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 skills add nortonx/ai-tooling-free --skill check-testsgit clone --depth 1 https://github.com/nortonx/ai-tooling-freeWrote 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/nortonx/ai-tooling-free/check-tests)<a href="https://agentmods.dev/skills/nortonx/ai-tooling-free/check-tests"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/check-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.
<a href="https://agentmods.dev/skills/nortonx/ai-tooling-free/check-tests"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/check-tests.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.01219 |
| Opus 5.5 | $0.00008 | $0.00488 |
| Sonnet 5.5 | $0.00004 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
check-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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
[<file-or-module>]
- Optional. Narrows the scope to a specific file or module; default is the branch diff vs the resolved base branch (
origin/HEAD, elsemain, elsemaster). - If the value does not resolve to an existing file or directory, the skill stops and asks rather than silently falling back to the whole branch diff.
- Examples:
/check-tests,/check-tests src/auth.ts
Copilot CLI note:
$ARGUMENTSdoes not substitute in skills; include the argument inline in your prompt.
Check Branch Tests
Analyze test coverage for this branch changes.
Scope
Diff between this branch and the base branch. Resolve the base branch in this order:
- If the user prompt names a branch explicitly, use it.
- Else
git symbolic-ref refs/remotes/origin/HEADif it resolves. - Else
mainif it exists locally, elsemaster. - If neither exists, stop and ask which branch to diff against.
If $ARGUMENTS is non-empty and resolves to an existing file or directory, narrow the scope to it. If $ARGUMENTS is a string that does not resolve to a real path, stop and ask; do not silently fall back to the whole branch diff.
Task
For each changed file in the diff:
- Identify functions/methods that were added or modified
- Check whether adequate tests exist for those changes
- Flag untested code paths, missing edge cases, and regression gaps
- Check if test format is consistent with other existing tests in the project
- AAA adherence: flag tests missing clear Arrange / Act / Assert separation or with multiple logical assertions crammed in
- FIRST compliance: flag tests that are slow, order-dependent, non-repeatable (unmocked
time.now/ random), or rely onprintinstead of assertions - Flaky-test smells:
sleep/setTimeout/ timing waits, unmocked clock or randomness, shared mutable state between tests - Mock placement: flag mocks of the SUT or its internal helpers: mocks belong at boundaries (network, filesystem, clock, randomness) only
- Behavior vs implementation: flag assertions on private methods / internal data structures; public-contract assertions only
- Near-duplicate tests: flag pairs that differ only by input: should be parameterised
- Name quality: flag vague names like
test_1,works,happy; expectshould_<expected>_when_<condition>orgiven_<state>_when_<action>_then_<outcome>
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.
- 1mo ago Changed 73d716be5fc5
- 1mo ago First seen · 97 lines · 21 tokens per session scan A 24fe3fb5d7b7
check-tests is a skill published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 18d ago), licensed MIT. It adds 21 tokens to every session and 1,219 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 2026-08-31.
Other skills, from other repositories
evaluate-skill
Evaluate an AI skill across model tiers using blind sub-agent testing.
external-site-profile-learning
Use this skill when investigating, adding, validating, or debugging external website profiles for the 99idea Playwright browser demo. It teaches how to probe selectors, classify failure modes, add config-driven profiles, and validate both heuristic and Gemini flows.
llm-evaluation
Skill "llm-evaluation" from frank-luongt/faos-skills-marketplace, covering llm evaluation, do not use this skill when, instructions, use this skill when and core evaluation types.
roblox-scrum-dev-story
Executes Roblox story implementation following a context-filled story spec file, using TDD, StyLua, Rojo, and the Roblox Studio MCP integration. Use when the user says "develop story [key]" or "implement the next story".
roblox-tdd
Use to drive Roblox / Luau implementation via red-green-refactor cycles with TestEZ or Jest-Roblox. Use when the user says "TDD", "test-driven", "write the test first", "test it properly", before implementing any non-trivial Luau module, or any time disciplined coverage is needed before code lands.
roblox-ultraqa
Use to verify Roblox work is actually complete via runtime evidence, not static inspection. Use when about to claim a feature is "done", before merging, before declaring a bug fixed, when the user says "verify this works", "prove it's done", "test it for real", "ultraqa", or any time replication / persistence / remote…