writing-plans

writing-plans is a skill for Claude Code from itallstartedwithaidea/agent-skills. It costs 41 tokens per session (1,214 once invoked), scanned A, original, MIT.

A method for turning an implementation request into a detailed sequence of small steps with exact files, code, and checks. The resulting plan is written so another agent can follow it without the original conversation.

In plain words
What is it for?
It helps plan work that changes several files, specify implementation details, and define tests, commands, or interface checks for verification.
Why use it?
It removes ambiguity from larger changes and catches mistakes after each step instead of allowing them to accumulate.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the TodoWrite tool; mentions Claude Code.

Part of the software-dev-skills plugin — 8 skills shipped together , and of all-skills

Good fit It helps plan work that changes several files, specify implementation details, and define tests, commands, or interface checks for verification.

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

Made for: Claude Code.

Or install software-dev-skills, the plugin that ships this one along with the rest of its 8 skills.

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/itallstartedwithaidea/agent-skills/writing-plans/github.svg)](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/writing-plans)
Your own site
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/writing-plans"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/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/itallstartedwithaidea/agent-skills/writing-plans"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/writing-plans.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 1,214 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.01214
Opus 5 $0.00020 $0.00607
Sonnet 5 $0.00008 $0.00243
Haiku 4.5 $0.00004 $0.00121

Measured 5d ago against content hash 53ec142f9da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

writing-plans scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Plans include verification steps after each implementation step: a test to run, a curl command to execute, or a UI state to confirm. This tight feedback loop ensures errors are caught immediately rather than compounding
skills/software-dev/writing-plans/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Plans

Part of Agent Skills™ by googleadsagent.ai™

Description

Writing Plans decomposes any implementation task into a sequence of atomic steps, each completable in 2-5 minutes, with exact file paths, complete code blocks, and verification commands. The plan is a self-contained execution script that another agent—or a future version of the same agent—can follow without needing the original conversation context.

The critical distinction between a plan and a TODO list is specificity. A plan does not say "update the API handler." It says "in src/api/routes/users.ts, add a GET /users/:id/preferences handler at line 47 that returns a UserPreferences object with fields theme, locale, and notifications, validated by the preferencesSchema defined in src/api/schemas.ts." Every step is unambiguous enough to execute mechanically.

Plans include verification steps after each implementation step: a test to run, a curl command to execute, or a UI state to confirm. This tight feedback loop ensures errors are caught immediately rather than compounding across subsequent steps.

Use When

  • A task involves modifying 3+ files
  • The implementation path is known but the execution is non-trivial
  • Work needs to be handed off to another agent or resumed later
  • The user asks for a plan, roadmap, or step-by-step breakdown
  • You need to estimate effort before committing to implementation
  • Complex refactoring requires precise ordering of changes

How It Works

graph TD
    A[Task Description] --> B[Identify Affected Files]
    B --> C[Determine Change Order]
    C --> D[Write Step 1: File + Code + Verify]
    D --> E[Write Step 2: File + Code + Verify]
    E --> F[Write Step N: File + Code + Verify]
    F --> G[Add Rollback Instructions]
    G --> H[Estimate Total Duration]
    H --> I[Present Plan for Approval]
    I -->|Approved| J[Save as plan.md]
    I -->|Needs Revision| B

Read the full file on GitHub · 121 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. 5d ago First seen · 121 lines · 41 tokens per session scan A 53ec142f9da7

Subscribe to this mod's changes

writing-plans is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (37 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,214 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.