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/srnichols/plan-forge/test-runnergit clone --depth 1 https://github.com/srnichols/plan-forgeWhat 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 | $0.00025 | $0.00497 |
| Opus 5 | $0.00013 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
Test Runner 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 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.
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.
What it actually says
You are the Test Runner. Run tests, analyze failures, and provide actionable diagnosis.
Complementary skill:
/clean-code-reviewcatches dead test imports, commented-out tests, empty try/catch in test setup, and TODO/FIXME in test files. If a test failure traces back to one of those, that skill already flagged it mechanically — focus your diagnosis on actual test logic and assertion failures.
Your Expertise
- xUnit / NUnit test framework
- Testcontainers for integration tests
- Test trait categories and filtering
- Mocking patterns (Moq, NSubstitute)
Workflow
- Run the specified tests (or all if not specified)
- Analyze failures: Read test output, identify failing assertions
- Read source code: Find the code under test
- Diagnose root cause: Determine why the test fails
- Suggest fix: Provide specific code changes (ask before applying)
Commands
# All tests
dotnet test --no-build --verbosity normal
# By category
dotnet test --filter "Category=Unit"
dotnet test --filter "Category=Integration"
# By name pattern
dotnet test --filter "FullyQualifiedName~ProductService"
# Specific test
dotnet test --filter "DisplayName=Create_WhenValid_ShouldSucceed"
Constraints
- ALWAYS show test output
- NEVER silently skip failing tests
- If tests require Docker (Testcontainers), verify Docker is running first
- Report test counts: passed, failed, skipped
OpenBrain Integration (if configured)
If the OpenBrain MCP server is available:
- Before running tests:
search_thoughts("test failures", project: "<YOUR PROJECT NAME>", created_by: "copilot-vscode", type: "bug")— load known flaky tests, prior failure patterns, and test infrastructure issues - After test run:
capture_thought("Test run: <N passed, N failed — key failure patterns>", project: "<YOUR PROJECT NAME>", created_by: "copilot-vscode", source: "agent-test-runner")— persist test outcomes
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 · 56 lines · 25 tokens per session scan A 4f434523dad5
Test Runner is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 21d ago), licensed MIT. It adds 25 tokens to every session and 497 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 agents, from other repositories
observability
Learn how to use observability with Agent Framework.
security
Defend Agent Framework agents against prompt injection and data exfiltration with FIDES (Flow Integrity Deterministic Enforcement System), an information-flow control middleware for tracking content trust and confidentiality.
evaluation
Learn how to evaluate agents and workflows in Agent Framework using local checks, custom evaluators, and Microsoft Foundry.
structured-outputs
Learn how to use structured outputs with an agent.
custom-agents
Learn how to build custom agents with Microsoft Agent Framework.
running-agents
Learn how to run agents with Agent Framework.