Implement Execplan

Community

grp06

implement-execplan

Execute an ExecPlan from a work item under `.agent/work/` or, when necessary, from the older singleton `.agent/execplan-pending.md` flow. Use when the user asks to implement a plan, execute the pending plan, or resume blocked implementation work.

Overview

Publisher	grp06
Repository	`useful-codex-skills`
Skill name	`implement-execplan`
Stars	78
Forks	6
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

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 grp06 on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/grp06/useful-codex-skills/tree/main/implement-execplan
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.

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/grp06/useful-codex-skills.git /tmp/useful-codex-skills
mkdir -p .claude/skills
cp -r /tmp/useful-codex-skills/implement-execplan .claude/skills/implement-execplan

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Implement Execplan 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 Implement Execplan 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 Implement Execplan 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.

Implement ExecPlan

Use the ExecPlan as the implementation contract for delivering both the intended behavior and the intended simplification of the system.

Preferred Input Resolution

Preferred target resolution order:

explicit work-item path supplied by the user
explicit execplan.md path supplied by the user
.agent/active when it points to a work item with:
- stage="plan" and state="completed", or
- stage="implementation" and state="blocked"
the most recently updated work item under .agent/work/ matching those same rules
legacy fallback: .agent/execplan-pending.md

If no supported plan exists, stop and tell the user.

Work Item Responsibilities

If operating on a work item, read:

meta.json
decision.md when present
execplan.md

This skill owns execution-state transitions in meta.json:

when starting work: stage="implementation", state="active"
when blocked or only partially complete: stage="implementation", state="blocked"
when implementation completes: stage="implementation", state="completed"

Do not rename plans or move directories to represent lifecycle state.

Ousterhout Lens

When the plan leaves room for judgment:

prefer deep modules over shallow wrappers
prefer interfaces that hide sequencing and policy
prefer fewer concepts, fewer knobs, and fewer special cases
prefer simple mental models over clever decomposition

Workflow

Read the ExecPlan in full, then read .agent/PLANS.md.
Reconstruct the intended behavior, target boundary, and complexity dividend.
If available, read decision.md so the implementation stays aligned with the original decision rationale.
Before coding, update meta.json to stage="implementation" and state="active".
Inspect the relevant code paths before editing.
Implement milestone by milestone.
Keep the ExecPlan's Progress, Surprises & Discoveries, Decision Log, and Outcomes & Retrospective sections up to date as you go.
After each meaningful slice, run the plan's validation steps or the nearest targeted verification.
If you finish the implementation, set state="completed".
If you cannot finish safely in the current turn, record the blocker in the plan, set state="blocked", and stop cleanly.

Implementation-First Rule

This skill is for execution, not more planning.

You may update the ExecPlan during implementation only to:

record progress actually made
record discoveries from code already inspected
tighten milestones or acceptance criteria to match current repo reality
document design decisions that unblock the next implementation step

Do not turn an implementation turn into another plan-improvement pass.

Anti-Patterns

satisfying the letter of the plan while preserving the same interface burden
adding wrappers, adapters, or helper layers that hide little
pushing sequencing or policy outward to callers
finishing with only ExecPlan edits when implementation work remains
using file moves or renames as the primary state transition

Frequently asked questions

What does the Implement Execplan AI skill do?

Why use Implement Execplan on TypingMind?

Because you install it once and use it with any model. Implement Execplan 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 Implement Execplan in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/grp06/useful-codex-skills/tree/main/implement-execplan. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Implement Execplan?

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 Implement Execplan?

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

Is the Implement Execplan AI skill free?

Yes. It is published on GitHub by grp06 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

Deep Research

affaan-m

CommunityPopular

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

Documentation Lookup

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React,…

Everything Claude Code

affaan-m

CommunityPopular

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

Discord User Post

Post an approved message as the logged-in Discord user through the Discord desktop app. Use for release announcements or other direct user-authored Discord posts; not for OpenClaw channel sends, bots,…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Implement ExecPlan

Preferred Input Resolution

Work Item Responsibilities

Ousterhout Lens

Workflow

Implementation-First Rule

Anti-Patterns

Frequently asked questions

Related AI Skills

Set up your own AI workspace now