Github Planner
Productivitygithub-plannerGithub Planner is an Agent Skill for productivity published in the syi0808/screenize repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Fetch a GitHub issue and create a detailed implementation plan. Use when given a GitHub issue URL or number to analyze the issue, explore relevant codebase areas, and produce a step-by-step implementation plan with file changes, architecture considerations, and risk assessment.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/syi0808/screenize/blob/HEAD/.claude/skills/github-planner/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/github-planner, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
GITHUB ISSUE IMPLEMENTATION PLANNER
Fetch a GitHub issue, analyze its requirements, explore the relevant codebase, and produce a comprehensive implementation plan.
When to use: Execute /plan-issue with a GitHub issue URL or number to generate an implementation plan before starting work.
Step 1: Fetch Issue
Run the fetch script to retrieve issue details:
uv run .claude/skills/github-planner/scripts/fetch_issue.py <issue_url_or_number>
Accepts:
- Full URL:
https://github.com/owner/repo/issues/123 - Short URL:
owner/repo#123 - Issue number (uses current repo):
123or#123
The script outputs structured JSON with title, body, labels, comments, and metadata.
Step 2: Analyze Issue
Parse the fetched issue content and identify:
- Problem statement - What needs to be solved
- Proposed solution - If described in the issue
- Acceptance criteria - Explicit or inferred requirements
- Scope boundaries - What is and isn't included
Step 3: Explore Codebase
Based on the analysis, explore relevant parts of the codebase:
- Use Glob/Grep to find files related to the issue's domain
- Read key files to understand current architecture
- Identify integration points and dependencies
- Check for existing patterns that the implementation should follow
- Reference
CLAUDE.mdfor project architecture and conventions
Step 4: Generate Implementation Plan
Write the plan to private-docs/plans/<issue-number>-<slug>.md using the template:
uv run .claude/skills/github-planner/scripts/create_plan.py \
--issue <number> \
--title "<issue-title-slug>"
Fill the generated template with:
- Overview: Issue summary and goals
- Architecture Analysis: How changes fit into existing architecture
- Implementation Steps: Ordered tasks with specific file changes
- Files to Modify/Create: Exhaustive list with descriptions
- Risk Assessment: Potential issues, edge cases, breaking changes
- Testing Strategy: How to verify the implementation
Step 5: Present Plan
After writing the plan file, present a concise summary to the user:
- Key architectural decisions
- Number of files affected
- Implementation order
- Any open questions or ambiguities from the issue
- Language: All plans MUST be written in English (per CLAUDE.md)
- Specificity: Reference exact file paths and function names
- Actionable: Each step should be independently implementable
- Architecture-aware: Respect existing patterns from CLAUDE.md
- Scope-bounded: Do not plan beyond what the issue requests
- Plan template - Markdown template for implementation plans