plan

A planning skill that coordinates several specialist agents to create a written plan for a software task.

In plain words
What is it for?
Use it to plan a story or ticket, choose planning specialists based on scope, write the plan to the project state folder, and surface blocking questions.
Why use it?
It separates requirements, scope, risks, testing, and relevant technical design work so a task has a clearer implementation path.

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/bostonorange/claude-code-framework/plan
Any agent
npx skills add BostonOrange/claude-code-framework --skill plan
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 958 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 $0.00063 $0.00958
Opus 5 $0.00032 $0.00479
Sonnet 5 $0.00013 $0.00192
Haiku 4.5 $0.00006 $0.00096

Measured yesterday against content hash 6b89b59c25a4, 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 yesterday.

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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan — Multi-Agent Planning

A specialist-driven plan for the current branch's work. The planner-coordinator agent classifies scope, spawns the right planning specialists in parallel, and synthesizes their outputs into a single plan document.

Usage

/plan                       — plan the current task using conversation context
/plan TICKET-123            — plan a tracked ticket; reads docs/stories/TICKET-123/story.md
/plan --refresh             — re-run planning even if a plan exists for this branch
/plan --scope=large         — override the auto-classified scope (forces all specialists)

Process

Phase 1: Read the Story

Source of the story:

  • If a TICKET-id is passed, read docs/stories/<TICKET-id>/story.md (and any linked design docs)
  • Otherwise, use the user's stated task from conversation context
  • If neither is available, ask the user

Phase 2: Spawn the Planner Coordinator

Spawn planner-coordinator as a sub-agent:

Invoke planner-coordinator on the following story: <story>.
Use scope classifier to pick specialists.
Write the plan to .claude/state/plan-<branch>.md.
Surface blocking questions and the next action.

The coordinator handles:

  • Scope classification (tiny / small / medium / large)
  • Specialist selection
  • Parallel spawning of Wave 1 (requirements-clarifier, scope-decomposer, architect, api-designer, database-architect)
  • Sequential spawning of Wave 2 (risk-assessor, test-strategy-planner — they consume Wave 1 outputs)
  • Merging into a single plan
  • Persisting to .claude/state/plan-<branch>.md

Phase 3: Surface to User

Show the user:

  • Scope and specialist selection (so they know what was checked)
  • Blocking questions (most important — work cannot start until resolved)
  • The work-breakdown table (collapsed sub-steps unless asked)
  • Top 3 risks
  • Next action (resolve questions → re-plan, OR proceed to /build)

Phase 4: Save and Exit

The plan file is the state. No additional persistence needed.

Read the full file on GitHub · 96 lines

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. yesterday First seen · 96 lines · 63 tokens per session scan A 6b89b59c25a4

Subscribe to this mod's changes

plan is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 958 once invoked, about $0.0003 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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens