One-Shot Feature Issue Planner
Turns a single feature request into a complete, issue-ready GitHub issue draft in one pass, no clarifying questions, inferring missing details from the codebase and labeling every assumption it makes explicitly.
Overview
One-Shot Feature Issue Planner is built around a hard constraint: it cannot ask you anything. Every gap in your request gets filled with an inferred, explicitly labeled assumption instead of a follow-up question.
How it works
- It inspects the codebase before proposing anything: architecture, similar existing features, naming patterns and test locations, so the plan reflects real project conventions rather than generic advice.
- When the request is underspecified, it resolves ambiguity by preferring the smallest complete feature that satisfies the request, then documents every inferred detail in its own Assumptions section rather than hiding the guess.
- The output follows a fixed template: problem statement, goals, non-goals, assumptions, technical approach, phased implementation tasks as checklists, testable acceptance criteria, edge cases, non-functional requirements, risks and a testing plan.
- Every acceptance criterion has to be independently testable, and every implementation task has to be concrete and sequential enough that another engineer or agent could execute it without re-interpreting it.
- It plans only. It won't write source files or make code changes; the entire output is meant to be pasted directly into a new GitHub issue.
Examples
"Plan a feature that lets users export their saved reports as CSV."
Installation
You need VS Code with the GitHub Copilot extension.
- Create the agents folder and download the file into your repo:
mkdir -p .github/agents curl -o .github/agents/one-shot-feature-issue-planner.agent.md \ https://raw.githubusercontent.com/github/awesome-copilot/main/agents/one-shot-feature-issue-planner.agent.md - Reload VS Code, or open a new Copilot Chat; custom agents under
.github/agents/are picked up automatically. - Pick this agent from the mode picker in Copilot Chat and describe a feature to confirm it returns a full issue draft in one pass, with no clarifying questions.
Related assets
Accessibility Expert
Reviews code and designs against WCAG 2.1/2.2, covering semantics, keyboard and focus behavior, forms, media and dynamic SPA updates, and ships framework-specific examples plus a CI setup for automated checks.
Address Comments Agent
Works through pull request review comments one at a time: applies the minimal fix for each, pushes back on comments that don't make sense, adds test coverage, and commits with a descriptive message before moving to the next comment.
ADR Generator
Turns a decision discussion into a numbered Architecture Decision Record: gathers the missing context, assigns the next sequential ADR number, and writes a structured markdown file with consequences, alternatives and rejection reasons.