plan

A collaborative planning workflow for turning a software task into a multi-phase plan. It asks clarifying questions, reviews the codebase, and can use a separate research document when one exists.

In plain words
What is it for?
Use it before larger or uncertain coding tasks that need research, multiple phases, or agreement on scope and technical approach.
Why use it?
It exposes unclear requirements and important project constraints before implementation begins. This helps produce plans that fit the existing code instead of assuming a blank project.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/brian-lai/para-programming-plugin/plan
Any agent
npx skills add brian-lai/para-programming-plugin --skill plan
Clone the repo
git clone --depth 1 https://github.com/brian-lai/para-programming-plugin

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,209 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.02209
Opus 5 $0.00008 $0.01104
Sonnet 5 $0.00003 $0.00442
Haiku 4.5 $0.00002 $0.00221

Measured 2d ago against content hash 31e4f42b11a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/plan/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a planning document through collaborative dialogue, with support for multi-phase plans.

Usage

/para:plan [task-description]

If no task description is provided, Claude will ask for one.

Collaborative Planning Process

Planning is a dialogue, not a one-shot generation.

When /para:plan is invoked:

  1. Identify ambiguities in the task description -- scope, approach, constraints, preferences.

  2. Ask 1-4 clarifying questions using AskUserQuestion before doing anything else:

    • Present options with trade-offs clearly explained
    • Reference existing codebase patterns when relevant ("I see you use X elsewhere, should we follow that?")
    • Skip only if ALL of these are true: task is very narrow, only one reasonable approach exists, no risk of breaking changes, user gave extremely detailed requirements.
  3. Check for research doc. If a research document exists (context/data/YYYY-MM-DD-task-name-research.md), use it as primary input for steps 4-6. If no research doc exists for a non-trivial task, suggest running /para:research first.

  4. Explore the codebase with clarifications in hand -- identify:

    • Existing patterns, conventions, and affected components
    • Complexity and existing test patterns (test framework, test file locations, naming conventions)
    • Interface boundaries between systems (APIs, message formats, shared types, database schemas used across modules)
    • Existing graceful degradation patterns (how the codebase currently handles external dependency failures, timeouts, retries)
  5. Draft spec + stubs:

    • Create a spec file in context/data/YYYY-MM-DD-task-name-spec.yaml (OpenAPI/Swagger YAML for HTTP APIs; TypeScript interface file or markdown contract for UI components, modules, and scripts)
    • Create stub source files in the project tree with signatures matching the spec but no implementation (return null, {}, or 501 Not Implemented as appropriate)
    • Reference the spec and stub file paths in the plan

Read the full file on GitHub · 157 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 157 lines · 16 tokens per session scan A 31e4f42b11a2

Subscribe to this mod's changes

plan is a skill published in the GitHub repository brian-lai/para-programming-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 2,209 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens