prototype-loop

prototype-loop is a command for Claude Code from Generous-Corp/pulp. It costs 31 tokens per session (832 once invoked), scanned A, original, MIT.

A command for running a focused watch-and-rebuild loop while working on visual matching and framework fixes. It records a target operating system such as macOS, Linux, or Windows before starting the loop.

In plain words
What is it for?
Use it during porting or visual-parity work to set the platform focus, optionally inspect a consumer's React bundle, and repeatedly rebuild while watching for changes.
Why use it?
It removes repeated manual steps when checking changes against another application or platform. It also reminds the developer to turn off the loop and prepare the change for review.

Command for Claude Code

Part of the pulp plugin — 63 skills, 30 commands, 3 hooks, 1 MCP server 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/generous-corp/pulp/prototype-loop
Clone the repo
git clone --depth 1 https://github.com/Generous-Corp/pulp

Made for: Claude Code.

Or install pulp, the plugin that ships this one along with the rest of its 63 skills, 30 commands, 3 hooks, 1 MCP server.

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 prototype-loop

README.md
[![agentmods](https://agentmods.dev/badge/commands/generous-corp/pulp/prototype-loop.svg)](https://agentmods.dev/commands/generous-corp/pulp/prototype-loop)
Your own site
<a href="https://agentmods.dev/commands/generous-corp/pulp/prototype-loop"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/prototype-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 832 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 $0.00031 $0.00832
Opus 5 $0.00015 $0.00416
Sonnet 5 $0.00006 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured today against content hash 843a5f79a095, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prototype-loop 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 today.

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.

.claude/commands/prototype-loop.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prototype-loop — Leveraged-prototype focus mode

Use the prototype-loop skill for the full playbook. This slash command is the Claude Code entry point — it confirms the focus platform with the user, then orchestrates the loop.

What this command does

  1. Asks the user to confirm the focus platform (macOS / Linux / Windows). Defaults to the auto-detected host.
  2. Persists the focus marker via pulp loop --platform=<...> (or runs --no-watch first if the user wants to set the marker without entering the watch loop yet).
  3. Runs the normal watch + rebuild loop after persisting the focus marker; use separate screenshot tooling when visual proof is needed.
  4. Prompts the user to run pulp loop --off and shipyard pr (or pulp pr) before landing the consumer-side PR.

Step-by-step

1. Confirm the focus platform

pulp loop --status

Read the auto-detected host from the output. If the user wants to override, ask "Which platform do you want to focus on? (macos / linux / windows)" and pass --platform=<value>.

2. Optionally analyze the consumer's bundle

If the user is doing porting / parity work and hasn't analyzed the consumer's React bundle yet:

"Have you run pulp-css-analyze against this consumer's bundle? It produces a coverage report identifying unmapped CSS props with occurrence counts — the ideal input for filing framework issues."

If they say no, point them at the analyzer. Until the analyzer is lifted into the shared Pulp tooling, the Spectr-side copy lives at spectr/native-react/tools/pulp-css-analyze.

3. File framework issues from the analyzer output

Coach the user through issue-filing per the skill's Step 2:

  • One-line title.
  • Occurrence count.
  • Acceptance criteria.
  • Bridge-fn signature suggestion.
  • Cross-link to the analyzer report.

4. Enter focus mode

pulp loop --platform=<chosen> --test

Add --validate, --run, --target per the user's needs. The watch loop kicks off — every save triggers rebuild + tests using the current project build configuration.

Read the full file on GitHub · 84 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. today First seen · 84 lines · 31 tokens per session scan A 843a5f79a095

Subscribe to this mod's changes

prototype-loop is a command published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 832 once invoked, about $0.0002 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 2026-09-04.