Planning And Task Breakdown
skuramatata/my-pi-agent
A skill your agent uses when my-pi-agent work needs requirement slicing, implementation planning, multi-step ordering, dependency decisions, or clear acceptance criteria before coding.
Runs new features, scripts and structural changes through explore, design, approval, implementation and verification phases, with a tool search and an explicit plan sign-off.
Install Plan and Implement Workflow
$ npx skills add mp-web3/claude-starter-kit --skill plan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mp-web3/claude-starter-kit plan --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mp-web3/claude-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/plan-and-implement .claude/skills/plan && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "plan" agent skill from https://github.com/mp-web3/claude-starter-kit/tree/main/skills/plan-and-implement into .claude/skills/plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mp-web3/claude-starter-kit/tree/main/skills/plan-and-implementType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mp-web3/claude-starter-kit --skill plan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mp-web3/claude-starter-kit plan --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mp-web3/claude-starter-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/plan-and-implement .agents/skills/plan && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "plan" agent skill from https://github.com/mp-web3/claude-starter-kit/tree/main/skills/plan-and-implement into .agents/skills/plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mp-web3/claude-starter-kit --skill plan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mp-web3/claude-starter-kit plan --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mp-web3/claude-starter-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/plan-and-implement .cursor/skills/plan && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "plan" agent skill from https://github.com/mp-web3/claude-starter-kit/tree/main/skills/plan-and-implement into .cursor/skills/plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mp-web3/claude-starter-kit.git --path skills/plan-and-implement--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mp-web3/claude-starter-kit --skill plan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mp-web3/claude-starter-kit plan --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mp-web3/claude-starter-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/plan-and-implement .gemini/skills/plan && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "plan" agent skill from https://github.com/mp-web3/claude-starter-kit/tree/main/skills/plan-and-implement into .gemini/skills/plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mp-web3/claude-starter-kit planInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mp-web3/claude-starter-kit --skill plan -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mp-web3/claude-starter-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/plan-and-implement .github/skills/plan && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "plan" agent skill from https://github.com/mp-web3/claude-starter-kit/tree/main/skills/plan-and-implement into .github/skills/plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mp-web3/claude-starter-kit --skill plan -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mp-web3/claude-starter-kit plan --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mp-web3/claude-starter-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/plan-and-implement .opencode/skills/plan && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "plan" agent skill from https://github.com/mp-web3/claude-starter-kit/tree/main/skills/plan-and-implement into .opencode/skills/plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
plan- GitHub stars
- 109
- Token cost
- ~913 tokens
- SKILL.md length
- 465 words
- Files
- 2
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Runs new features, scripts and structural changes through explore, design, approval, implementation and verification phases, with a tool search and an explicit plan sign-off.
- Works in 7 steps: Explore → 5: Tool Discovery (autonomy-first) → Design → …
- Adding a new skill, script or piece of infrastructure to a project
- SKILL.md covers Phase 1: Explore, Phase 1.5: Tool Discovery…, Phase 2: Design and Phase 3: Approve, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Before anything else the agent reads the skill's LEARNINGS.md, then works through the phases in order and does not implement before you approve. Exploration covers CLAUDE.md, any file map and related existing skills, with no proposals yet. A tool discovery step follows, looking for an existing MCP server or official SDK before any custom code, in that order of preference, and checking .mcp.json for servers already connected.
Design classifies the change as a skill, script, database, config, structure or other, lists the files to create and modify with their dependencies, and asks clarifying questions instead of guessing. The plan is presented under What, Why, How and Verify headings and ends with a request to approve it or suggest changes. Implementation, verification and an update step come after your approval.
When your agent uses it
- Adding a new skill, script or piece of infrastructure to a project
- Making an architectural change that deserves an approved plan first
- Checking whether an MCP server or SDK already covers a service before writing a wrapper
Example prompts
- “Add a skill that summarizes my weekly calendar. Explore first and show me a plan.”
- “Plan and implement a nightly backup script for the notes folder.”
- “Before writing any code, check whether an MCP server exists for Todoist.”
Requirements
- The skill's LEARNINGS.md file, which the agent reads first
- Pre-approved tools (allowed-tools): Read, Grep, Glob, Write, Edit, Bash, WebSearch, WebFetch, AskUserQuestion
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 546c72c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepGlobWriteEditBashWebSearchWebFetchAskUserQuestion
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Plan and Implement Workflow loads about 913 tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 465 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Grep, Glob, Write, Edit, Bash, WebSearch, WebFetch, AskUserQuestion
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mp-web3/claude-starter-kit at commit 546c72c, republished under its MIT licence (© mp-web3). 465 words, ~913 tokens.
Download SKILL.mdSave it as
.claude/skills/plan/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- plan
- description
- Structured workflow for planning and implementing new features, skills, scripts, or major changes. Use when the user asks to build something new, add a skill, create infrastructure, or make architectural changes. Guides through explore, plan, approve, implement, verify, update.
- allowed-tools
- Read, Grep, Glob, Write, Edit, Bash, WebSearch, WebFetch, AskUserQuestion
- disable-model-invocation
- true
- argument-hint
- [feature description]
Plan & Implement Workflow
First: Read LEARNINGS.md (in this skill's directory) before proceeding.
You are executing a structured 6-phase workflow for building or changing project features. Follow each phase in order. Do NOT skip phases or start implementing before approval.
The user's request: $ARGUMENTS
Phase 1: Explore
Understand the current project state before designing anything.
- Read
CLAUDE.mdfor project conventions, key paths, and existing skills - Look for a file map or project structure documentation
- Read any existing skills, scripts, or files that relate to what's being built
- Identify reusable patterns, utilities, or templates from existing code
Do NOT propose anything yet — just gather context.
Phase 1.5: Tool Discovery (autonomy-first)
Before designing a custom solution, search for existing tools that do the job.
- Search for MCP servers — WebSearch for
"<service-name> MCP server"on GitHub/npm/PyPI - Search for official SDKs — Check if the service has an official Python/Node SDK
- Check existing MCP servers — Read
.mcp.jsonfor already-connected servers - Evaluate options: MCP server > official SDK > custom wrapper
- If an MCP server exists: configure it in
.mcp.jsoninstead of writing custom code - If no MCP server: proceed with custom implementation but note it as a future improvement target
Phase 2: Design
Classify what's being built and design the implementation.
- Classify the change type: skill / script / database / config / structure / other
- List files to create (with paths) and files to modify
- Define dependencies between files (what must be created first)
- Detail the design based on type
- Ask clarifying questions via AskUserQuestion if requirements are ambiguous — do NOT guess
Phase 3: Approve
Present the plan and wait for explicit approval.
Format the plan as:
Show full SKILL.md (185 more words)Show less
What
- Files to create (path + one-line description each)
- Files to modify (path + what changes)
Why
- What problem this solves or capability it adds
How
- Implementation order with dependencies noted
- Key design decisions and rationale
Verify
- Specific steps to confirm it works after implementation
Then ask: "Approve this plan, or suggest changes?"
Do NOT proceed to Phase 4 until the user approves.
Phase 4: Implement
Execute the approved plan step by step.
- Create directories first, then files in dependency order
- For each file: write it, verify it exists and is well-formed
- For each modification: read current file, make edit, verify change
- Follow all project conventions from CLAUDE.md
Phase 5: Verify
Run the verification steps defined in the approved plan. Report results. If anything fails, fix it before proceeding.
Phase 6: Update Project Files
Update all project metadata to reflect the changes.
- Update any file map or structure documentation
- Update
CLAUDE.mdif the change affects skills, paths, or workflows - Update settings files if new permissions or hooks are needed
- Confirm all updates are done, then summarize what was built
© mp-web3, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/plan-and-implement of mp-web3/claude-starter-kit.
- SKILL.md
- LEARNINGS.md
Open the folder on GitHubat commit 546c72c
Compare with similar skills
Plan and Implement Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Plan and Implement Workflow this skillmp-web3/claude-starter-kit | 109 | — | ~913 | Automated safety check: Notes | MIT | |
| Planning And Task Breakdownskuramatata/my-pi-agent | 114 | — | ~679 | Automated safety check: Pass | None | |
| Codex with ChatGPT Planning LoopXiaoDuoYa/codex-with-chatgpt | 7.1k | — | ~11k | Automated safety check: Notes | MIT | |
| MemPalace Task HandoffMemPalace/mempalace | 59k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Ask User QuestionMemTensor/MemOS | 12k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Planning And Task Breakdownabashev/vfs-s3 | 106 | 8 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Codex with ChatGPT Planning Loop
XiaoDuoYa/codex-with-chatgpt
Uses ChatGPT in the browser as the planning and review brain for a Codex session, with Codex keeping all execution and ChatGPT reading the workspace through a bridge.
MemPalace Task Handoff
MemPalace/mempalace
Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.
Ask User Question
MemTensor/MemOS
Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.
Planning And Task Breakdown
abashev/vfs-s3
Breaks work into ordered tasks. An agent skill from abashev/vfs-s3.
Agentmemory Forget
rohitg00/agentmemory
Deletes chosen memories from agentmemory only after showing the matches and getting an explicit yes, for privacy requests and cleanup of outdated notes.
More from mp-web3/claude-starter-kit
Create Skill
mp-web3/claude-starter-kit
Walks through building a new Claude Code skill: asks what it should do, scaffolds it with an init script, writes SKILL.md and LEARNINGS.md and validates the result.
Claude Project Bootstrap
mp-web3/claude-starter-kit
Sets up a project for Claude Code by surveying it and writing a .claude folder with a short CLAUDE.md, a CODEBASE.md overview, module docs and optional skills and hooks.
Personal Assistant Onboarding
mp-web3/claude-starter-kit
Walks a new user through a five-step first session, profile, problems, goals and initial tasks, to turn the agent into a personal assistant that remembers them.
Session Reflection Learnings
mp-web3/claude-starter-kit
Analyzes recent sessions for corrections, preferences and implicit feedback, then routes the real learnings to the right knowledge or rules file.
Task Backlog Manager
mp-web3/claude-starter-kit
Keeps a personal task backlog in SQLite behind a /tasks command that adds, reviews, completes and measures tasks against a list of long-term problems.
Related
Works with
Categories
Questions about Plan and Implement Workflow
What does Plan and Implement Workflow do?
Runs new features, scripts and structural changes through explore, design, approval, implementation and verification phases, with a tool search and an explicit plan sign-off. md, then works through the phases in order and does not implement before you approve.md, any file map and related existing skills, with no proposals yet.
When should I use Plan and Implement Workflow?
Plan and Implement Workflow fits situations like: adding a new skill, script or piece of infrastructure to a project; making an architectural change that deserves an approved plan first; checking whether an MCP server or SDK already covers a service before writing a wrapper.
How do I install Plan and Implement Workflow in Claude Code?
Run `npx skills add mp-web3/claude-starter-kit --skill plan -a claude-code`. Or copy the skill folder (skills/plan-and-implement in mp-web3/claude-starter-kit) into .claude/skills/plan in your project. Claude Code loads it when a task matches its description.
How do I install Plan and Implement Workflow in Codex?
Run `npx skills add mp-web3/claude-starter-kit --skill plan -a codex`. Or copy the skill folder (skills/plan-and-implement in mp-web3/claude-starter-kit) into .agents/skills/plan in your project. Codex loads it when a task matches its description.
Can I use Plan and Implement Workflow in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mp-web3/claude-starter-kit --skill plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plan, .gemini/skills/plan, .github/skills/plan and .opencode/skills/plan in your project.
What does Plan and Implement Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Plan and Implement Workflow is instructions for the agent only. Our summary lists: The skill's LEARNINGS.md file, which the agent reads first. Its frontmatter pre-approves these tools: Read, Grep, Glob, Write, Edit, Bash, WebSearch, WebFetch, AskUserQuestion.
Does Plan and Implement Workflow access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Plan and Implement Workflow safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Plan and Implement Workflow use?
Plan and Implement Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Plan and Implement Workflow use?
About 913 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Plan and Implement Workflow?
Skills that share tags, products or a category with Plan and Implement Workflow: Planning And Task Breakdown (skuramatata/my-pi-agent, 114 stars), Codex with ChatGPT Planning Loop (XiaoDuoYa/codex-with-chatgpt, 7.1k stars), MemPalace Task Handoff (MemPalace/mempalace, 59k stars) and Ask User Question (MemTensor/MemOS, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Plan and Implement Workflow?
mp-web3 (a GitHub user) maintains it in mp-web3/claude-starter-kit, which has 109 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on March 18, 2026.
Source: mp-web3/claude-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.