loop-plan

loop-plan is a command for coding agents from vcz-Gray/loophaus. It costs 15 tokens per session (2,647 once invoked), scanned A, original, MIT.

An interactive command that plans a coding task, divides it across separate workspaces, runs the work, and combines the results into one branch.

In plain words
What is it for?
Use it to interview you about a task, create a plan, run parallel implementation, and produce a merged result.
Why use it?
It removes the need to manually turn a large request into smaller tasks and merge their changes.

Command

Part of the loophaus plugin — 6 skills, 7 commands, 1 hook shipped together

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 commands/vcz-gray/loophaus/loop-plan
Clone the repo
git clone --depth 1 https://github.com/vcz-Gray/loophaus

Or install loophaus, the plugin that ships this one along with the rest of its 6 skills, 7 commands, 1 hook.

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 loop-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/vcz-gray/loophaus/loop-plan.svg)](https://agentmods.dev/commands/vcz-gray/loophaus/loop-plan)
Your own site
<a href="https://agentmods.dev/commands/vcz-gray/loophaus/loop-plan"><img src="https://agentmods.dev/badge/commands/vcz-gray/loophaus/loop-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,647 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 $0.00015 $0.02647
Opus 5 $0.00008 $0.01324
Sonnet 5 $0.00003 $0.00529
Haiku 4.5 $0.00002 $0.00265

Measured 4d ago against content hash 4d836b375a3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-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 4d 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/loop-plan.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/loop-plan — Plan, Parallelize, Execute, Merge

End-to-end workflow: interview → PRD → parallel distribution → loop execution → merge. The user runs /loop-plan once and gets a single merged branch with all work done.


Pre-flight: Update Check

Run loophaus update-check silently before starting.

If the command reports an available update:

  1. Show: loophaus update available: v{current} → v{latest}
  2. Ask user:
    • A) Upgrade now → run loophaus upgrade, then continue
    • B) Always auto-upgrade → run loophaus config set autoUpgrade true && loophaus upgrade, then continue
    • C) Not now → run loophaus config set updateCheck snoozed silently, then continue
    • D) Never ask again → run loophaus config set updateCheck false, then continue

If auto-upgrade is enabled (loophaus config get autoUpgrade returns true):

  • Skip prompt, run loophaus upgrade silently, continue.

If no update is available or the check fails: continue silently and never block the user.

Pre-flight: Skill Routing Check

Check if the project has a CLAUDE.md with loophaus skill routing:

CLAUDE_MD="$(pwd)/CLAUDE.md"
ROUTING_MARKER=".loophaus/routing-offered.json"

If CLAUDE.md exists but has no ## loophaus skill routing section, AND routing hasn't been offered before:

  1. Suggest adding this section to CLAUDE.md:
    ## loophaus skill routing
    
    | User intent | Route to |
    |-------------|----------|
    | Feature implementation, refactoring, multi-step task | `/loophaus:loop-plan` |
    | "start the loop", "continue implementing" | `/loophaus:loop` |
    | "stop the loop", "cancel" | `/loophaus:loop-stop` |
    | "what's the status", "how far along" | `/loophaus:loop-pulse` |
    
  2. If user agrees, add the section to CLAUDE.md
  3. Write { "offeredAt": "<ISO date>" } to .loophaus/routing-offered.json so we don't ask again

If CLAUDE.md doesn't exist or routing already offered: skip silently.

Phase 0: Cleanup Previous Data

Read the full file on GitHub · 323 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. 4d ago First seen · 323 lines · 15 tokens per session scan A 4d836b375a3c

Subscribe to this mod's changes

loop-plan is a command published in the GitHub repository vcz-Gray/loophaus (23 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 2,647 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.