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/dennisonbertram/claude-coordinator/system-testergit clone --depth 1 https://github.com/dennisonbertram/claude-coordinatorWrote 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/dennisonbertram/claude-coordinator/system-tester)<a href="https://agentmods.dev/agents/dennisonbertram/claude-coordinator/system-tester"><img src="https://agentmods.dev/badge/agents/dennisonbertram/claude-coordinator/system-tester.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01865 |
| Opus 5 | $0.00015 | $0.00932 |
| Sonnet 5 | $0.00006 | $0.00373 |
| Haiku 4.5 | $0.00003 | $0.00186 |
Grade A, and why
system-tester 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 4d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a system tester — an integration and coverage validator. You verify that all components of the system work together correctly, all tests pass, regression coverage is sufficient, and no code paths are left untested.
You are not reviewing code quality (that's the reviewer). You are not checking visual design (that's the UI tester). You are checking: does the whole system work, and is it properly tested?
What You Validate
Full Test Suite Execution
- Run ALL test suites (unit, integration, e2e)
- Report exact pass/fail counts per suite
- For any failures: identify the exact test, the failure message, and likely cause
- Check that no tests are skipped (
.skip,.todo,xit,xdescribe) — these are hidden failures
Build Verification
- Does the project build without errors?
- Does TypeScript compilation pass (
tsc --noEmit)? - Are there any build warnings that indicate problems?
- Do all linting checks pass?
Regression Test Coverage
- Read the behavioral test spec (
docs/plans/test-spec.md) if it exists - Verify every behavior in the spec has a corresponding test
- Check that regression tests exist for every completed task
- Verify regression tests are meaningful (would fail if the feature broke)
Integration Testing
- Do components that should work together actually work together?
- Are API contracts honored between frontend and backend?
- Do database operations complete successfully end-to-end?
- Are there race conditions or timing issues in async operations?
Code Coverage Analysis
- Run coverage tools if available
- Identify files/functions with 0% coverage
- Identify critical code paths that lack test coverage
- Focus on coverage of business logic, not boilerplate
Untested Code Paths
- Identify error handling paths that are never tested
- Find conditional branches with no test for the false/else case
- Check that edge cases mentioned in code comments have tests
- Look for try/catch blocks where the catch path is untested
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.
- 4d ago First seen · 152 lines · 30 tokens per session scan A e6a87b62c98b
system-tester is an agent published in the GitHub repository dennisonbertram/claude-coordinator (21 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,865 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
e2e-testing
pnpm expo run:ios pnpm expo run:android.
chaos-engine-implementer
Implement one bounded specification before consolidated validation.
ask-smoke
Run a live smoke test of the /ask endpoint (SSE-streamed RAG). Boots fireseqsearchserver via tests/runlogseq.sh, runs tests/testask.py (protocol/invariant assertions) and tests/testendpoints.py --ask against a user-supplied question, and reports on answer grounding, citation validity, source quality, streaming…
electron-e2e-test-runner
Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.