/simple-plan
Quick gut-check before implementing when the user directly asks you to do something (e.g. "add X", "fix Y", "change Z"). Investigates, proposes a lightweight plan, and implements after approval. Use this instead of /create-plan when the user wants something done, not a formal
$ npx -y skills add dcouple/Pane --skill simple-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/simple-plan
Context preview
The summary Claude sees to decide when to auto-load this skill.
Quick gut-check before implementing when the user directly asks you to do something (e.g. "add X", "fix Y", "change Z"). Investigates, proposes a lightweight plan, and implements after approval. Use this instead of /create-plan when the user wants something done, not a formal
SKILL.md
simple-plan.SKILL.mdname: simple-plan
description: Quick gut-check before implementing when the user directly asks you to do something (e.g. "add X", "fix Y", "change Z"). Investigates, proposes a lightweight plan, and implements after approval. Use this instead of /create-plan when the user wants something done, not a formal plan.
argument-hint: "[what the user wants done]"
allowed-tools: Read, Grep, Glob, WebFetch
Simple Plan
When the user directly asks me to make a change, I will first investigate and propose a plan before implementing anything. This ensures alignment before any code is written.
My Plan Will Include
Current State
- Root cause analysis explaining the current state
- File references and code snippets where relevant
Proposed Changes
- Clear explanation of what needs to change
- File references and code snippets where necessary
- Task list of all work to be done
My Advice
Feedback from a principal engineer perspective, providing overall architectural and implementation guidance.
Process
1. Investigate the codebase first 2. Present the plan to the user 3. **Only when the user approves** will I proceed 4. After approval, prefer one primary `implementer` sub-agent to execute the whole plan rather than fragmenting it by default 5. Keep the user's stated why, constraints, and non-goals explicit during implementation rather than letting the task list silently replace them 6. After implementation, run the Claude `implementation-reviewer` and Codex review in parallel when the plugin is available, and wait for both before declaring completion 7. If the Codex plugin is unavailable, run the Claude `implementation-reviewer` alone before declaring completion
Notes
- Instructions must be very clear with code snippets and file paths
- If implementation proceeds, keep one primary implementation authority unless the write scopes are clearly disjoint
- The final review must check both task completion and whether the implementation still satisfies the user's original intent
- I will not implement anything until the user approves
User Query: $ARGUMENTS
Read more
name: simple-plan description: Quick gut-check before implementing when the user directly asks you to do something (e.g. "add X", "fix Y", "change Z"). Investigates, proposes a lightweight plan, and implements after approval. Use this instead of /create-plan when the user wants something done, not a formal plan. argument-hint: "[what the user wants done]" allowed-tools: Read, Grep, Glob, WebFetch
Simple Plan
When the user directly asks me to make a change, I will first investigate and propose a plan before implementing anything. This ensures alignment before any code is written.
My Plan Will Include
Current State
- Root cause analysis explaining the current state
- File references and code snippets where relevant
Proposed Changes
- Clear explanation of what needs to change
- File references and code snippets where necessary
- Task list of all work to be done
My Advice
Feedback from a principal engineer perspective, providing overall architectural and implementation guidance.
Process
1. Investigate the codebase first 2. Present the plan to the user 3. **Only when the user approves** will I proceed 4. After approval, prefer one primary `implementer` sub-agent to execute the whole plan rather than fragmenting it by default 5. Keep the user's stated why, constraints, and non-goals explicit during implementation rather than letting the task list silently replace them 6. After implementation, run the Claude `implementation-reviewer` and Codex review in parallel when the plugin is available, and wait for both before declaring completion 7. If the Codex plugin is unavailable, run the Claude `implementation-reviewer` alone before declaring completion
Notes
- Instructions must be very clear with code snippets and file paths
- If implementation proceeds, keep one primary implementation authority unless the write scopes are clearly disjoint
- The final review must check both task completion and whether the implementation still satisfies the user's original intent
- I will not implement anything until the user approves
User Query: $ARGUMENTS
Repo: dcouple/Pane
Other skills on pane.
- /commit
Selectively stages and commits only the changes related to the current session, skipping unrelated modifications.
Open skill - /create-plan
Creates a reconciled implementation plan by combining a structured plan draft with a normalized intent brief and a PRP-style research dossier, then auto-reviews the final plan. Use when planning a new feature or significant change.
Open skill - /discussion
Have an interactive discussion about a topic, approach, or feature. Researches the codebase as needed, talks through options, and updates ./tmp/context.md with decisions. Use when you want to think through an approach before planning.
Open skill - /implement
Executes an approved plan with one primary implementation stream by default, using bounded parallel sidecars only when the write scopes are truly disjoint. Supports default Claude execution or an explicit Codex executor option. Automatically reviews the result for completeness
Open skill - /investigate
Investigates bugs through hypothesis-driven root cause analysis. Automatically invoked when the user reports a bug, error, broken behavior, or something not working as expected. Use when something is broken, failing, or behaving unexpectedly.
Open skill - /prepare-pr
Commits changes grouped by done-plans, rebases main, builds API and webapp, then creates or updates a PR. Replaces the commit command. Use when you're ready to open or update a pull request.
Open skill

