plan

plan is a skill for Claude Code from yash-gadodia/claude-init. It costs 41 tokens per session (898 once invoked), scanned A, original, MIT.

A planning guide for turning a non-trivial coding request into a detailed sequence of small implementation tasks.

In plain words
What is it for?
Use it to plan multi-file changes, new features, or architecture work, including the files involved and the order of implementation.
Why use it?
It helps clarify the problem, inspect the existing project, compare possible approaches, and catch design risks before coding begins.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Part of the claude-init plugin — 11 skills, 1 command, 7 agents shipped together

Good fit Use it to plan multi-file changes, new features, or architecture work, including the files involved and the order of implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yash-gadodia/claude-init/plan
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.

Any agent
npx skills add yash-gadodia/claude-init --skill plan
Clone the repo
git clone --depth 1 https://github.com/yash-gadodia/claude-init

Made for: Claude Code.

Or install claude-init, the plugin that ships this one along with the rest of its 11 skills, 1 command, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/yash-gadodia/claude-init/plan/github.svg)](https://agentmods.dev/skills/yash-gadodia/claude-init/plan)
Your own site
<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/plan"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/plan"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 898 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00041 $0.00898
Opus 5 $0.00020 $0.00449
Sonnet 5 $0.00008 $0.00180
Haiku 4.5 $0.00004 $0.00090

Measured 9d ago against content hash b4f150308529, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

templates/skills/plan/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan: Design Before You Build

Turn a feature request into a vetted, executable implementation plan.

When This Triggers

Automatically for any non-trivial change (multi-file, new feature, architecture change). Skip for trivial fixes (typos, config tweaks, one-liner bug fixes).

Process

Phase 1: Understand

  • Read CLAUDE.md and ARCHITECTURE.md for project context
  • Explore related code (Grep for keywords, read files that will change)
  • Identify existing patterns to follow
  • If the request is vague, ask up to 3 clarifying questions (one at a time, prefer multiple choice)
  • Make reasonable assumptions and state them explicitly

Phase 2: Explore Approaches

For medium+ tasks, propose 2-3 approaches:

  • Lead with your recommendation and why
  • Show trade-offs for each
  • Consider: simplest version? Existing patterns to reuse? What's hardest to change later?

Phase 3: Design

Write the plan with bite-sized tasks. Each task should take 2-5 minutes.

## Plan: [Feature Name]

### Problem
<What we're solving, 1-2 sentences>

### Approach
<How we solve it, chosen from Phase 2>

### File Structure
<Which files will be created or modified, what each is responsible for>

### Tasks

#### Task 1: [Component Name]
**Files:**
- Create: `exact/path/to/file.ts`
- Modify: `exact/path/to/existing.ts`
- Test: `exact/path/to/test.ts`

- [ ] Write failing test for [behavior]
- [ ] Verify test fails
- [ ] Implement [specific change]
- [ ] Verify test passes + full suite green
- [ ] Commit

#### Task 2: [Next Component]
...

### Risks
<What could go wrong, ordered by impact>

### Out of Scope
<What this explicitly does NOT include>

Phase 4: Devil's Advocate

Challenge your own plan before presenting it:

  • What's the simplest version of this? Can we ship less?
  • What happens if an assumption is wrong?
  • Is there an existing pattern we should use instead of a new one?
  • What will be hardest to change later if we get it wrong?
  • What happens under 10x load? What if an external service is down?
  • What are the race conditions?

Read the full file on GitHub · 117 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. 9d ago First seen · 117 lines · 41 tokens per session scan A b4f150308529

Subscribe to this mod's changes

plan is a skill published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 898 once invoked, about $0.0002 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.