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 notorious-ai/claude-plugins --skill testinggit clone --depth 1 https://github.com/notorious-ai/claude-pluginsWrote 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/notorious-ai/claude-plugins/testing)<a href="https://agentmods.dev/skills/notorious-ai/claude-plugins/testing"><img src="https://agentmods.dev/badge/skills/notorious-ai/claude-plugins/testing/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/notorious-ai/claude-plugins/testing"><img src="https://agentmods.dev/badge/skills/notorious-ai/claude-plugins/testing.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 | $0.00068 | $0.01747 |
| Opus 5.5 | $0.00027 | $0.00699 |
| Sonnet 5.5 | $0.00014 | $0.00349 |
| Haiku 4.5 | $0.00007 | $0.00175 |
Grade A, and why
testing 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Committed Go Tests
Imitation is the method, split by role. The exemplar/ files are annotated
verbatim snippets from the Go team's own packages; imitate them, because
canon is the source and nothing bundled is canon of its own. WRITING tests:
after go doc -all, match the package's disjoint symbol clusters to
archetypes via exemplar/README.md and read ONLY the matched samples, as
inspiration — generation is creative synthesis; the review loop carries the
nuance load. REVIEWING or critiquing tests: read the whole exemplar corpus
with its annotations — evaluation is discrimination; the corpus is your
grading sense, calibrated by evaluator-cases.md, the rulings evaluators
mis-graded before. Load references on scenario, not sooner:
references/helpers.md— a test wants a helper, a fake, or a dependency.references/tables-and-subtests.md— cases repeat, or a t.Run forms.references/fixtures.md— file inputs, long literals, malformed cases.references/examples.md— an Example function is written, reviewed, or judged.references/concurrency.md— goroutines, panics, races, invalid inputs.references/harnesses.md— conformance suites and testing packages.
The contract and the golden hierarchy
Test freely while developing: throwaway tests, tailored executables, build-tagged experiments, runs under constrained CPU (a weak-runner flake is a contract failure too). None of it gets committed: committed _test.go files carry only the package's contract with its users, so a breaking change either fails the tests or amends them to state the new contract; unit tests are rapid iteration against a contract, not bug hunts.
The package's prose, the package doc and exported doc comments that godoc publishes and users rely on, is the most sacred part of its contract. Authority descends through exported signatures, code behavior, and unexported comments, down to the existing tests: the least golden thing in the room, never the standard. A test authored from the implementation mirrors it, bugs included; one authored from the prose holds the package to its promises. Drift is a finding, never silently absorbed: ask the owner, else side with prose unless the code moved deliberately, then fix the prose. Go-doc-first makes this operational: draft the test plan from go doc -all alone, no bodies, before opening source, so every collision is surfaced drift.
What ships with it
17 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.
- evaluator-cases.md 9.2 KB
- exemplar/.provenance.md 1.5 KB
- exemplar/archive-zip.md 2.5 KB
- exemplar/cmd-gofmt.md 3.3 KB
- exemplar/database-sql.md 3.8 KB
- exemplar/encoding-json.md 2.1 KB
- exemplar/go-parser.md 2.9 KB
- exemplar/hash-maphash.md 3.0 KB
- exemplar/io.md 4.0 KB
- exemplar/README.md 3.8 KB
- exemplar/strings.md 3.7 KB
- references/concurrency.md 2.2 KB
- references/examples.md 4.8 KB
- references/fixtures.md 1.3 KB
- references/harnesses.md 4.2 KB
- references/helpers.md 2.7 KB
- references/tables-and-subtests.md 2.4 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.
- 1mo ago First seen · 131 lines · 68 tokens per session scan A 24dfa035334b
testing is a skill published in the GitHub repository notorious-ai/claude-plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,747 once invoked, about $0.0003 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
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.