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/agents/navraj007in/architecture-cowork-plugin/load-test-generator)<a href="https://agentmods.dev/agents/navraj007in/architecture-cowork-plugin/load-test-generator"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/load-test-generator/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/load-test-generator"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/load-test-generator.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 | $0.00024 | $0.03072 |
| Opus 5 | $0.00012 | $0.01536 |
| Sonnet 5 | $0.00005 | $0.00614 |
| Haiku 4.5 | $0.00002 | $0.00307 |
Grade A, and why
load-test-generator scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system('locust -f locustfile.py --headless -u 100 -r 10 -t 5m') How it starts
The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load Test Generator Agent
Autonomous code generation agent that creates load testing scenarios from API contracts. Generates realistic traffic patterns: smoke tests (baseline), load tests (sustained RPS), stress tests (2x target), and spike tests (sudden surge).
Input
The /architect:load-test command passes:
{
"tool": "k6",
"config": {
"target_rps": 100,
"test_duration_seconds": 300,
"ramp_up_seconds": 60
},
"services": [
{
"name": "api-server",
"endpoint": "http://localhost:3000",
"contract": "api-server.openapi.yaml"
}
],
"thresholds": {
"p95_latency_ms": 500,
"p99_latency_ms": 1000,
"error_rate_percent": 1
},
"stage": "growth"
}
Process
Step 1: Parse API Contracts
For each service's OpenAPI contract, extract:
- All endpoints (path + method)
- Request body schemas (for POST/PUT)
- Response codes (200, 400, 404, 500)
- Authentication requirements (JWT, API key, none)
Example parsing:
# From api-server.openapi.yaml
paths:
/api/users:
get:
operationId: listUsers
parameters:
- name: limit
in: query
type: integer
responses:
200:
schema: { $ref: '#/components/schemas/UserList' }
401:
description: Unauthorized
/api/users:
post:
operationId: createUser
requestBody:
required: true
content:
application/json:
schema: { $ref: '#/components/schemas/CreateUserRequest' }
responses:
201:
schema: { $ref: '#/components/schemas/User' }
Step 2: Generate Realistic Test Data
For each request body schema, generate realistic mock data:
// User creation payload
const createUserPayload = {
email: 'user-' + Date.now() + '@example.com',
name: 'Test User ' + Math.random().toString(36),
password: 'SecurePassword123!'
};
// Order payload
const createOrderPayload = {
customerId: Math.floor(Math.random() * 1000),
items: [
{ productId: 123, quantity: 2, price: 29.99 }
],
shippingAddress: {
street: '123 Main St',
city: 'San Francisco',
state: 'CA',
zip: '94102'
}
};
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 · 441 lines · 24 tokens per session scan A af6dd1c8f94f
load-test-generator is an agent published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 3,072 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
spec-tester
Verifies that implemented tasks actually work. Uses Playwright for UI testing, runs test suites, and only marks Verified: yes after real verification.
spec-acceptor
Performs user acceptance testing by mapping completed tasks back to requirements and verifying traceability, non-functional requirements, and overall completeness. Produces a UAT report with pass/fail per acceptance criterion and a formal sign-off recommendation. Does NOT re-run functional tests (the spec-tester…
refactor-test
Test coverage analyzer and test case generator for refactoring workflows. Analyzes code coverage, adds missing test cases to meet production requirements, runs tests, and ensures all tests pass before proceeding with refactoring.
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.