Remember Interactive Programming — Agent Skill by GitHub

From the author

A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that has a live REPL that the agent can use. Adapt the prompt with any specific reminders in your workflow and/or workspace.

— the description by PEZ

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a micro-prompt designed to shift an AI agent's operational mode toward interactive programming. By emphasizing the REPL as the primary source of truth, the agent is encouraged to explore and modify the system dynamically rather than relying solely on static file editing. It includes specific behavioral guidelines for communicating evaluation results to the user and prioritizing structural editing techniques.

What it does

Establishes a persona focused on interactive, REPL-driven development.
Instructs the agent to use the live system state as the ultimate source of truth.
Provides guidelines for summarizing large code evaluations to the user.
Encourages the use of structural editing tools for file modifications.
Reminds the agent to maintain and update a todo list during the session.

When to use it

When working in environments with live REPL access, such as Clojure development.
When you want the agent to prioritize system exploration over static code generation.
When you need the agent to maintain a consistent workflow involving iterative testing and evaluation.
When using agents that support structural editing and task tracking.

Advantages

Promotes a more iterative and accurate development process.
Reduces ambiguity by grounding the agent's logic in live system feedback.
Improves communication by standardizing how evaluation results are reported.
Encourages cleaner code modifications through structural editing.

Usage examples

“Remember that you are an interactive programmer. Given the current REPL state, how should I refactor this function?”: The agent will adopt the interactive persona, evaluate the function in the REPL to understand its current behavior, and propose refactoring steps based on live feedback.
“Apply the interactive programmer persona and check the todo list for the next task.”: The agent will acknowledge the persona, review the existing todo list, and proceed with the next task using REPL-driven exploration.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/github/remember-interactive-programming/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip remember-interactive-programming.zip -d .agents/skills

Documentation by PEZ

Remember that you are an interactive programmer with the system itself as your source of truth. You use the REPL to explore the current system and to modify the current system in order to understand what changes need to be made.

Remember that the human does not see what you evaluate with the tool:

If you evaluate a large amount of code: describe in a succinct way what is being evaluated.

When editing files you prefer to use the structural editing tools.

Also remember to tend your todo list.

Files

ATTRIBUTION.mdAdded by AutoGineer1.2 KiB
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md882 B

Requirements and compatibility

Written for: GitHub Copilot

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Handoff
Matt Pocock· Community
Generates a concise handoff document to facilitate seamless transitions between AI agents.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Chief Of Staff
Matt Pocock· Community
A strategic orchestration agent that manages long-term goals by coordinating subagents and maintaining a persistent knowledge wiki.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Ask Matt
Matt Pocock· Community
A central routing skill that helps you identify the correct agent skill or workflow for your current situation.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Claude Handoff
Matt Pocock· Community
Seamlessly transfer your current conversation context to a new background agent.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Executing Plans
Jesse Vincent (obra)· Community
Execute implementation plans inline without subagents, maintaining rigorous progress tracking and verification.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository314k
Using Superpowers
Jesse Vincent (obra)· Community
A mandatory protocol for AI agents to identify and invoke relevant skills before performing any task or responding to user input.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository314k