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/database-scaling)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/database-scaling"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/database-scaling/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/database-scaling"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/database-scaling.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 | $0.00015 | $0.01196 |
| Opus 5 | $0.00008 | $0.00598 |
| Sonnet 5 | $0.00003 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
database-scaling 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:database-scaling
Trigger
/architect:database-scaling [options]
Options:
[non_interactive:true]— generate from _state.json
Purpose
Databases hit limits. This command designs a scaling strategy with specific recommendations: read replicas (connection routing), connection pooling (PgBouncer, Prisma), table partitioning (for large entities), horizontal sharding (if needed), caching layer sizing. Tailored to your database type and entity sizes. Outputs design document + config stubs for immediate use.
Workflow
Quick Navigation
| Phase | Steps |
|---|---|
| Setup | Step 1 |
| Analysis | Step 2 |
| Generation | Step 3 |
| Completion | Step 4 · Step 5 |
Step 1: Read Context
ℹ️ CONTEXT LOADING: _state.json → SDL
Read:
_state.json.entities[]with field counts (to estimate row size)_state.json.tech_stack.database(PostgreSQL, MySQL, MongoDB, etc.)- SDL data section (databases, indexes, types)
- Scaffolded infrastructure (docker-compose.yml, k8s configs)
Step 2: Analyze Scaling Needs
For each entity, estimate:
- Current size: rows × average row size
- Growth rate: rows/month (from personas, industry benchmarks)
- Query patterns: how many reads vs writes
- Hot data: what percent accessed frequently vs historical
Example analysis:
- Users table: 100K rows × 1 KB = 100 MB, 10% growth/month
- Orders table: 1M rows × 2 KB = 2 GB, 20% growth/month
- Posts table: 10M rows × 500 B = 5 GB, 5% growth/month
Step 3: Generate Scaling Strategy
Create architecture-output/database-scaling.md:
By database size and growth:
| Entity | Current | Monthly Growth | Scaling Approach | Timeline |
|---|---|---|---|---|
| users | 100 MB | 10 MB | Connection pooling (PgBouncer) | Immediate |
| orders | 2 GB | 400 MB | Read replicas (2 replicas) | 3–6 months |
| posts | 5 GB | 250 MB | Table partitioning by date | 6–12 months |
| events | 50 GB | 5 GB | Sharding by user_id (4 shards) | 12+ months |
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 · 146 lines · 15 tokens per session scan A 284b29d7663a
database-scaling is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,196 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.
laravel-performance-cache
Add caching to reduce work; use the laravel:performance-caching skill exactly as written.
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:sync
Update the current feature branch against its base (rebase by default, merge on request). Refuses on main/master/develop or with a dirty tree.
nyann:undo
Safely undo the last commit (or last N commits) on a feature branch. Always previews first. Refuses main/master/develop, merge commits, and pushed commits (override with --allow-pushed).
frappe-cache
Manage Redis cache - clear, monitor, and optimize Frappe cache performance.