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/scaffold-component)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/scaffold-component"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/scaffold-component/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/scaffold-component"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/scaffold-component.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 | $0.00014 | $0.07595 |
| Opus 5.5 | $0.00006 | $0.03038 |
| Sonnet 5.5 | $0.00003 | $0.01519 |
| Haiku 4.5 | $0.00001 | $0.00760 |
Grade A, and why
scaffold-component 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 2mo 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:scaffold-component
Trigger
/architect:scaffold-component <component_name>
Purpose
Scaffolds a single component by name from the SDL. This command is invoked by the parallel scaffold orchestrator to scaffold one component at a time, enabling parallel execution across multiple agents.
A component is anything defined in the SDL: backend service, frontend web app, mobile app, AI agent, shared library, database setup, cloud resource, infrastructure config — whatever gets generated as part of the SDL.
Unlike /architect:scaffold which scaffolds everything, this command targets exactly one component and is designed for non-interactive, single-focus execution.
Workflow
Quick Navigation
Step 1 · Step 2 · Step 3 · Step 4 · Step 5 · Step 6
Step 1: Identify the Component
Extract the component name from the command argument. The name corresponds to a component defined in the SDL.
Locate the SDL:
- Check
solution.sdl.yamlin the project root — if it exists, read it - If absent, check for
sdl/directory — readsdl/README.mdfirst, then the module containing component definitions (typicallysdl/architecture.yamlorsdl/projects.yaml)
Find the component matching the provided name by searching:
architecture.projects[](array form)architecture.projects.backend[]andarchitecture.projects.frontend[](object form)- Top-level
components[],modules[], orservices[]
If no matching component is found, respond:
"Component '{name}' not found in SDL. Available components: {list}."
Step 2: Extract Component Configuration
From the matching SDL entry, extract all available fields:
- name — directory name
- type — component type (rest-api, graphql, web, admin, mobile, worker, agent, shared-lib, database, cloud-resource, cdn, queue, cache, etc.)
- runtime — runtime/platform (node, python, go, java, swift, kotlin, flutter, terraform, etc.)
- language — programming language
- framework — framework if specified (express, fastapi, next, react, react-native, flutter, django, spring, etc.)
- purpose — what the component does
- interfaces — endpoints, events, screens, or ports
- dataOwnership — data responsibilities (cross-reference with
domain.entities[]in SDL) - port — assigned port
- deploy_target — deployment target
- Any other component-specific fields (build_tool, rendering, state_management, navigation, permissions, etc.)
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.
- 2mo ago First seen · 477 lines · 14 tokens per session scan A 7a637c87c29b
scaffold-component is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 7,595 once invoked, about $0.0001 per session on Opus 5.5. 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
spec-release
Generate release notes, changelog, and deployment checklist.
spec-status
Show status and progress of current spec.
spec-validate
Validate spec completeness and consistency.
spec-verify
Run post-deployment smoke tests against a live environment.
spec-refine
Refine requirements or design for an existing spec.
spec-tasks
Regenerate tasks from updated spec requirements and design.