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.
npx agentmods add commands/cyperx84/claude-code-plugin-examples/test-apigit clone --depth 1 https://github.com/cyperx84/claude-code-plugin-examplesWhat 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 | $0.00007 | $0.00395 |
| Opus 5 | $0.00003 | $0.00198 |
| Sonnet 5 | $0.00001 | $0.00079 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
test-api 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(curl:*, node:*) What it actually says
API Endpoint Testing
Test API: $ARGUMENTS (URL or specification)
Comprehensive Testing
1. Quick Test
/test-api https://api.example.com/users
# Tests:
✅ GET /users (200 OK, 45ms)
✅ Response is valid JSON
✅ Returns array of users
⚠️ No rate limiting detected
⚠️ Missing CORS headers
2. Full Test Suite
Automatically generates tests for:
- Happy Path - Valid requests
- Error Cases - Invalid data, auth failures
- Edge Cases - Empty, null, large data
- Security - Auth, injection, headers
- Performance - Response time, load
3. Contract Testing
API Contract Validation:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
GET /users
✅ Status: 200 OK
✅ Content-Type: application/json
✅ Response Schema: Valid
⚠️ Missing: pagination metadata
❌ Response Time: 1.2s (expected < 500ms)
POST /users
✅ Status: 201 Created
✅ Validates required fields
✅ Returns created resource
✅ Sets Location header
DELETE /users/:id
✅ Status: 204 No Content
✅ Requires authentication
⚠️ No confirmation step (security risk)
Example Usage
# Test single endpoint
/test-api GET https://api.example.com/users
# Test with authentication
/test-api https://api.example.com/users --auth "Bearer token"
# Load test
/test-api https://api.example.com/users --load 100
# Generate test suite
/test-api https://api.example.com/openapi.json --generate-tests
Pattern Demonstrated: API Testing & Validation Automation
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.
- yesterday First seen · 75 lines · 7 tokens per session scan A 760dc0145449
test-api is a command published in the GitHub repository cyperx84/claude-code-plugin-examples (2 stars, last pushed 10mo ago), licensed MIT. It adds 7 tokens to every session and 395 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.