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 eugeniosegala/claude-connoisseur --skill testifygit clone --depth 1 https://github.com/eugeniosegala/claude-connoisseurWrote 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/eugeniosegala/claude-connoisseur/testify)<a href="https://agentmods.dev/skills/eugeniosegala/claude-connoisseur/testify"><img src="https://agentmods.dev/badge/skills/eugeniosegala/claude-connoisseur/testify/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/eugeniosegala/claude-connoisseur/testify"><img src="https://agentmods.dev/badge/skills/eugeniosegala/claude-connoisseur/testify.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 | $0.00019 | $0.00990 |
| Opus 5 | $0.00010 | $0.00495 |
| Sonnet 5 | $0.00004 | $0.00198 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
testify 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testify
Write new tests or improve existing ones, always reusing the project's established testing patterns, style of writing, mocks, and fixtures.
Files and instructions: $ARGUMENTS
Core principles
Reuse before creating
- Before writing any mock, fixture, factory, or helper, search the codebase for how other tests solve the same problem. If the project already has a pattern for it, use it
- Follow the mocking strategy already established (module mocks, dependency injection, HTTP interception, etc.). Only introduce a different approach when the existing one genuinely cannot cover the case
- Reuse existing test data builders and factories. If no factory exists and the same setup appears in multiple places, extract one into the project's shared test utilities
Mocking
- Mock only what is needed — not the entire module. Keep mocks scoped to the dependency being isolated
- Do not mock the unit under test
- Clean up mocks after each test to prevent leakage between tests
Structure and isolation
- Apply arrange-act-assert. Each test should verify a single behaviour
- Name tests to describe the scenario and expected outcome, not the implementation detail
- Eliminate shared mutable state between tests. Use per-test setup (
beforeEach) over shared setup (beforeAll) unless the data is truly static - Remove order dependencies between tests
Assertions
- Use specific assertions (
toBe(expected),assertEqual(result, expected)) over vague ones (toBeTruthy,assert result) - Every test should verify a concrete outcome — if code runs but nothing is asserted, add the missing assertion
Test data
- Extract hardcoded magic values into named constants or factory functions
- Reuse existing fixtures and builders from the project instead of duplicating setup
Robustness
- Replace time-dependent logic with mocked clocks
- Replace network/filesystem dependencies with stubs
- Remove non-deterministic ordering assumptions
- Fix incorrect framework usage (e.g.
beforeAllwhenbeforeEachis needed, missingawaiton async assertions, wrong matcher usage)
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.
- 12d ago First seen · 87 lines · 19 tokens per session scan A a79483b0b695
testify is a skill published in the GitHub repository eugeniosegala/claude-connoisseur (9 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 990 once invoked, about $0.0001 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.