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 skills/alexei-led/cc-thingz/improving-testsnpx skills add alexei-led/cc-thingz --skill improving-testsgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/skills/alexei-led/cc-thingz/improving-tests)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/improving-tests"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/improving-tests.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 5.1 | $0.00089 | $0.01654 |
| Opus 5 | $0.00044 | $0.00827 |
| Sonnet 5 | $0.00018 | $0.00331 |
| Haiku 4.5 | $0.00009 | $0.00165 |
Grade A, and why
improving-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 6d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Improvement
Improve tests so they catch real behavior regressions without blocking safe code changes. Suite latency is a quality attribute. Coverage is a signal, not the goal.
Role-gated action
Detect capability from tools:
- Write-capable role: inspect tests, apply changes, and run verification.
- Read-only role: inspect supplied files/output and emit changes in the Proposed Changes contract. Apply nothing; run nothing.
- Missing key tool or permission: stop with Blocked and ask for the exact artifact, access, or approval needed.
Use an interactive question tool when available for mode selection, missing scope, missing framework approval, or unsafe test-stack choices.
Route elsewhere
Do not use this for:
- production bug fixes →
fixing-code - production-code refactors →
refactoring-code - non-test code review →
reviewing-code - new feature implementation unless the user asked for TDD
- browser-only UI investigation without a test-improvement goal →
browser-automation
References
Detect languages from files in scope and read only the matching reference:
- C# →
references/csharp.md - Go →
references/go.md; for slow-suite or feedback-loop work, also readreferences/go-performance.md - Java/Kotlin →
references/java-kotlin.md - Python →
references/python.md; for slow-suite or feedback-loop work, also readreferences/python-performance.md - TypeScript →
references/typescript.md; for slow-suite or feedback-loop work, also readreferences/typescript-performance.md - Rust →
references/rust.md - Web →
references/web.md
Use generic rules only for unsupported languages.
Modes
review: find weak, duplicate, brittle, missing, slow, or flaky testsrefactor: simplify tests without changing covered behaviorcoverage: add tests for uncovered business behavior or error pathstdd: one red-green-refactor slice at a timeperformance: measure test latency and remove speed waste without weakening behaviorfull: review, refactor, performance, and add coverage
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .agentbundler/targets/claude.json 4.0 KB
- references/csharp.md 2.3 KB
- references/go-performance.md 2.8 KB
- references/go.md 3.5 KB
- references/java-kotlin.md 3.5 KB
- references/python-performance.md 3.7 KB
- references/python.md 4.1 KB
- references/rust.md 3.5 KB
- references/typescript-performance.md 3.2 KB
- references/typescript.md 3.3 KB
- references/web.md 1.7 KB
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.
- 6d ago First seen · 178 lines · 89 tokens per session scan A bf615c114ffe
improving-tests is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,654 once invoked, about $0.0004 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 skills, from other repositories
cpp-testing
C++ テストの作成/更新/修正、GoogleTest/CTest の設定、失敗またはフレーキーなテストの診断、カバレッジ/サニタイザーの追加時にのみ使用します。.
perl-testing
Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.
dotnet-test
This skill should be used when running .NET tests selectively with a build-first, test-targeted workflow. Use it for running tests with xUnit focus.
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
test-first
Drive one feature through a strict TDD Red-Green-Refactor cycle with checklists for each phase. Use when implementing new functionality test-first, or when the user runs /test-first.