A command that sends a proposed feature through four reviews: business value, engineering design, user experience, and developer experience.

Use it to decide whether to build a feature and identify affected code, screens, tests, migrations, and deployment concerns.

It surfaces scope, cost, architecture, usability, and implementation risks before coding starts.

autoplan — Command for Claude Code by Achitokun14

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/Achitokun14/claude-universal

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/achitokun14/claude-universal/autoplan.svg)](https://agentmods.dev/commands/achitokun14/claude-universal/autoplan)

Your own site

<a href="https://agentmods.dev/commands/achitokun14/claude-universal/autoplan"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/autoplan.svg" alt="Measured on agentmods" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 423 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00423
Opus 5	$0.00013	$0.00211
Sonnet 5	$0.00005	$0.00085
Haiku 4.5	$0.00003	$0.00042

Measured 7d ago against content hash 83412a73ee9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

autoplan 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 7d 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.

user/commands/autoplan.md · 23 lines

What it actually says

You're running an AUTOPLAN on: $ARGUMENTS

Dispatch 4 agents in parallel (single message, multiple Agent tool calls), each with Explore subagent type, and summarize their findings:

CEO/Founder review — Agent with prompt: "Scope-and-strategy critique of this feature: '$ARGUMENTS'. Should we build it? What's the expected user impact vs engineering cost? Are there cheaper alternatives (existing library, 3rd party SaaS, manual process)? Produce a 3-paragraph verdict with either 'GO' or 'KILL' or 'DEFER' at the top."
Engineering review — Agent with prompt: "Architecture critique of '$ARGUMENTS' in THIS codebase (read key files first). List: affected modules, API contracts, data migrations needed, breaking changes, test coverage gaps, performance risks, deployment ordering. Call out anything that must happen BEFORE implementation starts."
Design review — Agent with prompt: "UX/design critique of '$ARGUMENTS'. What does the user flow look like? What new screens/components? How does this interact with existing design patterns? Rate 0-10 on: clarity, consistency, accessibility, delight. Surface risks."
Developer-Experience review — Agent with prompt: "DX critique of '$ARGUMENTS' for the next engineer. Is the ergonomics good? What needs documenting? What gets harder? What friction exists? Provide 3 concrete DX improvements the implementation should include from day 1."

After all 4 complete, synthesize into a GO/KILL/DEFER decision, a bullet list of BLOCKERS, and a bullet list of NON-BLOCKING IMPROVEMENTS. Ask the user if they want to proceed to /paul:plan (or a manual plan) for the GO path.

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.

7d ago First seen · 23 lines · 25 tokens per session scan A 83412a73ee9f

Subscribe to this mod's changes

autoplan is a command published in the GitHub repository Achitokun14/claude-universal (2 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 423 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 2026-08-31.

Claude Code Planning ai-agents bash codex coding-agents gemini-cli

autoplan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

init

milestone-list

fix

recall

amp-identity

claude-request