unskip-closed-tests

unskip-closed-tests is an agent for Claude Code from dotnet/skills. It costs 27 tokens per session (466 once invoked), scanned A, original, MIT.

A read-only planner for selecting eligible ignored .NET tests for trusted checking and execution. It uses a trusted manifest, which is a file listing approved test locations, identities, and eligibility details, and returns only exact approved identifiers.

In plain words
What is it for?
Use it to decide which ignored .NET tests may be safely revalidated and run.
Why use it?
It prevents stale, ambiguous, or mismatched test records from being re-enabled accidentally. It also keeps source inspection from creating new test identities outside the manifest.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to decide which ignored .NET tests may be safely revalidated and run.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dotnet/skills/unskip-closed-tests
About the project

.NET/skills is a repository of reusable instructions and custom agents that help AI coding agents work with .NET and C#. It supports tasks such as C# language-server integration, data access, diagnostics, builds, packages, upgrades, MAUI, templates, and AI development. The catalogue entries are the repository's skills, agents, plugins, and instructions.

dotnet/skills · 5,647 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/dotnet/skills

Made for: Claude Code.

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.

agentmods badge for unskip-closed-tests

README.md
[![agentmods](https://agentmods.dev/badge/agents/dotnet/skills/unskip-closed-tests/github.svg)](https://agentmods.dev/agents/dotnet/skills/unskip-closed-tests)
Your own site
<a href="https://agentmods.dev/agents/dotnet/skills/unskip-closed-tests"><img src="https://agentmods.dev/badge/agents/dotnet/skills/unskip-closed-tests/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.

agentmods 80×15 button for unskip-closed-tests

Your own site · 80×15
<a href="https://agentmods.dev/agents/dotnet/skills/unskip-closed-tests"><img src="https://agentmods.dev/badge/agents/dotnet/skills/unskip-closed-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 466 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00466
Opus 5.5 $0.00011 $0.00186
Sonnet 5.5 $0.00005 $0.00093
Haiku 4.5 $0.00003 $0.00047

Measured 10d ago against content hash f162a68fb86e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unskip-closed-tests 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 10d 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.

agentic-workflows/unskip-closed-tests/agents/unskip-closed-tests.agent.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unskip Closed Tests Planner

You are a read-only planner. The trusted manifest is the sole authority for source sites, containing declarations, test FQNs, tracking identities, remote eligibility, and revision freshness.

Required process

  1. Read GH_AW_UNSKIP_MANIFEST with jq.
  2. Require its schema_version, source_commit, and manifest_digest to equal the trusted environment values.
  3. Consider only candidates where decision.eligible is true.
  4. Inspect the source only at each candidate's recorded repository-relative path and span. Use it to identify ambiguity, never to create a replacement identity.
  5. Defer class-level sites unless the manifest already enumerates every affected owner.test_fqns entry and has no class-level deferral.
  6. Select only IDs copied byte-for-byte from candidate_id.
  7. Call exactly one allowed output and stop.

Mandatory deferrals

Defer any candidate when:

  • its source path, span, owner, containing type chain, declaration identity, test FQN, issue identity, or state appears inconsistent;
  • a method's recorded owner is not its actual syntax ancestor;
  • class-level inheritance, nesting, partial declarations, or incomplete test enumeration is present;
  • issue context does not clearly correspond to the ignored test even though the deterministic remote state is eligible;
  • the candidate depends on an inferred anchor, source rewrite, or remote fact.

Never infer accessibility, issue state, PR merge state, containing types, method identities, or tests affected by a class-level attribute.

Output

For one or more selected candidates, call apply_verified_unskips once with the exact manifest digest and JSON array string of unique candidate IDs. The read-only verification and authorization jobs may retain fewer candidates after source, remote, build, and TRX revalidation.

When no candidate remains, call noop once. Do not edit files, run builds or tests, create a patch, construct a PR body, or call any other output.

Read the full file on GitHub · 51 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.

  1. 10d ago First seen · 51 lines · 27 tokens per session scan A f162a68fb86e

Subscribe to this mod's changes

unskip-closed-tests is an agent published in the GitHub repository dotnet/skills (5,647 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 466 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-06.

Related

Other agents, from other repositories

Expert .NET software engineer mode instructions

Provide expert .NET software engineering guidance using modern software design patterns.

github/awesome-copilot · 21 tokens

dnp-tdd-developer-hard

🔬 Deep TDD for complex .NET tasks: architectural decisions, ambiguous edge cases, high-risk refactoring. Writes both tests and production code with rigorous RED-GREEN-REFACTOR.

zdanovichnick/dotnet-pilot · 47 tokens

dnp-tdd-developer-easy

⚡ Fast TDD for routine .NET tasks: clear requirements, low-risk changes, well-defined scope. Writes both tests and production code following RED-GREEN-REFACTOR.

zdanovichnick/dotnet-pilot · 46 tokens

testability-migration

Orchestrates end-to-end testability migration for .NET codebases: detects untestable static dependencies, generates wrapper abstractions or guides built-in adoption, and performs mechanical bulk migration of call sites. Use when asked to make code testable, remove static coupling, migrate to TimeProvider, adopt…

F-U-S-E-E/FuseDevelopmentGroup · 79 tokens

test-engineer

.NET/C# QA engineer specialized in test strategy, test writing, and coverage analysis — xUnit v3 (or v2) or MSTest with native Assert.X, WebApplicationFactory, Testcontainers, Microsoft.Playwright, and Avalonia.Headless. Use for designing test suites, writing tests for existing code, or evaluating test quality.

peterblazejewicz/claude-plugins · 73 tokens

test-writer

Generates xUnit test suites for .NET code. Use for mechanical test generation, filling coverage gaps, or writing tests for a newly implemented feature. Runs on Haiku for cost efficiency.

cwoodruff/dotnet-claude-workshop-content · 42 tokens