writing-plans

writing-plans is a skill for Claude Code from Vimalk0703/shipworthy. It costs 38 tokens per session (1,180 once invoked), scanned A, original, MIT.

A way to turn an approved software design into a step-by-step implementation plan. Each task names the files, test code, implementation, verification command, and completion check.

In plain words
What is it for?
It is for planning features as small 2–5 minute tasks, mapping file changes, writing tests first, and recording how each step will be verified.
Why use it?
It removes guesswork from larger changes and prevents vague tasks such as “implement the logic here.” It also keeps work aligned with the project's architecture rules.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the shipworthy plugin — 66 skills, 7 commands, 3 hooks shipped together

Good fit It is for planning features as small 2–5 minute tasks, mapping file changes, writing tests first, and recording how each step will be verified.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vimalk0703/shipworthy/writing-plans
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 Vimalk0703/shipworthy --skill writing-plans
Clone the repo
git clone --depth 1 https://github.com/Vimalk0703/shipworthy

Made for: Claude Code.

Or install shipworthy, the plugin that ships this one along with the rest of its 66 skills, 7 commands, 3 hooks.

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 writing-plans

README.md
[![agentmods](https://agentmods.dev/badge/skills/vimalk0703/shipworthy/writing-plans/github.svg)](https://agentmods.dev/skills/vimalk0703/shipworthy/writing-plans)
Your own site
<a href="https://agentmods.dev/skills/vimalk0703/shipworthy/writing-plans"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/writing-plans/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 writing-plans

Your own site · 80×15
<a href="https://agentmods.dev/skills/vimalk0703/shipworthy/writing-plans"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,180 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 $0.00038 $0.01180
Opus 5.5 $0.00015 $0.00472
Sonnet 5.5 $0.00008 $0.00236
Haiku 4.5 $0.00004 $0.00118

Measured 1mo ago against content hash 330cb800d485, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

writing-plans 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 1mo 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/planning/writing-plans/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Plans

Purpose

Transform an approved design into a sequence of small, verifiable tasks that follow TDD discipline.

Plan Structure

Save plans to .shipworthy/plans/[feature-name].md.

Header

# Implementation Plan: [Feature Name]
**Design Spec**: [link to spec]
**Architecture Constraints**: [relevant Mandatory Rules from architecture.md]
**Date**: [YYYY-MM-DD]

File Map

Before defining tasks, list every file that will be created or modified:

## File Map
- `src/services/user-service.ts` — NEW: user service logic
- `src/routes/users.ts` — MODIFY: add new endpoints
- `src/types/user.ts` — MODIFY: add new types
- `tests/services/user-service.test.ts` — NEW: service tests

Tasks

Each task follows TDD flow and takes 2-5 minutes:

## Task 1: [Descriptive Name]
**Files**: [exact paths]
**Test first**: [the test to write, with actual code — not pseudocode]
**Implementation**: [the code to write — actual code, not descriptions]
**Verification**: [command to run: `npm test`, `npm run build`, etc.]
**Quality gate**: [what proves this task is done]

Rules for Tasks

  1. Zero placeholders — every task has actual code, not "implement the logic here"
  2. 2-5 minutes each — if a task takes longer, break it down further
  3. TDD flow — test first, then implementation, then verification
  4. One responsibility — each file should have one clear purpose (SOLID)
  5. Atomic commits — each task should be committable independently
  6. Consistent naming — type/method names must be consistent across ALL tasks
  7. Architecture compliance — every task must reference which architecture rules it satisfies

Security & Performance Sections

## Security Considerations
- [What input validation is needed?]
- [What authentication/authorization applies?]
- [Any sensitive data handling?]

## Performance Impact
- [New database queries introduced?]
- [Bundle size impact?]
- [API response time expectations?]

Read the full file on GitHub · 109 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. 1mo ago First seen · 109 lines · 38 tokens per session scan A 330cb800d485

Subscribe to this mod's changes

writing-plans is a skill published in the GitHub repository Vimalk0703/shipworthy (6 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 1,180 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.