A testing assistant for finding relevant tests and investigating failures in .NET projects. It uses code-analysis tools to discover test projects, run tests, and narrow down problems.

Use it when tests fail locally or in CI, or when you need tests related to changed files. It can discover tests, run focused tests, and help analyze failures and possible flaky tests.

It reduces the time spent searching for the right tests after a change or when continuous integration reports failures.

test-triage — Skill for Claude Code by darylmcd

Install

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.

Any agent

npx skills add darylmcd/Roslyn-Backed-MCP --skill test-triage

Clone the repo

git clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCP

Made for: Claude Code.

Or install roslyn-mcp, the plugin that ships this one along with the rest of its 44 skills, 5 agents, 2 hooks, 2 MCP servers.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/test-triage/github.svg)](https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/test-triage)

Your own site

<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/test-triage"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/test-triage/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/test-triage"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/test-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 750 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00045	$0.00750
Opus 5	$0.00023	$0.00375
Sonnet 5	$0.00009	$0.00150
Haiku 4.5	$0.00005	$0.00075

Measured 12d ago against content hash 23776de163f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

test-triage 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 12d 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.

skills/test-triage/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Triage

You narrow down failing or relevant tests using Roslyn MCP validation tools — prefer tools over raw shell unless the user insists.

Input

$ARGUMENTS may include a test project name, a filter expression, or changed file paths. If missing, start from full discovery then narrow.

Server discovery

Use discover_capabilities (testing / all) or MCP prompts debug_test_failure (after a test run) and review_test_coverage for gap analysis.

Workflow

workspace_load if needed; workspace_status for health.
test_discover — summarize frameworks, projects, and test counts.
test_run — full suite, or scoped with project/filter from arguments.
On failures: use output stack traces; symbol_search / go_to_definition to jump to code; MCP prompt debug_test_failure to structure the next steps.
After local edits: test_related for symbols or test_related_files for changed file paths, then test_run on the smallest useful scope.
Optionally build_workspace if compilation state is uncertain before tests.

Flake detection mode

Invoke with --detect-flakes[=N] (default N=5) or ask "is this test flaky?" to bucket failing tests by determinism.

After Step 3 produces a list of failures, take the failing test filter and call test_run with that filter N times in sequence. Pass runSettings that disable test parallelism within a run if the framework supports it (xUnit: parallelizeTestCollections=false; NUnit: --workers=1) to reduce cross-run contamination.
Bucket each failing test across the N runs:
- deterministic-fail: failed in N/N runs — real bug, fix the assertion or the system under test
- flake: failed in 1 < k < N runs — flaky, likely timing/ordering/state-leak
- transient-pass: failed once and passed in all retries — likely environmental (clock skew, tmp dir race)
Produce a per-test row with bucket, pass-rate (k passes / N), and suggested next action:
- deterministic-fail → inspect the assertion + surrounding code via symbol_info / get_source_text
- flake → look for DateTime.Now, Task.Delay, new Random() without seed, shared statics in the SUT — scan via symbol_search on likely suspects
- transient-pass → annotate as suspected flake; do not act unless it recurs

Read the full file on GitHub · 49 lines

Changes

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.

12d ago First seen · 49 lines · 45 tokens per session scan A 23776de163f6

Subscribe to this mod's changes

test-triage is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 750 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 2026-08-31.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

test-triage