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.
git clone --depth 1 https://github.com/navraj007in/architecture-cowork-pluginWrote 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.
[](https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/prototype-iterate)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/prototype-iterate"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/prototype-iterate/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.
<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/prototype-iterate"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/prototype-iterate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.01703 |
| Opus 5 | $0.00006 | $0.00851 |
| Sonnet 5 | $0.00002 | $0.00341 |
| Haiku 4.5 | $0.00001 | $0.00170 |
Grade A, and why
prototype-iterate 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:prototype-iterate
Trigger
/architect:prototype-iterate — run only after /architect:prototype has completed (phase_complete === 4). The change request should follow the command in the conversation.
Purpose
Apply targeted, surgical changes to an existing prototype. This command reads the change request from the conversation, identifies only the affected files, rewrites them, and leaves everything else untouched.
This is NOT a rebuild — do not regenerate the entire prototype.
Step 0: Validate
Check that prototype/_manifest.json exists and phase_complete === 4.
- If the file does not exist, or
phase_completeis less than 4: stop and tell the user to run/architect:prototypefirst. - If validation passes: continue.
Step 1: Read Context
Read the following files to understand the current state of the prototype:
architecture-output/_state.json— project name, design tokens (palette, fonts), entities, personasprototype/_manifest.json— full manifest:screensarray,appName,personality,files_written
Then, based on the change request, selectively read only the relevant files:
- If the change affects specific screens: read only those screen files (use the
screensarray from manifest to identify file paths — typicallyprototype/src/pages/{id}.tsxorprototype/src/screens/{id}.tsx) - If the change affects shared components: Grep
prototype/src/components/for the relevant component(s) - If the change affects theme/design: read
prototype/src/styles/globals.cssandprototype/tailwind.config.ts - If the change affects mock data: read
prototype/src/data/mock.ts - If the change affects routing/navigation: read
prototype/src/App.tsx
Do NOT read all files unless the change request is global (e.g. "redesign the entire UI"). Be selective.
Step 2: Understand Change Request
Parse the change request from the conversation (the text that follows the /architect:prototype-iterate command).
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.
- 8d ago First seen · 168 lines · 12 tokens per session scan A 2fcdc9accd87
prototype-iterate is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,703 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.
Other commands, from other repositories
theme-swap
Recolour an extracted site's design around a new brand primary. OKLCH hue rotation preserves perceptual lightness — neutrals, type, spacing, and motion stay untouched. Side-by-side HTML preview + recoloured tokens (DTCG, Tailwind, shadcn, Figma).
design-audit
Audit an existing HTML/CSS design. Deterministic checks only (contrast, fonts, colors, states, dark mode) plus a visual pass. No generation.
design-component
Generate a single component using existing design-system.md tokens. Skips inspiration browsing — fast path for isolated UI elements.
design-page
New page or screen in an existing project. Skips design-system creation — reuses the existing design-system.md tokens.
design
Full design pipeline for a web or web-app target: brief → tokens → generation → motion → review. Use /design:mobile for iOS/Android instead.
dark-mode-specialist
Use when dark mode looks wrong. Pure black surfaces, elevation that disappears, brand colours that vibrate against dark, a white flash on load, or a mode toggle that does not persist.