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/load-test)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/load-test"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/load-test/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/load-test"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/load-test.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 | $0.00018 | $0.02283 |
| Opus 5 | $0.00009 | $0.01141 |
| Sonnet 5 | $0.00004 | $0.00457 |
| Haiku 4.5 | $0.00002 | $0.00228 |
Grade A, and why
load-test 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:load-test
Trigger
/architect:load-test [options]
Options:
[tool:k6|locust|artillery]— specify load testing tool (default: k6)[non_interactive:true]— skip all questions, derive from SDL performance targets[rps:100]— override requests per second (default: from SDL or 10)
Purpose
Before production launch, verify APIs handle expected load. This command generates load testing scenarios from OpenAPI contracts with realistic traffic patterns: smoke tests (baseline), load tests (target RPS), stress tests (2x), and spike tests (sudden 10x surge). Uses k6, Locust, or Artillery depending on preference.
Workflow
Quick Navigation
| Phase | Steps |
|---|---|
| Setup | Step 1 · Step 1.5 |
| Configuration | Step 2 |
| Generation | Step 3 · Step 3.5 |
| Completion | Step 4 · Step 4.5 · Step 5 |
Step 1: Read Context and Detect Contracts
ℹ️ CONTEXT LOADING: _state.json → SDL → OpenAPI contracts
First, read architecture-output/_state.json if it exists. Extract:
project.name,project.stage(MVP/growth/enterprise)tech_stack.backend(which services to test)components[]with port numbers
Then, check for API contracts:
- Look for
architecture-output/contracts/*.openapi.yaml - If contracts don't exist, respond:
"I need API contracts to generate load tests from. Run
/architect:scaffold(which generates contracts in Step 3.7), then come back here."
For each contract, extract:
- All endpoints (GET, POST, PUT, DELETE, etc.)
- Request body schemas (for POST/PUT)
- Response schemas
- Status codes (200, 400, 404, 500, etc.)
Step 1.5: Detect Load Testing Tool
❓ DECISION POINT: Tool and framework selection
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 · 239 lines · 18 tokens per session scan A 3bcb0c011429
load-test is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 2,283 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
cloudflare-durable-objects:setup
Interactive Durable Objects project initialization. Scaffolds new DO project with proper bindings, migrations, and boilerplate code.
spec-verify
Run post-deployment smoke tests against a live environment.
spec-accept
Run user acceptance testing against spec requirements for formal sign-off.
test
Generate API integration tests for endpoints.
e2e
Generate and run end-to-end API tests with Testcontainers for Spring Boot (MVC and WebFlux) applications.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.