plan-issue
Plan-only workflow for issue/repo changes. Use when user asks to plan, scope, estimate, or design.
Best use case
plan-issue is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Plan-only workflow for issue/repo changes. Use when user asks to plan, scope, estimate, or design.
Teams using plan-issue should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/plan-issue/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How plan-issue Compares
| Feature / Agent | plan-issue | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Plan-only workflow for issue/repo changes. Use when user asks to plan, scope, estimate, or design.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Plan-Issue Skill ## Use This Skill When - The user asks to plan implementation. - The user asks for scope, sequencing, risks, or rollout strategy. - The task is non-trivial and would change files, infra, or workflows. ### Proactive Trigger Matrix Use `/plan` proactively when any of these apply: - New feature implementation with non-obvious design choices. - Multiple valid approaches exist and tradeoff selection matters. - Changes are likely to touch more than 2-3 files. - Existing behavior/architecture will change. - Requirements are partially unclear and need repo exploration first. - User preference materially affects implementation direction. Skip `/plan` for: - Trivial typo or obvious one-line fixes. - Small deterministic edits with no architectural impact. - Pure information lookup requests (no implementation intent). ## Required Workflow 1. Gather context using read-only operations first. 2. Build a concrete implementation plan that includes: - Goal and acceptance criteria. - In-scope and out-of-scope. - Step-by-step execution plan. - Assumptions and risks/failure modes. - Test/validation checklist. - At least one alternative with tradeoffs. 3. End with a hard gate: - `Reply APPROVE to execute this plan.` ## Hard Limits - No file writes. - No package installation. - No commits, PRs, or system-changing commands. - If the user requests immediate implementation, still provide the plan unless they explicitly say to skip planning. ## Command Alias `/plan` is a channel alias for this skill. ## Handoff Contract At the end of every plan response, include: - `Reply APPROVE to execute this plan.` If the user sends `APPROVE` in the same conversation context, execution may proceed via `coding-agent`.
Related Skills
implement_plan
Implement technical plans from thoughts/shared/plans with verification
building-a-work-plan
Use when orchestrating the creation of a work plan from a design document. Manages branch setup, codebase investigation, milestone planning, and execution handoff.
adhd-daily-planner
Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.
accessibility-planning
Plan accessibility compliance - WCAG 2.2, Section 508, EN 301 549, inclusive design principles, audit planning, and remediation strategies.
verify-issue
Verify a completed issue by comparing implementation against acceptance criteria, running tests, and critiquing the work. Adds review notes as a comment on the ticket. Supports both Linear and Jira backends via progressive disclosure. Use as the final step in the issue workflow after execute-issue, when the user mentions "verify", "review", or "check" an issue.
speckit-plan
Generate technical implementation plans from feature specifications. Use after creating a spec to define architecture, tech stack, and implementation phases. Creates plan.md with detailed technical design.
skill-issue
Audit and review all installed agent skills. Run on-demand or via cron to get a health report: skill inventory, usage tracking, version checks, dependency health, and actionable recommendations (keep, update, review, remove). Use when asked to review skills, check for skill updates, find unused skills, or audit the skill ecosystem.
quant-plan-reviewer
Use when reviewing implementation plans for quantitative trading systems before execution - catches data leakage, look-ahead bias, scalability risks, and production pitfalls
planning-phase
Generates implementation plans with code reuse analysis, architecture design, and complexity estimation during the /plan phase. Use when planning feature implementation, analyzing code reuse opportunities, or designing system architecture after specification phase completes. Integrates with 8 project documentation files for constraint extraction. (project)
plan-refiner
Generate and iteratively refine implementation plans from an initial spec/prompt. Takes a specification as input, generates an initial plan, then refines it through multiple review passes (minimum 3) with fresh agent context. User can continue beyond 3 passes until satisfied. Use when turning requirements into polished implementation plans.
kitt-create-plans
Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that the AI agent will execute. Produces agent-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]