test-sweep

test-sweep is a skill for Claude Code from srnichols/plan-forge. It costs 38 tokens per session (878 once invoked), scanned A, original, MIT.

A test runner that executes unit, integration, API, GraphQL, and end-to-end tests, then combines the results into one report. End-to-end tests check a complete user flow across the system.

In plain words
What is it for?
Use it after an implementation phase or before a review gate to run .NET test categories, check for TODO and FIXME markers, and summarize passed, failed, and skipped tests.
Why use it?
It gives a single view of test health and avoids running later test groups when an earlier required group has already failed.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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.

agentmods
npx agentmods add skills/srnichols/plan-forge/test-sweep
Any agent
npx skills add srnichols/plan-forge --skill test-sweep
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

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 test-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/srnichols/plan-forge/test-sweep.svg)](https://agentmods.dev/skills/srnichols/plan-forge/test-sweep)
Your own site
<a href="https://agentmods.dev/skills/srnichols/plan-forge/test-sweep"><img src="https://agentmods.dev/badge/skills/srnichols/plan-forge/test-sweep.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 878 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.00878
Opus 5 $0.00019 $0.00439
Sonnet 5 $0.00008 $0.00176
Haiku 4.5 $0.00004 $0.00088

Measured 2d ago against content hash 75eb90ca5c05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

test-sweep 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 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.

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.

presets/dotnet/.github/skills/test-sweep/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Sweep Skill

Trigger

"Run all tests" / "Full test sweep" / "Check test health"

Steps

1. Unit Tests

dotnet test --filter "Category=Unit" --logger "console;verbosity=normal" --results-directory TestResults/

Conditional: Unit Test Failure

If unit tests fail → skip integration/E2E tests, go directly to Report.

2. Integration Tests

dotnet test --filter "Category=Integration" --logger "console;verbosity=normal" --results-directory TestResults/

3. API / GraphQL Tests

dotnet test --filter "Category=Api|Category=GraphQL" --logger "console;verbosity=normal" --results-directory TestResults/

4. E2E Tests (if available)

dotnet test --filter "Category=E2E" --logger "console;verbosity=normal" --results-directory TestResults/

5. Completeness Scan

Use the forge_sweep MCP tool to scan for TODO/FIXME/stub markers in the codebase.

6. Report

Aggregate results:

✅ Unit:        X passed, Y failed, Z skipped
✅ Integration: X passed, Y failed, Z skipped
✅ API:         X passed, Y failed, Z skipped
✅ E2E:         X passed, Y failed, Z skipped
✅ Sweep:       N markers (TODO/FIXME/stub)
──────────────────────────────────────────────
Total:          X passed, Y failed, Z skipped

On Failure

  • Show failed test names and error messages
  • Read the failing test source to diagnose
  • Suggest fixes (ask before applying)

Temper Guards

Shortcut Why It Breaks
"Skipped tests are probably flaky" Skipped tests hide real regressions. Each skip needs a documented reason and a linked issue.
"80% coverage is good enough" Coverage thresholds prevent ratcheting down. If baseline is 85%, dropping to 80% means new code is untested.
"Integration tests cover the unit tests" Integration tests are slow and brittle. Unit tests catch logic errors in milliseconds, not minutes.
"I'll fix the failing test later" Broken tests normalize failure. The suite must be green before any code ships.

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 38 tokens per session scan A 75eb90ca5c05

Subscribe to this mod's changes

test-sweep is a skill published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 878 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 2026-09-03.