Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/smart-test/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/smart-ai-memory/attune-ai/smart-test)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/smart-test"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/smart-test.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 | $0.00041 | $0.00775 |
| Opus 5 | $0.00020 | $0.00387 |
| Sonnet 5 | $0.00008 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
smart-test 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 3d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Test
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="smart-test", mode="preamble") and
display the returned preamble text as a blockquote. Then
tell the user they can say "tell me more" for a step-by-step
guide, or answer the scoping questions below to proceed.
If the MCP call fails, fall back to:
Smart Test — Finds untested code and generates pytest tests with edge cases and error paths.
Scoping
Before running, ask:
- Target: "Which file or module needs tests?"
- Approach: "What kind of testing?"
- Gap analysis — Find untested public functions
- Generate tests — Write pytest tests for a module
- Both — Audit gaps then generate tests for them
MCP Tools
| Tool | What It Does |
|---|---|
test_audit |
Coverage audit and gap detection |
test_generation |
Generate unit tests with edge cases |
test_gen_parallel |
Batch test generation (10-50 modules) |
Execution
Shared command workspace (preferred)
Open adapter smart-test with the validated target and gap, generate, or
both approach. The bound audit action is read-only. Publish the actual audit
as audit_result, including exact proposed test paths before any generator is
called. Present the proposal widget or Markdown; only an explicitly confirmed
generate_tests action authorizes those paths.
After test_generation, publish generation_result with the exact files
reported from disk. The adapter independently hashes those files and rejects
writes outside or different from the approved set. Run the returned test
probe and publish its exact command and exit code as validation_result.
Generator or test failure must say “did not complete” and retain the written
paths for rollback; it may not claim tests were created successfully. Preserve
the same preview/write/validation gates in compact text when the shared tools
are unavailable.
For gap analysis:
test_audit(path="<target>")
For targeted test generation:
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.
- 3d ago Changed · +17 lines caaaa9e52974
- 7d ago First seen · 97 lines · 41 tokens per session scan A 090e9760d383
smart-test is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 775 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.
Other skills, from other repositories
axiom-swift-testing
Use when writing unit tests, adopting Swift Testing framework, making tests run faster without simulator, architecting code for testability, testing async code reliably, or migrating from XCTest - covers @Test/@Suite macros.
solidity-testing
Every core function must have tests covering.
axiom-ios-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or asking about Swift Testing vs XCTest. Covers unit tests, UI tests, fast tests without simulator, async testing, test architecture.
prodtest
Senior-QA test pass on a newly implemented feature. Detects the project's real test stack, writes unit and functional/integration tests, then drives the running app with Playwright for end-to-end coverage, saving screenshots to a gitignored folder for human review. Asks upfront whether found bugs should be fixed or…
test-gen
Generate tests for code — use when asked to write tests, create a test suite, add test coverage, or generate unit/integration tests for a file or module. Triggers the deterministic test-gen workflow (analyze → generate via test-writer agent → run-fix loop → report).
verify
Verify recent code changes work end-to-end by building, running tests, and exercising affected features. Use when the user asks to verify changes, requests "/verify", or wants confirmation a feature actually works.