plan-mode
Structured planning mode for AI agents working on coding and development tasks.
Skill by espennilsen
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/espennilsen-plan-mode
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/plan-mode
What's inside
- Skill name
plan-mode- Description
- Structured planning mode for AI agents working on coding and development tasks. Produces a comprehensive plan BEFORE any code is written or changed, including task decomposition, architecture decisions, risk assessment, and approval gates. Use this skill whenever the user says "/plan", "plan mode", "plan first", "think before coding", "make a plan", or asks the agent to plan before executing. Also trigger when the user describes a complex multi-step development task and would clearly benefit from structured planning before implementation — especially for tasks involving new features, refactors, migrations, infrastructure changes, or multi-file edits. When in doubt, plan. A few minutes of planning prevents hours of rework.
- License
- MIT
- Instructions
- 205 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Plan Mode
When triggered, switch into **planning mode**: analyze the task, produce a structured plan, and wait for explicit user approval before writing any code or making changes.
The core philosophy: **think deeply, communicate clearly, execute only when aligned.**
## When to Enter Plan Mode
- User explicitly requests it (`/plan`, "plan this", "think first", etc.)
- Task touches 3+ files or components
- Task involves architecture decisions, new patterns, or breaking changes
- Task is ambiguous and could be approached multiple ways
- Task involves infrastructure, CI/CD, database changes, or migrations
- You're unsure about the right approach
## Plan Output Structure
Produce a plan with these sections. Adapt depth to task complexity — a small bug fix needs a lighter plan than a new feature.
### 1. Understanding (What)
Restate the task in your own words to confirm understanding. Call out any ambiguities or assumptions you're making. This catches misalignment early.
```
## Understanding
[Restate the goal in 2-3 sentences]
**Assumptions:**
- [List anything you're assuming that wasn't explicitly stated]
**Open questions:**
- [List anything you need clarified before proceeding]
```
If there are open questions that would significantly change the approach, STOP here and ask the user before continuing with the plan. Don't build a full plan on shaky assumptions.
### 2. Approach Options (How)
For non-trivial tasks, present 2-3 distinct approaches. For simple tasks, present one recommended approach with brief justification.
For each option include:
- **Summary**: One-line description
- **How it works**: Key implementation steps (keep high-level, not line-by-line)
- **Pros**: Why this approach is good
- **Cons**: Tradeoffs and risks
- **Effort estimate**: Relative complexity (small / medium / large)
End with a clear recommendation and why.
```
## Approach Options
### Option A: [Name]
**Summary:** [One line]
**How it works:** [3-5 bullet points, high-level]
**Pros:** [What's good about this]
**Cons:** [Tradeoffs]
**Effort:** [small / medium / large]
### Option B: [Name]
...
**Recommendation:** Option [X] because [reason tied to project context].
```
### 3. Task Breakdown (Steps)
Break the chosen (or recommended) approach into concrete, ordered steps. Each step should be small enough to verify independently. Group related steps into phases.
```
## Task Breakdown
### Phase 1: [Name, e.g. "Setup / Preparation"]
- [ ] Step 1.1: [Concrete action]
- [ ] Step 1.2: [Concrete action]
**Checkpoint:** [What should be true after this phase — a testable condition]
### Phase 2: [Name, e.g. "Core Implementation"]
- [ ] Step 2.1: [Concrete action]
- [ ] Step 2.2: [Concrete action]
**Checkpoint:** [Testable condition]
### Phase 3: [Name, e.g. "Verification & Cleanup"]
- [ ] Step 3.1: [Concrete action]
- [ ] Step 3.2: [Concrete action]
**Checkpoint:** [Testable condition]
```
Guidelines for good steps:
- Each step modifies 1-2 files at most
- Steps are ordered so the project stays in a working state after each phase
- Include test/verification steps, not just implementation
- Checkpoints are concrete and testable ("tests pass", "server starts", "endpoint returns 200")
### 4. Risk Assessment
Identify what could go wrong and how to mitigate it. Focus on risks specific to *this* task, not generic software risks.
```
## Risks
| Risk | Likelihood | Impact | Mitigation |
|------|-----------|--------|------------|
| [Specific thing that could go wrong] | low/med/high | low/med/high | [How to prevent or handle it] |
```
Always consider:
- **Breaking changes**: Will this break existing functionality? Which consumers/callers are affected?
- **Data implications**: Any database migrations, data loss risk, or state changes?
- **Rollback**: If this goes wrong, how hard is it to undo?
- **Dependencies**: External services, libraries, or team coordination needed?
### 5. Files & Scope
List the files that will be created, modified, or deleted. This helps the user understand the blast radius.
```
## Affected Files
- **Create:** `path/to/new-file.ts` — [purpose]From espennilsen/pi, MIT.
More from espennilsen/pi
- 0.739score
herdr-setup
espennilsen
Use when installing, updating, configuring, or troubleshooting Herdr, including missing commands, PATH errors, version differences, or Pi integration setup.
SkillBFreshness: B★ 122Claude Code +9 - 0.739score
herdr-operations
espennilsen
Use when inspecting or operating Herdr sessions, workspaces, tabs, panes, agents, terminal output, agent messaging, or waits.
SkillBFreshness: B★ 122Claude Code +9 - 0.729score
cmux
espennilsen
Orchestrate cmux terminal panes — split terminals, run parallel processes, read output from other panes, and use the built-in browser.
SkillBFreshness: B★ 122Claude Code +9 - 0.726score
pi-subagent
espennilsen
Delegate tasks to specialized subagents for parallel or sequential execution.
SkillBFreshness: B★ 122Claude Code +9 - 0.681score
github
espennilsen
Interact with GitHub repos, PRs, issues, CI, and notifications via the pi-github extension commands and gh CLI.
SkillCFreshness: C★ 122Claude Code +9 - 0.676score
docstring-generator
espennilsen
Generate and update language-idiomatic doc comments for TypeScript (TSDoc/JSDoc) and Rust (Rustdoc).
SkillCFreshness: C★ 122Claude Code +9 - 0.671score
comfyui-node-update
espennilsen
Write and improve documentation for ComfyUI nodes in per-node JSON files.
SkillCFreshness: C★ 122Claude Code +9 - 0.607score
dry-code-review
espennilsen
Perform a comprehensive DRY (Don't Repeat Yourself) code review on a codebase.
SkillDFreshness: D★ 122Claude Code +9 - 0.607score
pdf-reader
espennilsen
Read and extract content from PDF files — text, tables, metadata, and images.
SkillDFreshness: D★ 122Claude Code +9 - 0.607score
extract-design-system
espennilsen
Reverse-engineer a design system from a live website (public URL or localhost).
SkillDFreshness: D★ 122Claude Code +9 - 0.607score
codebase-docs
espennilsen
Generate and maintain AI-readable markdown documentation for a codebase in docs/.
SkillDFreshness: D★ 122Claude Code +9 - 0.607score
google-workspace
espennilsen
Manage Google Workspace via the gws CLI — Drive, Gmail, Sheets, Docs, Slides, People, Chat, Meet, Forms, and cross-service workflows.
SkillDFreshness: D★ 122Claude Code +9
Signals
- Stars
- 122
- Forks
- 13
- Open issues
- 1
- Last commit (this folder)
- Apr 22, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/espennilsen/pi
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from espennilsen
- 0.739score
herdr-setup
espennilsen
Use when installing, updating, configuring, or troubleshooting Herdr, including missing commands, PATH errors, version differences, or Pi integration setup.
SkillBFreshness: B★ 122Claude Code +9 - 0.739score
herdr-operations
espennilsen
Use when inspecting or operating Herdr sessions, workspaces, tabs, panes, agents, terminal output, agent messaging, or waits.
SkillBFreshness: B★ 122Claude Code +9 - 0.729score
cmux
espennilsen
Orchestrate cmux terminal panes — split terminals, run parallel processes, read output from other panes, and use the built-in browser.
SkillBFreshness: B★ 122Claude Code +9 - 0.726score
pi-subagent
espennilsen
Delegate tasks to specialized subagents for parallel or sequential execution.
SkillBFreshness: B★ 122Claude Code +9 - 0.681score
github
espennilsen
Interact with GitHub repos, PRs, issues, CI, and notifications via the pi-github extension commands and gh CLI.
SkillCFreshness: C★ 122Claude Code +9 - 0.676score
docstring-generator
espennilsen
Generate and update language-idiomatic doc comments for TypeScript (TSDoc/JSDoc) and Rust (Rustdoc).
SkillCFreshness: C★ 122Claude Code +9
Cite this page
plan-mode skill. Agent Mart. https://agentmart.dev/skills/espennilsen-plan-mode (last updated 2026-10-24)