auto-plan

auto-plan is a skill for Claude Code, Codex from appautomaton/automaton. It costs 20 tokens per session (1,923 once invoked), scanned A, original, MIT.

A planning workflow that turns an approved software specification into small, ordered pieces of work and the checks needed to verify them.

In plain words
What is it for?
It helps create an execution plan, divide a change into slices, and define verification commands.
Why use it?
It gives implementation a bounded sequence and avoids adding work beyond the agreed specification.

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/appautomaton/automaton/auto-plan
Any agent
npx skills add appautomaton/automaton --skill auto-plan
Clone the repo
git clone --depth 1 https://github.com/appautomaton/automaton

Made for: Claude Code, Codex.

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 auto-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/appautomaton/automaton/auto-plan.svg)](https://agentmods.dev/skills/appautomaton/automaton/auto-plan)
Your own site
<a href="https://agentmods.dev/skills/appautomaton/automaton/auto-plan"><img src="https://agentmods.dev/badge/skills/appautomaton/automaton/auto-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,923 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 $0.00020 $0.01923
Opus 5 $0.00010 $0.00962
Sonnet 5 $0.00004 $0.00385
Haiku 4.5 $0.00002 $0.00192

Measured 5d ago against content hash e45eddc7ddd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-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.

skills/auto-plan/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auto-plan

Planning controller. Turns approved framing into ordered slices with verification commands.

First action: run node .agent/.automaton/scripts/get-context.mjs from the project root.

Preamble

auto-plan builds the smallest plan that makes execution safe while preserving the approved scope. It does not write code or broaden scope beyond the approved spec.

Loading discipline: hold SPEC.md, review state, and source files needed for accurate slices. Read wider project files when understanding existing code informs slice boundaries or verification commands. Read .agent/.automaton/references/CONTEXT-BUDGET.md when wider reads threaten context pressure. When a lookup would otherwise pull wide reads into context, dispatch the read-only automaton-librarian (see .agent/.automaton/references/LIBRARIAN.md): it returns evidence, you keep the decision.

Artifact discipline: PLAN.md is the reloadable execution index, not the whole implementation dossier. Keep PLAN.md compact enough to re-read. For large coherent work, summarize slices in PLAN.md and link optional detail files under .agent/work/<change>/slices/. Split only for independent outcomes, not because one coherent plan has many requirements.

Quality Gate

Before finalizing PLAN.md:

  • Give every material slice a concrete output.
  • Attach a verification command to every material slice.
  • Name the execution topology: default continuation path, explicit checkpoints, subagent routes, and any parallel-safe groups.
  • Remove vague tasks that do not define done.
  • Read references/quality.md when the plan leaves execution decisions to the implementer.

Do

Context Loading

Load the canonical SPEC.md, linked spec detail that carries normative requirements, relevant DESIGN.md, and source files needed to choose slice boundaries, dependencies, and verification commands. Do not ignore linked spec/*.md files when they contain requirement IDs, gap IDs, invariants, audit questions, migration checkpoints, coverage targets, or acceptance detail.

Read the full file on GitHub · 139 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 139 lines · 20 tokens per session scan A e45eddc7ddd2

Subscribe to this mod's changes

auto-plan is a skill published in the GitHub repository appautomaton/automaton (21 stars, last pushed 18d ago), licensed MIT. It adds 20 tokens to every session and 1,923 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 2026-08-30.