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/generate-data-model)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/generate-data-model"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/generate-data-model/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/generate-data-model"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/generate-data-model.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 | $0.00023 | $0.05482 |
| Opus 5 | $0.00012 | $0.02741 |
| Sonnet 5 | $0.00005 | $0.01096 |
| Haiku 4.5 | $0.00002 | $0.00548 |
Grade A, and why
generate-data-model 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 — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:generate-data-model
Trigger
/architect:generate-data-model — generate schemas for all databases detected in the SDL (default).
/architect:generate-data-model [databases:X] — generate schema for one database only.
/architect:generate-data-model [databases:X,Y] — generate schemas for a named subset.
Database names
Use the database type as the name:
| Name | What it generates |
|---|---|
postgresql / mysql / sqlite |
Relational ORM schema (Prisma, Drizzle, SQLAlchemy, etc.) + migrations |
mongodb |
Mongoose / Motor document schemas |
redis |
Key schema definitions + TTL patterns |
elasticsearch / typesense |
Index mappings and search schema |
Examples:
/architect:generate-data-model [databases:postgresql]
/architect:generate-data-model [databases:postgresql,redis]
/architect:generate-data-model [databases:mongodb] [non_interactive:true]
When a [databases:...] tag is present, generate schemas only for the named databases and skip all others. When absent, generate for all databases found in the SDL.
Purpose
After generating a blueprint with /architect:blueprint, this command takes the shared types (deliverable 4d) and database definitions from the manifest and generates real, working ORM schemas. Turns type stubs into Prisma schemas, SQLAlchemy models, Mongoose schemas, or Drizzle tables — with relationships, indexes, enums, and seed data.
Workflow
Quick Navigation
| Phase | Steps |
|---|---|
| Setup | Step 1 · Step 2 · Step 3 |
| Generation | Step 3.5 · Step 3.6 · Step 3.7 |
| Completion | Step 4 · Step 5 · Step 5.5 |
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 · 553 lines · 23 tokens per session scan A 1c7a2277fcbd
generate-data-model is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 5,482 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 commands, from other repositories
v-memory-refresh
(Re)index docs/superpowers prose into the local V-memory cache so recall is current. Incremental by file hash; runs fully offline (FTS5, pure stdlib). Optionally enable the semantic lane with a one-time bootstrap. Run it after pulling new docs, or when /v:remember looks stale.
nyann:apply
Apply an Infrastructure-as-Code change — the highest-stakes mutator in nyann; it can change real cloud infrastructure. Re-runs the plan, shows it, confirms, then applies. Unmistakably opt-in: apply is never the default and destructive applies require a second explicit confirm. For IaC apply intent only (not "apply a…
nyann:release
Cut a release: generate a CHANGELOG section from Conventional Commits, make a release commit, and create an annotated tag. Defaults to conventional-changelog strategy.
nyann:gh-protect
Audit or apply GitHub branch protection, tag rulesets, signing requirements, and repo settings based on the active profile.
nyann:wait-for-pr-checks
Poll a GitHub PR's checks until they all pass, any one fails, or a timeout is hit. Returns a structured outcome the caller can gate on.
nyann:gen-claudemd
Regenerate the nyann-managed block in CLAUDE.md from the current profile and stack detection without running a full bootstrap.