delivery-schedule
v1.0.0The unattended lane, stacked on delivery: the eleven schedule-* skills that run with nobody watching, plus install, plus the catalog of triggers that fires them. Nine schedulable entry points that pick their own input and run a flow or a review — bug fix, merge review, package update, performance review, review, security review, week starter, weekly cost analysis, and what's new — and six trigger definitions naming a target, a cadence, the plugins that target needs, and the prompt for a cloud session that starts with nothing but the repository. delivery-schedule:install creates or updates them through whatever scheduler the live session exposes and records the selection under components.schedule; schedule-status reads their runs and logs; schedule-run fires one now. One capability, two host names: Routines in Claude Code, Automations in the GitHub Copilot app. Depends on delivery and names devbook: a trigger whose target is not enabled is reported and skipped, never scheduled.
By Job SchepersLicense: MIT0 GitHub starsUpdated last week
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 12 skill or MCP entries
- Source updated
- Sep 14, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install delivery-schedule for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install delivery-schedule@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/JSdotNet/ai-agent-stackClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/delivery-schedule/.
Plugin files
├── .claude-plugin/plugin.json├── skills/install/SKILL.md├── skills/schedule-bug-fix/SKILL.md├── skills/schedule-merge-review/SKILL.md├── skills/schedule-package-update/SKILL.md├── skills/schedule-performance-review/SKILL.md├── skills/schedule-review/SKILL.md├── skills/schedule-run/SKILL.md├── skills/schedule-security-review/SKILL.md├── skills/schedule-status/SKILL.md├── skills/schedule-week-starter/SKILL.md├── skills/schedule-weekly-cost-analysis/SKILL.md└── skills/schedule-whats-new/SKILL.md
Included Skills12
Put this repository's schedules from the catalog into the host's scheduler — its Routines page in Claude Code, its Automations page in the GitHub Copilot app — creating or updating each selected one, disabling the rest, and recording the selection under components.schedule in .devbook/config.json. Idempotent by name. Use when: setting up recurring unattended runs for a repository, scheduling routines or automations, changing a cadence, adding or removing one, or after upgrading this plugin. Triggers on: "schedule install", "schedule-install", "set up my routines", "set up my automations".
Pick the single highest-priority open GitHub issue labelled 'bug', claim it, and resolve it in this session by running flow-bug through to Personal Validation. One issue per run, no extra sessions.
Review every open pull request that is waiting on a reviewer: run the code review checklist over its diff, read its checks and its distance from the base branch, and post one review comment per pull request with the findings and a merge verdict. Never approves, never merges, never pushes. Idempotent per head commit, so a daily run re-reviews only what changed.
Update all outdated NuGet packages in a .NET solution, check installed plugins for newer versions, and open a PR with the changes. Handles Central Package Management, Aspire integration upgrades, and post-update build and test verification.
Identify 10 performance improvements across the codebase, score each by impact and effort, then implement and open a PR for the single highest-impact, lowest-effort finding.
Run a full automated review cycle on the codebase or a specific scope: collects TODO items, surfaces future-improvement suggestions, and runs a structured code review. Produces a prioritised findings report and optionally opens GitHub issues for the highest-priority items.
Fire one of this repository's schedules now, outside its cadence, and report the run. Use when: running a routine or automation now, testing one right after delivery-schedule:install, or re-running one that failed.
Run a layered security review of the repository: vulnerable dependencies from the package managers' own audits, secrets committed to the tree, CI workflow hardening, and the security items of the code review checklist. Produces a severity-ranked report and opens one GitHub issue per new high-severity finding, deduplicated against the issues already open.
Show this repository's schedules and how their recent runs went — cadence, enabled state, the last runs, what each published, and the log of a run that failed or parked. Use when: checking whether a scheduled run fired, why one failed, what a routine or automation produced last night, or listing what is scheduled for this repository.
Scan configured topics for updates published in the last 7 days and produce a concise "What's new this week" digest. Default topics: .NET Aspire, Claude Code, and the Anthropic engineering blog.
Analyse the token usage the delivery-surface-dashboard recorded for the week's flow runs, surface the top actionable cost-reduction tips, and produce a concise report.
Check one or more GitHub repositories for what changed since the last run: open pull requests and pull requests merged since the last checkpoint. Correlates each PR with related Jira tickets or GitHub issues where discoverable, and persists a per-repo checkpoint so the next run only reports genuinely new activity.
Plugin manifests1
{
"name": "delivery-schedule",
"version": "1.0.0",
"description": "The unattended lane, stacked on delivery: the eleven schedule-* skills that run with nobody watching, plus install, plus the catalog of triggers that fires them. Nine schedulable entry points that pick their own input and run a flow or a review — bug fix, merge review, package update, performance review, review, security review, week starter, weekly cost analysis, and what's new — and six trigger definitions naming a target, a cadence, the plugins that target needs, and the prompt for a cloud session that starts with nothing but the repository. delivery-schedule:install creates or updates them through whatever scheduler the live session exposes and records the selection under components.schedule; schedule-status reads their runs and logs; schedule-run fires one now. One capability, two host names: Routines in Claude Code, Automations in the GitHub Copilot app. Depends on delivery and names devbook: a trigger whose target is not enabled is reported and skipped, never scheduled.",
"author": {
"name": "Job Schepers"
},
"license": "MIT",
"keywords": [
"schedule",
"routines",
"automations",
"cron",
"unattended",
"cloud",
"delivery",
"devbook"
],
"dependencies": [
{
"name": "delivery",
"version": ">=1.0.0 <2.0.0",
"marketplace": "jsdotnet"
}
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[delivery-schedule on Agent Plugins Marketplace](https://pluginsmp.com/plugins/delivery-schedule)