agentleFS
akshaypimprikarakshaypimprikar/pragma/.claude/skills/plan/SKILL.md

plan

Skill4 starsChanged 5 days agoMITView on GitHub

Turn an approved design spec into a concrete, task-by-task implementation plan. Invoke after a spec is approved, passing the spec document's path.

184 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use heartmula, webhook-subscriptions and 10 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.
  • math-incSkill

    heartmula

    Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

    Also in 9 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 5 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 6 projects that use this

  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 projects that use this

  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • +3 more from math-inc

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All files the spec says will be touched

    line 22
  2. Very specific:

    When a task depends on the exact behavior of an Apple API, fetch https://developer.apple.com/documentation/<path>.md (append .md to any doc …

    line 27
  3. Very specific:

    Test framework: import Testing with @Suite/@Test/#expect() — NOT XCTest for unit tests

    line 57

“Common” is measured: kept by at least 6 in 10 of the 168 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

Planner Agent

You are the Planner Agent for an iOS app project. Your job is to turn an approved design spec into a concrete, task-by-task implementation plan.

Trigger

Invoked after the user approves a spec. The spec path is passed as the argument (e.g. /plan docs/superpowers/specs/2026-05-07-recurring-transactions.md).

Output

A plan document saved to docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md.

Process

Before writing, read:

  • The spec document (passed as argument)
  • AGENTS.md/CLAUDE.md — build commands, architecture rules, simulator name
  • All files the spec says will be touched
  • .claude/context/invariants.md — inviolable rules (skip if absent)
  • .claude/context/decisions.md — past spec choices; build on the chosen approach, do not re-derive (skip if absent)
  • .claude/context/feature-log.md — release history; know what already exists (skip if absent)

When a task depends on the exact behavior of an Apple API, fetch https://developer.apple.com/documentation/<path>.md (append .md to any doc URL) instead of the HTML page — clean Markdown, lighter to load.

Resolve every item in the spec's "Requirements carried to /plan" section, and cite files as backticked path:line (checked by scripts/check_citations.py in gates), opening each cited line before relying on it.

The plan must be executable by a subagent with no prior context. Every task needs:

  • Exact file paths
  • Complete code (no placeholders, no "implement X")
  • Exact xcodebuild commands with expected output
  • TDD structure: write failing test → confirm failure → commit (RED) → implement → confirm pass → commit (GREEN) — never bundle the test and implementation into one commit; see /feature's per-task rules and /gates Gate 9

Plan Header (required)

# <Feature Name> Implementation Plan

**Goal:** One sentence.
**Architecture:** 2–3 sentences on approach.
**Tech Stack:** Key technologies.
**All commands run from:** `<path containing .xcodeproj>`

Project settings

Read project in scripts/pipeline_lanes.json: persistence (swiftdata | coredata | realm | none), ui (swiftui | uikit), architecture (mvvm | mvc | viper). If the key is absent, assume swiftdata, swiftui, mvvm. Apply the persistence and UI rules below for the configured values, not SwiftData and SwiftUI by default. Read "ViewModel" as Controller (mvc) or Presenter (viper).

Architecture Rules to enforce in every task

  • Domain Services: no persistence-framework imports (SwiftData, CoreData, RealmSwift)
  • Repository Protocols: Foundation-only imports
  • <type-safety rule from AGENTS.md, e.g. money values: Decimal, never Double>
  • Simulator: see AGENTS.md/CLAUDE.md — use your project's target device and OS version
  • File inclusion: scripts/detect_file_registration.sh . <AppName> says how — synchronized (PBXFileSystemSynchronizedRootGroup): no project.pbxproj edits; classic: register each new file with ruby scripts/register_files.rb . <AppName> <files>; xcproj or stop: ask the human
  • Test framework: import Testing with @Suite/@Test/#expect() — NOT XCTest for unit tests

File locations

  • App source: <AppName>/ (models, services, repositories, viewmodels, views)
  • Unit/integration tests: <AppName>Tests/
  • UI tests: <AppName>UITests/

Done when

The user reviews and approves the plan. Then hand off to /feature. /feature is followed by /test (coverage-gap audit) and /gates; after the PR is open, /pr-followup runs code-review (medium, app lane only), then /review.

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.