Executing Plans logo

Executing Plans

Community
andreaswasita
executing-plans

Executes approved plans one task at a time, verified.

Overview

Publisherandreaswasita
Repositorycopilot-agents-dojo
Skill nameexecuting-plans
Stars
54
Forks
15
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Executing Plans 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/andreaswasita/copilot-agents-dojo/tree/main/skills/executing-plans
  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/andreaswasita/copilot-agents-dojo.git /tmp/copilot-agents-dojo
mkdir -p .claude/skills
cp -r /tmp/copilot-agents-dojo/skills/executing-plans .claude/skills/executing-plans
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Executing Plans 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 Executing Plans 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 Executing Plans 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.

Executing Plans Skill

Walks an approved tasks/todo.md plan step by step: pick the next task, execute it, verify it, commit it, mark it done. Does NOT freelance new scope mid-execution and does NOT skip the verification gate.

When to Use

  • A plan in tasks/todo.md has been approved.
  • Starting or resuming a multi-step implementation.
  • User says "go", "start", "execute", or "begin".
  • A sub-agent batch finishes and the next batch is ready.
  • NOT before the design is approved (use brainstorming first).

Prerequisites

  • Approved tasks/todo.md containing ordered steps with acceptance criteria.
  • git configured for atomic commits.
  • The view, edit, and powershell Copilot tools.
  • A green baseline test run.
  • The verify-before-done skill available for the verification step.

How to Run

text
1. Read tasks/todo.md. Identify the next unchecked task.
2. Confirm its prerequisites are satisfied.
3. Execute the task.
4. Run the verify-before-done skill.
5. Append the Verification Results block.
6. Commit. Mark the checkbox `- [x]`.
7. Repeat. Post a short progress note every 2–3 tasks.

Quick Reference

PhaseActionTool
LoadRead tasks/todo.mdview
ExecuteMake the changeedit, powershell
VerifyTests + gate + diffverify-before-done skill
RecordAppend Verification Resultsedit
CommitOne commit per taskpowershell → git commit
Mark doneFlip - [ ] to - [x]edit

Procedure

Step 1: Load the Plan

Open tasks/todo.md with view. Locate the next - [ ] step. If none exist, the plan is done — hand off to finishing-a-development-branch.

Step 2: Check Prerequisites

Read the task. Confirm any "depends on" notes are satisfied. If a prerequisite is missing, STOP — do not improvise around it; re-plan first.

Step 3: Execute Exactly One Task

Make the change. Resist the urge to bundle "while I'm here" cleanups. Scope discipline is the whole point of the plan.

Step 4: Verify

Invoke the verify-before-done skill. Do not consider the task complete until it has produced a Verification Results block:

markdown
### Verification Results
- [x] Tests: 47 passed, 0 failed
- [x] Dojo gate: `verify.sh --check` PASS
- [x] Diff matches plan
- [x] Clean tree

Step 5: Commit and Mark Done

bash
git add -A
git commit -m "<type>: <task title>"

Then edit tasks/todo.md to flip - [ ] → - [x].

Step 6: Handle Blockers Explicitly

If a task cannot complete as planned:

  1. Do not improvise around it.

  2. Annotate the task in tasks/todo.md:

    markdown
    - [ ] Step 3: Implement API endpoints
      > ⚠️ BLOCKED: Schema does not support required query. Need index or restructure Step 1.
  3. Re-plan. Update the plan. Resume from the revised version.

Step 7: Progress Updates

Every 2–3 completed tasks, post a short status:

markdown
**Progress:** 3/5 tasks complete
- ✅ Schema, models, endpoints
- ⏳ Next: validation
- 🚫 No blockers

Pitfalls

  • DO NOT skip the plan order without re-planning first.
  • DO NOT batch 5 tasks then verify once. Verify after each.
  • DO NOT add scope mid-execution ("while I'm here…"). Log it as a follow-up; stay on plan.
  • DO NOT mark a task done without a Verification Results block.
  • DO NOT silently work around blockers. Annotate and re-plan.

Verification

  • Every flipped - [x] has a Verification Results block above it.
  • One commit per completed task (or one logical unit).
  • No scope was added to the plan without explicit user agreement.
  • Progress updates were posted at least every 3 tasks.
  • Blockers, if any, are documented in tasks/todo.md.

Frequently asked questions

What does the Executing Plans AI skill do?

Executes approved plans one task at a time, verified.

Why use Executing Plans on TypingMind?

Because you install it once and use it with any model. Executing Plans 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 Executing Plans in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/andreaswasita/copilot-agents-dojo/tree/main/skills/executing-plans. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Executing Plans?

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 Executing Plans?

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

Is the Executing Plans AI skill free?

Yes. It is published on GitHub by andreaswasita 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 👇