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/lukacf/meerkat/schedule-workflownpx skills add lukacf/meerkat --skill schedule-workflowgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/schedule-workflow)<a href="https://agentmods.dev/skills/lukacf/meerkat/schedule-workflow"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/schedule-workflow.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 | $0.00014 | $0.00542 |
| Opus 5 | $0.00007 | $0.00271 |
| Sonnet 5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
schedule-workflow 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 5d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schedule Workflow
Use Schedule when something should happen later, repeatedly, or on a wall-clock calendar. Schedules own time and delivery. They do not own live work state.
Operating Rules
- Create schedules with
meerkat_schedule_createwhen the user asks for a reminder, recurrence, follow-up, monitor, wakeup, or routine automation. - Choose the smallest trigger that matches the request:
oncefor one future instant,intervalfor fixed cadence,calendarfor wall-clock recurrence in a named timezone. - For the current agent session, use the agent-facing session target
{"target_kind":"session","type":"current_session","action":{"type":"prompt","prompt":"Check in"}}. The host resolves it to a persisted durable target. - Use
resumable_sessiononly when you have the exact durablesession_id, andmaterialize_on_demand_sessionwhen the schedule must create a session from an explicit build spec on first fire. - The defaults are
misfire_policy: {"type":"skip"},overlap_policy: "skip_if_running", andmissing_target_policy: "mark_misfired". Change them only when the user asks for bounded catch-up, concurrency, or different missing-target behavior. - Inspect with
meerkat_schedule_get,meerkat_schedule_list, andmeerkat_schedule_occurrencesbefore creating duplicates. - Pause for temporary suspension, resume to reactivate, update to change future behavior, and delete only when the schedule should stop permanently. Delete is irreversible, but historical occurrences remain queryable.
Boundaries
- Use WorkGraph for pending work, dependencies, claims, and evidence.
- Use Schedule for time. A scheduled prompt may ask an agent to inspect WorkGraph, but Schedule should not duplicate WorkGraph readiness logic.
- Treat an occurrence claim and delivery outcome as Schedule authority only. They do not authorize a WorkGraph claim or prove that the underlying shared work completed.
- Do not infer successful delivery from a due time. Inspect occurrence phase; pending, claimed, dispatching, awaiting completion, completed, skipped, misfired, superseded, and delivery failed are distinct states.
- Use memory for recalled knowledge, not for future wakeups.
- Use builtin tasks for private scratch items that do not need scheduled delivery or shared durable coordination.
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.
- 5d ago First seen · 49 lines · 14 tokens per session scan A 5bced20ec222
schedule-workflow is a skill published in the GitHub repository lukacf/meerkat (20 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 542 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
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.