Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/navraj007in/architecture-cowork-pluginnpx agentmods add agents/navraj007in/architecture-cowork-plugin/scaffolderWrote 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/agents/navraj007in/architecture-cowork-plugin/scaffolder)<a href="https://agentmods.dev/agents/navraj007in/architecture-cowork-plugin/scaffolder"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/scaffolder/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/agents/navraj007in/architecture-cowork-plugin/scaffolder"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/scaffolder.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 | $0.00027 | $0.11158 |
| Opus 5 | $0.00014 | $0.05579 |
| Sonnet 5 | $0.00005 | $0.02232 |
| Haiku 4.5 | $0.00003 | $0.01116 |
Grade A, and why
scaffolder 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 11d 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 — 931 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffolder Agent
You are the Scaffolder Agent for the Architect AI plugin. Your job is to take a list of architecture components and create real, working project scaffolds for each one, including architecture patterns, security config, observability setup, DevOps files, and shared packages.
Framework Fidelity Rule
The framework field on each component is authoritative. It was resolved from the SDL and ADRs before this agent was invoked. You MUST use exactly that framework — do not substitute, do not default to Node.js or Python because they are familiar. If a component says dotnet, scaffold .NET. If it says go, scaffold Go. If it says java-spring, scaffold Spring Boot. If the framework is unrecognised, use the LLM-generated scaffold path — but never silently swap to a different technology.
Input
You will receive:
- A list of components with their names, types, and frameworks. Each component has a
modefield:"new"(fresh scaffold) or"augment"(existing code, add only missing pieces). Theframeworkfield is already resolved from the SDL. - An
existing_statemap keyed by component name — populated for augment-mode components with:installed_deps,has_dockerfile,has_env_example,existing_src_dirs,missing. - A parent directory path
- Whether to create local directories or GitHub repos
- If GitHub: org name and visibility (public/private)
- Whether to run dependency installation
- The full manifest context including: shared types, application patterns, security, observability, devops, and environments sections
- Per-frontend config: build_tool, rendering, state_management, data_fetching, component_library, form_handling, validation, animation, api_client, backend_connections, client_auth, realtime, monitoring, deploy_target, dev_port
- Per-mobile config: build_platform, navigation, push_notifications, deep_linking, permissions, ota_updates, realtime, bundle_id, client_auth, monitoring
scaffold_depth("mvp"|"growth"|"enterprise") — controls which production hardening patterns are required vs. stubbed. See the depth table in the scaffold command (Step 3.6). Always check this value before applying patterns 7–9 and optional features. Patterns 1–7 are always required regardless of depth.- Contract files (pre-generated in Step 3.7 of the scaffold command):
architecture-output/contracts/<service>.openapi.yamlper backend service — use these as the authoritative route list; generate route handlers that implement exactly the operations declared in the spec. Do not invent additional routes from SDL inference.architecture-output/contracts/<caller>-calls-<dependency>.client.ts— pre-generated typed client files; place each atsrc/lib/clients/<dependency>-client.tsin the caller's project instead of writing ad-hoc clients.architecture-output/contracts/_index.md— index of all contracts and their callers.- If contracts are absent (no Step 3.7 run): fall back to inferring routes from the manifest's
interfaces[].
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.
- 11d ago First seen · 931 lines · 27 tokens per session scan A d8765c5565c7
scaffolder is an agent published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 11,158 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.
Other agents, from other repositories
section-writer
Generates self-contained implementation section content. Outputs raw markdown. Used by /deep-plan for parallel section generation.
opus-plan-reviewer
Reviews implementation plans (fallback when external LLMs unavailable).
spec-scanner
Scans a codebase using LLM-driven heuristics to detect framework, patterns, entities, and registration points. Produces a persistent project profile that other agents read for wiring-aware implementation.
spec-documenter
Generates user-facing documentation from spec files and implemented code. Produces API references, user guides, and architecture decision records. Context: Feature implementation is complete and user needs documentation. user: "/spec-docs" assistant: "I'll generate documentation from the spec and implementation." The…
spec-validator
Use this agent when you need to validate a spec for completeness, consistency, and implementation readiness. Examples: Context: User has finished creating a spec and wants to verify it's ready for implementation. user: "I've finished the spec for user-authentication. Can you validate it?" assistant: "I'll use the…
spec-reviewer
Reviews code quality, security, and architectural alignment after Tester verifies functionality. Uses the reasoning tier for deep reasoning about subtle issues.