write-plan

write-plan is a command for Claude Code from axiomantic/spellbook. It costs 18 tokens per session (484 once invoked), scanned A, original, MIT.

A planning command that turns development requirements into small, ordered implementation tasks. Each task includes a concrete way to check that it is finished.

In plain words
What is it for?
It helps prepare detailed plans for features, fixes, migrations, and other development projects.
Why use it?
It makes multi-step work easier to start and track by exposing dependencies, decisions, and missing detail before coding begins.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit It helps prepare detailed plans for features, fixes, migrations, and other development projects.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/write-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.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Made for: Claude Code.

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 write-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/write-plan/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/write-plan)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/write-plan"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/write-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 write-plan

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/write-plan"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/write-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 484 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 $0.00018 $0.00484
Opus 5 $0.00009 $0.00242
Sonnet 5 $0.00004 $0.00097
Haiku 4.5 $0.00002 $0.00048

Measured 5d ago against content hash 3d9c8cf1e294, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

write-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 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.

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.

commands/write-plan.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MISSION

Transform requirements into executable implementation plan with atomic, verifiable tasks.

Invariant Principles

  1. Atomicity - Each task completable in one focused session. No multi-day tasks.
  2. Verifiability - Every task has concrete done criteria. "Done" without evidence = failure.
  3. Dependency awareness - Tasks ordered by dependencies. Parallel work identified explicitly.
  4. No shortcuts in decomposition - Rushing planning compounds into implementation chaos.
  5. Preserve flexibility - Plans guide; they don't constrain. Flag decision points.

Protocol

  1. Invoke writing-plans skill
  2. Follow skill workflow exactly as presented
  3. Store output in ~/.local/spellbook/docs/<project-encoded>/plans/

<FINAL_EMPHASIS> Plan quality determines implementation success. A plan with vague tasks or missing dependencies guarantees rework. Every item in the checklist above is a quality gate, not a suggestion. </FINAL_EMPHASIS>

Read the full file on GitHub · 67 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 · 67 lines · 18 tokens per session scan A 3d9c8cf1e294

Subscribe to this mod's changes

write-plan is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 484 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 2026-09-03.