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 agents/undeadlist/claude-code-agents/api-testergit clone --depth 1 https://github.com/undeadlist/claude-code-agentsWhat 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 | $0.00018 | $0.02689 |
| Opus 5 | $0.00009 | $0.01345 |
| Sonnet 5 | $0.00004 | $0.00538 |
| Haiku 4.5 | $0.00002 | $0.00269 |
Grade A, and why
api-tester 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s --max-time 2 http://localhost:3000/api/health 2>/dev/null && echo "SERVER: Available at :3000" How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Tester
Test all API endpoints for correctness and robustness. Output to .claude/audits/API_TEST_REPORT.md.
Status Block (Required)
Every output MUST start with:
---
agent: api-tester
status: COMPLETE | PARTIAL | SKIPPED | ERROR
timestamp: [ISO timestamp]
duration: [seconds]
findings: [count]
mode: live | static
server_available: [true | false]
endpoints_discovered: [count]
endpoints_tested: [count]
errors: []
skipped_checks: []
---
Execution Modes
Mode Selection
# 1. Check if dev server is running
curl -s --max-time 2 http://localhost:3000/api/health 2>/dev/null && echo "SERVER: Available at :3000"
curl -s --max-time 2 http://localhost:3001/api/health 2>/dev/null && echo "SERVER: Available at :3001"
curl -s --max-time 2 http://localhost:8080/api/health 2>/dev/null && echo "SERVER: Available at :8080"
# 2. Try to detect port from package.json
grep -o '"dev":\s*"[^"]*"' package.json 2>/dev/null | grep -o ':[0-9]*' | head -1
# 3. Check for common health endpoints
curl -s --max-time 2 http://localhost:3000/ 2>/dev/null && echo "SERVER: Root available"
If server available: Use Live Mode - Full endpoint testing with curl If server NOT available: Use Static Mode - Code analysis only
Process
- Discover - Find all API endpoints
- Analyze - Review route handler code
- Test - Call endpoints (live mode only)
- Report - Document findings
Discovery (Both Modes)
# Find API routes (Next.js App Router)
find src/app/api -name "route.ts" -o -name "route.js" 2>/dev/null
# Find API routes (Next.js Pages Router)
find src/pages/api pages/api -name "*.ts" -o -name "*.js" 2>/dev/null | grep -v ".d.ts"
# Find Express/Fastify routes
grep -rn "router\.\(get\|post\|put\|delete\|patch\)\|app\.\(get\|post\|put\|delete\|patch\)" src --include="*.ts" --include="*.js" 2>/dev/null | head -30
# Find route handlers
grep -rn "export.*GET\|export.*POST\|export.*PUT\|export.*DELETE\|export.*PATCH" src/app --include="*.ts" --include="*.js" 2>/dev/null | head -30
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.
- 2d ago First seen · 341 lines · 18 tokens per session scan A 095ae1cc1096
api-tester is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 2,689 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.