agentmods.dev

cron-scheduler

cron-scheduler is a skill for Claude Code, Codex from FirenzeClaw/kimi-session-orchestrator. It costs 33 tokens per session (2,244 once invoked), scanned A, original, MIT.

A scheduling skill for turning recurring project-management work into a chain of timed tasks. It uses a cron schedule, a common system format for running jobs at set times.

In plain words
What is it for?
Use it to set up daily or periodic development loops, sort and label issues on a schedule, or scan code changes and update documentation.
Why use it?
It keeps recurring work and its settings in one recorded place, so later sessions can resume and renew the same process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool; mentions AGENTS.md.

not rated 0repo 14d ago A scan 33 tokens original MIT

Good fit Use it to set up daily or periodic development loops, sort and label issues on a schedule, or scan code changes and update documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/firenzeclaw/kimi-session-orchestrator/cron-scheduler
View source ↗ FirenzeClaw/kimi-session-orchestrator
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 FirenzeClaw/kimi-session-orchestrator --skill cron-scheduler
Clone the repo
git clone --depth 1 https://github.com/FirenzeClaw/kimi-session-orchestrator

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 cron-scheduler

README.md
[![agentmods](https://agentmods.dev/badge/skills/firenzeclaw/kimi-session-orchestrator/cron-scheduler/github.svg)](https://agentmods.dev/skills/firenzeclaw/kimi-session-orchestrator/cron-scheduler)
Your own site
<a href="https://agentmods.dev/skills/firenzeclaw/kimi-session-orchestrator/cron-scheduler"><img src="https://agentmods.dev/badge/skills/firenzeclaw/kimi-session-orchestrator/cron-scheduler/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.

agentmods 80×15 button for cron-scheduler

Your own site · 80×15
<a href="https://agentmods.dev/skills/firenzeclaw/kimi-session-orchestrator/cron-scheduler"><img src="https://agentmods.dev/badge/skills/firenzeclaw/kimi-session-orchestrator/cron-scheduler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00033 $0.02244
Opus 5 $0.00016 $0.01122
Sonnet 5 $0.00007 $0.00449
Haiku 4.5 $0.00003 $0.00224

Measured 10d ago against content hash c61fd0773be0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cron-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 10d 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.

skills/cron-scheduler/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cron Scheduler — 定时自动化编排

概述

cron-scheduler 把重复性 PM 编排沉淀为一个可续期的 cron 链。cron.yaml 是唯一事实来源：先写 .kimi-tunnel/cron.yaml，再把同一内容双写到 project/decisions memory，后续 session 只从该配置恢复和续期。

触发

  • 用户调用 /cron-scheduler
  • PM 说“设置定时任务”“每天自动...”“定期跑...”
  • 需要把 loop-orchestrator、session-retire、memory_get/set 串成周期性执行链

启动前硬门

  1. 读取项目规范：AGENTS.md、README、相关 SPEC。
  2. 读取 skills/cron-scheduler/guide-cron-patterns.md，只有在选择 cron/heartbeat/hook/goal 模式时才加载。
  3. 读取可用模板：templates/daily-dev-loop.yaml、templates/issue-triage.yaml、templates/doc-sync.yaml。
  4. 调用 memory_get(namespace="project/meta") 与 memory_get(namespace="project/decisions") 时必须使用 kimi-session-orchestrator MCP，不使用 knowledge-graph memory MCP。

完成标准：PM 已确认项目背景、已有决策、目标工作目录和候选模板。

Phase 1: 采集

向用户展示预置模板，并收集自定义参数。Auto permission mode 下不要调用 AskUserQuestion，改用纯文本列出选项并基于用户已有描述继续；非 Auto 模式可一次只问一个关键问题。

预置模板

模板 场景 文件
daily-dev-loop GitHub Issues 驱动的每日开发循环 templates/daily-dev-loop.yaml
issue-triage 定时分类、排序、标注 issue，不实施 templates/issue-triage.yaml
doc-sync 定时代码变更扫描并同步文档 templates/doc-sync.yaml

自定义维度

  • 触发时间：每天、工作日、指定时刻、自定义 cron 表达式。
  • Git 策略：分支命名规则、是否 pull/rebase、是否 push、是否自动 PR。
  • 任务来源：GitHub Issues、Linear、项目 TODO 文件、自定义查询。
  • Issue 过滤：label、assignee、milestone、state、自定义搜索语法。
  • 实施模式：全自动、规范确认后自动、每步确认。
  • 验证策略：grade_step、cross-model、多轮自检、仅编译通过。
  • 完成后动作：自动 PR、仅 push、仅本地、只写报告。
  • 退役策略：每日退役、按 issue 数退役、按 context_tokens 阈值退役。

完成标准：已得到模板名、schedule、timezone、source、execution、completion、retire 七类配置；缺失项已用模板默认值补齐并显式标注。

Phase 2: 文档化

  1. 渲染 .kimi-tunnel/cron.yaml。缺少 .kimi-tunnel/ 时创建目录；不要把配置分散到多个文件。
  2. 配置必须包含 run_lock、renewal 与 external_actions：
    • run_lock 防止同一 schedule 重叠执行；上一轮未结束时本轮只记录 skipped-overlap。
    • renewal.mode 必须为 one-shot-chain 或 single-recurring-job。默认用 one-shot-chain；每次 CronCreate 必须 recurring=false，只注册下一次触发。
    • external_actions 对 issue 评论、label 更新、push、PR 等外部副作用逐项声明 requires_confirmation。
  3. 将同一份 YAML 内容写入 memory：

Read the full file on GitHub · 142 lines

Files

What ships with it

4 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.

  1. 10d ago First seen · 142 lines · 33 tokens per session scan A c61fd0773be0

Subscribe to this mod's changes

cron-scheduler is a skill published in the GitHub repository FirenzeClaw/kimi-session-orchestrator (0 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 2,244 once invoked, about $0.0002 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 2026-08-31.

Project managementkimi-codemcppm-automationsession-orchestratorworkflow-engine
Related

Other skills, from other repositories

create-rt-issue

Create a GitHub issue in camunda/camunda for load-test/Reliability Testing (RT) work, extending create-issue with the component/load-tests label and an rt/foundation, rt/coverage, or rt/enablement classification. Use when asked to create, file, or open an RT/load-test issue.

camunda/camunda · 72 tokens

mp-implement

Use when the user provides any kind of feature spec (rough notes / system design / partial spec / canonical PRD) and wants it implemented end-to-end autonomously on Claude Code alone — no external execution engine — or invokes /mp-implement.

skywalkercyt/mp-implement · 54 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens