheduler

README.md
[![agentmods](https://agentmods.dev/badge/skills/espressif/esp-claw/cap_scheduler.svg)](https://agentmods.dev/skills/espressif/esp-claw/cap_scheduler)
Your own site
<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>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 0df40e2fdbe3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

components/claw_capabilities/cap_scheduler/skills/cap_scheduler/SKILL.md · 153 lines

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 by id.
  • scheduler_add: add one scheduler entry from schedule_json string.
  • scheduler_update: update one scheduler entry from schedule_json string.
  • scheduler_remove: remove one scheduler entry by id.
  • scheduler_enable: enable one scheduler entry by id.
  • scheduler_disable: disable one scheduler entry by id.
  • scheduler_pause: pause one scheduler entry by id.
  • scheduler_resume: resume one scheduler entry by id.
  • scheduler_trigger_now: trigger one scheduler entry immediately.
  • scheduler_reload: reload scheduler definitions from disk.

Calling rules

  • scheduler_add and scheduler_update input must be:
{
  "schedule_json": "<JSON string of one scheduler entry object>"
}
  • schedule_json is a JSON string, not an object.
  • Use a stable, unique id. scheduler_add fails if the id already exists. scheduler_update requires the id to already exist.
  • scheduler_get, scheduler_remove, scheduler_enable, scheduler_disable, scheduler_pause, scheduler_resume, and scheduler_trigger_now take:
{
  "id": "schedule_id"
}

schedule_json object fields

  • Required fields:
    • id: schedule unique id.
    • kind: one of once, interval, or cron.
  • enabled: whether the schedule is active. Defaults to true.
  • start_at_ms: absolute Unix epoch timestamp in milliseconds. Required for once. Optional for interval.
  • end_at_ms: optional stop time in Unix epoch milliseconds for once or interval.
  • interval_ms: interval period in milliseconds. Required for interval.
  • cron_expr: 5-field cron expression for cron, in the form minute hour mday month wday.
  • event_type: event type published to the router. Defaults to schedule.
  • event_key: logical key for router matching and tracing. Defaults to id.
  • source_channel: event source channel. Defaults to time.
  • chat_id: optional target chat id when downstream router actions need one.
  • content_type: event content type. Defaults to trigger.
  • session_policy: one of trigger, chat, global, ephemeral, nosave. Defaults to trigger.
  • 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. 0 means unlimited.

Read the full file on GitHub · 153 lines

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.

  1. 7d ago First seen · 153 lines · 25 tokens per session scan A 0df40e2fdbe3

Subscribe to this mod's changes

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.