Update Plan logo

Update Plan

Organization
DasDigitaleMomentum
update-plan

Update an existing plan's status, todo list, and phase progress. Tracks what was done, updates completion status, and maintains the changelog. Use this skill during or after working on a plan phase to keep planning artifacts current.

Overview

PublisherDasDigitaleMomentum
Repositoryopencode-processing-skills
Skill nameupdate-plan
Stars
61
Forks
3
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by DasDigitaleMomentum on GitHub. Read the source before you install it.

Installation

Install the Update Plan AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/DasDigitaleMomentum/opencode-processing-skills/tree/main/skills/update-plan
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/DasDigitaleMomentum/opencode-processing-skills.git /tmp/opencode-processing-skills
mkdir -p .claude/skills
cp -r /tmp/opencode-processing-skills/skills/update-plan .claude/skills/update-plan
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Update Plan in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Update Plan on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Update Plan is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill: Update Plan

What This Skill Does

Keeps planning artifacts synchronized with actual progress:

  • Updates todo items (mark done, add new items, note blockers)
  • Updates phase status (pending → in_progress → completed)
  • Updates plan status and changelog
  • Updates implementation plan if approach changed during work
  • Prepares for next phase when current phase completes

When to Use

  • During work on a plan phase: to track progress in real-time
  • After completing work: to mark items and phases as done
  • When blockers are discovered: to document them
  • When the implementation approach changes: to update the implementation plan
  • After a plan review: to apply accepted Remove / Merge / Simplify findings while keeping scope artifacts consistent
  • When the user asks to "update the plan" or "mark phase as done"

Execution Model (Recommended)

  • Preferred: the primary agent runs this skill and updates artifacts under plans/<name>/.
  • Rationale: plan updates encode session decisions and current intent; the primary has the best access to that context.
  • Use doc-explorer only if verifying acceptance criteria requires codebase analysis (results are written to docs/).
  • Optional (edge cases): delegate mechanical edits (bulk todo moves, large reshuffles) to doc-explorer if needed.

Routing Matrix (Who does what)

  • Writes: updates under plans/<name>/ including plan.md, todo.md, phases/**, and (when needed) implementation/**.
  • Primary: preferred owner for updates (session decisions/intents live here).
  • doc-explorer: optional helper for mechanical edits or codebase analysis to verify acceptance criteria.
  • implementer: never used for plan maintenance.

Workflow

Step 1: Identify the Plan

Find the active plan:

  • Check plans/ directory for existing plans
  • If multiple plans exist, use the question tool to ask the user which plan
  • Read the plan's plan.md to understand the current status
  • Read todo.md to see current task state

Step 2: Determine What to Update

Option A: Todo updates (most common)

  • Mark completed items: move from Pending/In Progress to Completed
  • Add new items discovered during work
  • Mark blocked items with reason
  • Move next items to In Progress

Option B: Phase completion

  • Verify all acceptance criteria from the phase document are met
  • Update phase status in phases/phase-N.md frontmatter
  • Update the phases table in plan.md
  • Populate todo list with next phase's items (from implementation plan)
  • Add changelog entry

Option C: Implementation plan revision

  • If the technical approach changed during implementation
  • Update the affected implementation/phase-N-impl.md
  • Document the reason for the change
  • Update any affected todo items

Option D: Plan-level updates

  • Requirements changed → update plan.md
  • New risks identified → add to risks table
  • Scope adjustment → update scope section

Option E: Plan-review remediation

  • Inputs: immutable plan-review artifact, accepted finding IDs, explicitly rejected IDs with rationale, and user/primary decisions
  • Apply accepted Remove, Merge, and Simplify dispositions across plan.md, pending phase files, todo.md, and affected references
  • Do not invent replacement phases, abstractions, infrastructure, requirements, or acceptance criteria
  • Record applied finding IDs and material scope decisions in the changelog
  • If execution has not started, remove obsolete pending phase artifacts after explicit approval; if history exists, preserve it and mark the phase skipped or superseded with a concise pointer
  • Keep the review artifact immutable
  • Update references directly affected by the reduction, then stop; do not create a general plan-audit pass

Step 3: Apply Updates

Updating Todo List (todo.md)
markdown
### Completed
- [x] Implement user authentication endpoint (2025-02-14)

### In Progress
- [ ] Add input validation for login form

### Pending
- [ ] Write integration tests for auth flow

### Blocked
- [ ] Deploy to staging - waiting for CI pipeline fix

Always add a changelog entry:

markdown
### 2025-02-14
- Completed: Implement user authentication endpoint
- Started: Add input validation for login form
- Blocked: Deploy to staging (CI pipeline issue)
Updating Phase Status

In phases/phase-N.md frontmatter:

yaml
status: completed  # was: in_progress
updated: "2025-02-14"
Updating Plan Changelog

In plan.md:

markdown
### 2025-02-14
- Phase 1 completed, Phase 2 started

Step 4: Phase Transition

When a phase is completed and the next phase begins:

  1. Mark current phase as completed
  2. Mark next phase as in_progress
  3. Read the next phase's implementation plan
  4. Populate the todo list with the next phase's implementation steps
  5. Update the todo list's Phase Context section: update phase/implementation links, relevant docs, and latest handover reference
  6. Update plan status in plan.md if needed
  7. Add changelog entry documenting the transition

When the final phase is completed (Plan Completion):

  1. Mark the final phase as completed
  2. Update plan status in plan.md frontmatter to completed
  3. Verify that the overall Definition of Done is met
  4. Add a final changelog entry: "Plan completed"
  5. Clear the todo list's active phase header or add a "Plan Completed" note
  6. Use the question tool to confirm with the user that the plan is truly done

Step 5: Report

Summarize what was updated. If the phase is complete, highlight:

  • What was achieved
  • Whether all acceptance criteria were met
  • What comes next

For plan-review remediation, return:

  • Outcome: succeeded | partial | blocked
  • Findings: applied and unresolved IDs
  • Edits: changed artifacts with one-line descriptions
  • Next: stop | primary decision required; no independent re-review was started

Rules

  1. Always read before writing: Read the current state of all affected files before making changes.
  2. Changelog is append-only: Never modify or remove existing changelog entries. Only add new entries.
  3. Preserve history: When moving todo items between sections, maintain the completion date annotation.
  4. Atomic updates: Update all related files together (todo + phase + plan) - don't leave them in an inconsistent state.
  5. Phase transitions are explicit: A phase is only completed when all acceptance criteria are verified. Use the question tool to confirm with the user if unsure.
  6. Track deviations: If the actual implementation deviated from the plan, document the deviation in the implementation plan rather than silently updating.
  7. Use subagents sparingly: Plan updates are typically small enough for the primary agent. Only use subagents if verifying acceptance criteria requires codebase analysis.
  8. File-based interface: All updates are written to plan files. Do not return updated content as chat messages.
  9. Review remediation is bounded: Apply accepted findings once and stop. Do not automatically re-review, continue until zero findings, or reopen rejected findings.
  10. Reduction over compensation: When fixing gold-plating, remove or simplify work. Do not add replacement architecture, infrastructure, tests, or documentation unless the confirmed objective requires it.
  11. Review artifact immutability: Never modify the review that authorized remediation; record decisions and resulting scope in the plan changelog.

Templates

This skill includes normative templates as bundled files. Only read the templates when processing them. Output MUST preserve template headings/frontmatter keys when updating plan artifacts:

  • tpl-todo.md - Expected structure for the todo list
  • tpl-phase.md - Expected structure for phase documents
  • tpl-implementation-plan.md - Expected structure for implementation plans
  • tpl-plan.md - Expected structure for the plan document (reference for changelog/phases table updates)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Update Plan AI skill do?

Update an existing plan's status, todo list, and phase progress. Tracks what was done, updates completion status, and maintains the changelog. Use this skill during or after working on a plan phase to keep planning artifacts current.

Why use Update Plan on TypingMind?

Because you install it once and use it with any model. Update Plan is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Update Plan in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/DasDigitaleMomentum/opencode-processing-skills/tree/main/skills/update-plan. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Update Plan?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Update Plan?

As many as you like. As long as a model supports skills, you can use Update Plan with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Update Plan AI skill free?

Yes. It is published on GitHub by DasDigitaleMomentum under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇