agentleFS
Sign inStart free
anaidenkoanaidenko/claude-notify-resume/.claude/skills/plan-task/SKILL.md

plan-task

Skill1 starsChanged 4 months agoMITView on GitHub

Generate structured implementation plans for complex tasks before coding. Explores the codebase, identifies critical files, designs an approach, and breaks work into concrete steps saved to .claude/plans/.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ship, handoff and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 4 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the task description from $ARGUMENTS.

    line 15
  2. Distinctive:

    Read key files to understand existing patterns and conventions.

    line 18
  3. Distinctive:

    Consider platform differences (macOS vs Linux) and how the change will be tested without a real banner.

    line 23
  4. Distinctive:

    After saving the plan, display it to the user and ask:

    line 61
  5. Distinctive:

    If the user says yes, begin executing the steps in order, marking each complete before moving to the next.

    line 64
  6. Distinctive:

    Do not write any implementation code until the plan is saved and the user confirms.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plan Task Skill

Generate a structured implementation plan for a complex task before writing any code.

Usage: /plan-task [description of the task]

Steps:

  1. Read the task description from $ARGUMENTS. If none provided, ask the user to describe the task.
  2. Explore the codebase to understand the relevant context:
    • Identify the scripts, tests, and docs affected by this task.
    • Read key files to understand existing patterns and conventions.
    • Re-read the traps in CLAUDE.md — most constraints in this repo live there, not in the code.
  3. Design the implementation approach:
    • Identify the entry point and affected layers (hook, notifier script, click handler, setup script, tests).
    • Honor the one rule: a hook must never break the user's session — every failure path exits 0 silently.
    • Consider platform differences (macOS vs Linux) and how the change will be tested without a real banner.
  4. Break the work into concrete, ordered steps. Each step should be:
    • A single logical unit of work (one file or one concern)
    • Actionable (e.g. "Add tty matching to open-session.sh using ps ax -o tty=,command=")
    • Sized for ~1 commit
  5. Save the plan to .claude/plans/YYYY-MM-DD-[kebab-case-task-name].md (create the directory if needed). Plans are personal working documents and are gitignored — only git add one when explicitly asked.
  6. Use this structure:
# Plan: [Task Title]

Date: [today's date]
Branch: [current branch if derivable]

## Goal

[1-2 sentence summary of what this achieves and why]

## Affected Files

- [list of files to create or modify]

## Implementation Steps

1. [Step description] — `path/to/file.sh`
2. ...

## Open Questions

- [Any ambiguities that need user input before coding starts]

## Out of Scope

- [Explicitly what this plan does NOT cover]
  1. After saving the plan, display it to the user and ask:

    "Plan saved to .claude/plans/[YYYY-MM-DD]-[name].md. Would you like me to start implementing it now?"

If the user says yes, begin executing the steps in order, marking each complete before moving to the next. Do not write any implementation code until the plan is saved and the user confirms.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free