<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>planner on tomrochette.com</title>
    <link>https://tomrochette.com/tags/planner/</link>
    <description>Recent content in planner on tomrochette.com</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <managingEditor>tom@tomrochette.com (Tom Rochette)</managingEditor>
    <webMaster>tom@tomrochette.com (Tom Rochette)</webMaster>
    <copyright>© 2026 Tom Rochette</copyright>
    <lastBuildDate>Wed, 16 Sep 2026 04:47:00 -0400</lastBuildDate><atom:link href="https://tomrochette.com/tags/planner/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>Ordewell</title>
      <link>https://tomrochette.com/agents/task-management/ordewell/</link>
      <pubDate>Wed, 16 Sep 2026 00:00:00 +0000</pubDate>
      <author>tom@tomrochette.com (Tom Rochette)</author>
      <guid>https://tomrochette.com/agents/task-management/ordewell/</guid>
      <category>research-note</category><category>agent-curated</category><category>fully-ai-generated</category><category>llm=glm-5.3-flash</category><category>task-management</category><category>planner</category><category>multi-agent</category><category>open-source</category>
      <description>&lt;p&gt;Ordewell is an Apache-2.0 TypeScript CLI, terminal UI, and VS Code extension that turns one goal into an ordered plan of coding-agent tasks, each with its own runner, model, thinking effort and mode, then executes the plan and completes a task only when that task&amp;rsquo;s marker appears in the runner output.&#xA;Facts below verified as of 2026-09-16.&lt;/p&gt;&#xA;&lt;p&gt;&lt;strong&gt;The plan as a typed artifact you can rewrite before a token is spent, plus completion decided by markers rather than the model&amp;rsquo;s own verdict, is the design worth stealing, and the launch thread&amp;rsquo;s AI-written-replies episode is the caution this section exists to record.&lt;/strong&gt;&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;What it is&#xA;    &lt;div id=&#34;what-it-is&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#what-it-is&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;An npm package (&lt;code&gt;ordewell&lt;/code&gt;, also published scoped as &lt;code&gt;@ordewell/cli&lt;/code&gt;, Node 20+, tmux for the TUI) with three surfaces over one core: a CLI, a chat-left-plan-right terminal UI, and a VS Code extension that bundles its own core.&#xA;A planner researches the repo read-only, interrogates a vague goal in conversation instead of guessing, and commits the plan as JSON; planning is one continuous message loop (ADR-0002) with no approve buttons.&#xA;Every task then runs as a real coding-agent session in a fresh context, handed its predecessors&amp;rsquo; results, with independent tasks running in parallel and the dependency graph always respected.&#xA;Runners are pluggable: Claude Code, Codex, and OpenCode ship built in, anything else is a plugin manifest, the planner can itself be one of those agents on a subscription you already hold, and 25 API-key providers are recognized for standalone use.&#xA;The planner&amp;rsquo;s permissions are unusually explicit (ADR-0008): commands classify into auto, ask, and refuse tiers, refuse is not promptable, paths are confined to the workspace, and its docs concede this is a denylist over a real shell rather than an OS sandbox.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Status&#xA;    &lt;div id=&#34;status&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#status&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;Active, young, and small.&#xA;As of 2026-09-16: 101 stars, 6 forks, 6 open issues, created 2026-07-31, pushed 2026-09-11, latest release v0.4.19 on 2026-09-10, and roughly 3,300 npm downloads last month across the &lt;code&gt;ordewell&lt;/code&gt; and &lt;code&gt;@ordewell/cli&lt;/code&gt; package names.&#xA;The Show HN launch thread reached 50 points and 30 comments on 2026-09-15.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Strengths&#xA;    &lt;div id=&#34;strengths&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#strengths&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;The plan is editable structured data: change a task&amp;rsquo;s runner, model, effort, or mode without losing completed work or round-tripping the AI.&lt;/li&gt;&#xA;&lt;li&gt;Marker-based completion is a verification primitive this category mostly lacks; a task completes on evidence, exit codes are kept as diagnostics, and manual marks can be reversed.&lt;/li&gt;&#xA;&lt;li&gt;Per-task model assignment is a portfolio decision made in the open, so a security refactor and a README update do not get the same model.&lt;/li&gt;&#xA;&lt;li&gt;The exploration envelope (ADR-0008) is the most explicit read-only planner discipline profiled in this section, including the admission of its own limits.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Cautions&#xA;    &lt;div id=&#34;cautions&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#cautions&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;strong&gt;The launch thread&amp;rsquo;s defining exchange is the transparency record: a commenter observed that everything about the project, including author replies in the comments, is AI-written, and the maintainer confirmed heavy AI use for the docs and code while standing behind the design.&lt;/strong&gt;&lt;/li&gt;&#xA;&lt;li&gt;Replying to people with AI-generated text drew a specific objection in the same thread, so treat the repo&amp;rsquo;s discourse hygiene as part of the adoption decision.&lt;/li&gt;&#xA;&lt;li&gt;The same thread carried the standing structural objection to meta-frameworks: any advance gets absorbed into Claude and Codex within months, and this tool&amp;rsquo;s planner-plus-runners surface is exactly the kind that absorption targets.&lt;/li&gt;&#xA;&lt;li&gt;v0.4.x and 101 stars mean churn is likely; ADR-0002 records saved sessions being wiped without migration on that rewrite.&lt;/li&gt;&#xA;&lt;li&gt;The planner&amp;rsquo;s shell control is a denylist classifier over a real shell, not a sandbox (ADR-0011 tracks that gap).&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Pricing&#xA;    &lt;div id=&#34;pricing&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#pricing&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;Free and open source under Apache-2.0.&#xA;No paid tier exists; token costs follow your runner subscriptions or API keys.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Compared to&#xA;    &lt;div id=&#34;compared-to&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#compared-to&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/task-management/task-master/&#34; &gt;Task Master&lt;/a&gt;: both decompose an input into dependency-chained tasks, but Task Master&amp;rsquo;s pipeline starts from a written PRD and is now a Commons-Clause commercial engine, while Ordewell&amp;rsquo;s planner interrogates a vague goal and is Apache-2.0.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/task-management/beads/&#34; &gt;beads&lt;/a&gt;: beads is the shared-queue state layer with atomic claims; Ordewell is the planning layer above it, so they compose more than compete.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/task-management/backlog-md/&#34; &gt;Backlog.md&lt;/a&gt;: both keep the human in charge before code exists; Backlog.md gates on reviewing agent-written files, Ordewell gates on the editable plan artifact itself.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Bottom line&#xA;    &lt;div id=&#34;bottom-line&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#bottom-line&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;&lt;strong&gt;Recommended for engineers running mixed-model agent fleets who want per-task model assignment and evidence-based completion, and who accept a three-month-old project.&lt;/strong&gt;&#xA;Not for shared multi-agent queues (that is beads) or for teams that need maturity signals 101 stars cannot give.&#xA;The disagreeable claim I will defend: the AI-written launch thread is not disqualifying here, but it is the exact failure mode this section&amp;rsquo;s transparency rules exist to catch, and a tool that cannot surface its own authorship plainly should not be trusted to surface task completion either.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Changes&#xA;    &lt;div id=&#34;changes&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#changes&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;2026-09-16 - Created.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;See also&#xA;    &lt;div id=&#34;see-also&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#see-also&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/task-management/beads/&#34; &gt;beads&lt;/a&gt; - the shared-queue state layer Ordewell assigns work into&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/task-management/task-master/&#34; &gt;Task Master&lt;/a&gt; - the PRD-first pipeline and the commercialized counterpart&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/task-management/backlog-md/&#34; &gt;Backlog.md&lt;/a&gt; - the review-gate sibling for oversight before code exists&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/harnesses/claude-code/&#34; &gt;Claude Code&lt;/a&gt; - one of the three built-in runner agents&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/task-management/task-management-feature-matrix/&#34; &gt;Task Management Feature Matrix&lt;/a&gt; - the category comparison this note joins&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;References&#xA;    &lt;div id=&#34;references&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#references&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://github.com/ordewell/ordewell&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://github.com/ordewell/ordewell&lt;/a&gt; - README: plan artifact, runners, marker verification, plugin manifests&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://api.github.com/repos/ordewell/ordewell&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=api.github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://api.github.com/repos/ordewell/ordewell&lt;/a&gt; - stars, forks, dates, Apache-2.0 as of 2026-09-16&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://ordewell.ai&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=ordewell.ai&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://ordewell.ai&lt;/a&gt; - the product site: surfaces, the plan-execute-verify loop, marker wording&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://ordewell.ai/docs.html&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=ordewell.ai&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://ordewell.ai/docs.html&lt;/a&gt; - install, requirements, headless usage&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://github.com/ordewell/ordewell/blob/main/docs/adr/0002-planner-as-conversation-loop.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://github.com/ordewell/ordewell/blob/main/docs/adr/0002-planner-as-conversation-loop.md&lt;/a&gt; - the conversation-loop decision and the session wipe&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://github.com/ordewell/ordewell/blob/main/docs/adr/0008-planner-exploration-envelope.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://github.com/ordewell/ordewell/blob/main/docs/adr/0008-planner-exploration-envelope.md&lt;/a&gt; - the auto/ask/refuse tiers and path confinement&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://news.ycombinator.com/item?id=49712276&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=news.ycombinator.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://news.ycombinator.com/item?id=49712276&lt;/a&gt; - the launch thread: the AI-written exchange, the absorption objection, 50 points and 30 comments&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://api.npmjs.org/downloads/point/last-month/@ordewell/cli&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=api.npmjs.org&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://api.npmjs.org/downloads/point/last-month/@ordewell/cli&lt;/a&gt; - 1,810 downloads last month for the scoped package&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;</description>
      
    </item>
    
  </channel>
</rss>
