Skip to content
Agentmart
Submit a tool

planning-workflow

Use a structured planning workflow to produce an implementation-ready Builder handoff grounded in the actual repository.

Skill by judepayne

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying planning-workflow?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/judepayne-planning-workflow

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.

We use your email only for this newsletter. Privacy

About

Use a structured planning workflow to produce an implementation-ready Builder handoff grounded in the actual repository.

Use cases: productivity

No 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. Checked Oct 25, 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/planning-workflow

What's inside

Skill name
planning-workflow
Description
Use a structured planning workflow to produce an implementation-ready Builder handoff grounded in the actual repository.
License
MIT
Instructions
82 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Planning Workflow

Use this skill when you need to produce or refine an implementation plan.

## Goal

Turn the request into a Builder-ready plan grounded in the repository as it exists now.

## Default posture

- inspect before concluding
- keep source code read-only
- ask 1-3 focused planning questions before finalizing unless the answers would not change the plan
- use subagents for reconnaissance, not for the planning judgment
- if the prompt already names an active plan or design file, treat those as the authoritative artifacts

## Workflow

### 1. Frame the task
- restate the request in precise technical terms
- identify the goal, constraints, likely validation, and the files or subsystems most likely involved

### 2. Inspect the code
- read the relevant entry points, types, configuration, tests, and nearby call paths
- prefer targeted inspection over broad scanning
- if the scope spans multiple subsystems or patterns, use 1-3 exploratory subagents in parallel
- use a chain only when later reconnaissance depends on earlier findings

### 3. Clarify
Ask brief questions only where the answers would materially change:
- scope
- sequencing
- migration behavior
- validation expectations
- non-goals
- compatibility constraints

If you skip questions, say explicitly why they would not change the plan.

### 4. Design the plan
For each impacted file or area, capture:
- what changes
- why it belongs there
- dependencies or sequencing constraints
- risks, edge cases, or likely failure modes
- what was verified directly versus inferred

Consider alternatives only when there is a real design choice.

### 5. Validate the plan
This validation is Planner-owned. Do not delegate the completed plan for review unless the user explicitly requests an independent review.

Before finalizing:
- re-read the highest-risk files
- check the plan against the user's request
- make it can be executed it without reinterpretation
- ensure validation steps are included
- Does the documentation need to change? If so, include those steps

### 6. Produce the handoff
The final handoff should usually include:
- a short summary
- assumptions or open questions
- ordered implementation steps
- file-by-file impacts
- validation steps
- rollout or migration notes when relevant

For larger work (more than half a day's work), split the plan into phases.

## Output

- In chat, either ask the focused questions or present the final plan.
- In the saved plan file, keep the definitive Builder handoff version.

## Stop conditions

- If the user wants implementation now, stop and suggest an implementation mode.
- If the task is still under-shaped and needs architecture or interface work, suggest a design mode.
- If the user wants review of existing code rather than a forward plan, suggest a review mode.

From judepayne/picode, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 11, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from judepayne

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get planning-workflow running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying planning-workflow?

CallGet help
Cite this page

planning-workflow skill. Agent Mart. https://agentmart.dev/skills/judepayne-planning-workflow (last updated 2026-10-24)