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 hautc-it/cil --skill testinggit clone --depth 1 https://github.com/hautc-it/cilWrote 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/hautc-it/cil/testing)<a href="https://agentmods.dev/skills/hautc-it/cil/testing"><img src="https://agentmods.dev/badge/skills/hautc-it/cil/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/hautc-it/cil/testing"><img src="https://agentmods.dev/badge/skills/hautc-it/cil/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 | $0.00055 | $0.00721 |
| Opus 5.5 | $0.00022 | $0.00288 |
| Sonnet 5.5 | $0.00011 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Testing
Validate behavior, not implementation.
Project Context
Existing project
- Read
CLAUDE.md— project rules take priority (mock policy, test scope, forbidden patterns). - Identify the test runner — check the project manifest or config files to find what's already installed. Use it — never add a second test framework.
- Read existing tests — find 2–3 test files in the same module. Match their structure: file naming, test block nesting, assertion style, import paths, setup/teardown patterns.
- Check mock policy — does the project use real dependencies in tests, or mocks/stubs? Never introduce a strategy that contradicts what's already in use.
- Search memory —
memory_search("testing [component] conventions")— retrieve prior decisions about test scope or mock strategy. - Apply the protocol below within the project's conventions, not instead of them.
Greenfield project
No tests yet — you are establishing the conventions others will follow:
- Choose the test runner — use the standard one for the language/platform. Don't introduce a less-common alternative without a clear reason.
- Decide file layout upfront — co-located next to source files, or in a separate test directory. Pick one and document it. Changing later requires moving many files.
- Set the mock policy — prefer real dependencies where practical (catches integration bugs); mock only at expensive or unstable external boundaries. Document the policy in
CLAUDE.md. - Write the first test as the template — naming convention, assertion style, setup/teardown — this becomes the pattern every contributor follows.
- Store the decision:
memory_store("decision", "testing: runner=[x], layout=[x], mock policy=[x]", ["testing", "conventions"])
Protocol
- Boundary first — Test the outermost contract (API, function signature, CLI output).
- Happy path — Core case works with valid input.
- Edge cases — Empty input, null, zero, max values, type boundaries.
- Error cases — Invalid input fails with the right error and message.
- Regression — Every bug fix gets a test that would have caught it.
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 · 69 lines · 55 tokens per session scan A 076d9cccf953
testing is a skill published in the GitHub repository hautc-it/cil (1 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 721 once invoked, about $0.0002 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
mvp-readiness
Runs a structured MVP quality-gate audit covering stability, security, logging, docs, and implementation integrity. Reports pass/fail with evidence.
requirements-generator
Generates structured requirements documents with functional and non-functional requirements, Gherkin acceptance criteria, edge cases, and out-of-scope items.
test-writer
Generates comprehensive unit and integration tests for a given file or function, auto-detecting the project test framework and matching existing test style.
prove-the-gates
Audit the repository's own checks — for each test, gate and CI script, establish what it guards, whether anything still runs it, and whether it actually fails when you break what it protects. Use when the user says "prove the gates", "are our tests real", "audit the test suite", "which checks are fake", "תוכיח את…
tools-unity-test-framework
Unity Test Framework patterns for EditMode and PlayMode tests including async testing, mocking, and test organization.
strict-enforcement
Use when running claudikins-kernel:verify, checking implementation quality, deciding pass/fail verdicts, or enforcing cross-command gates — requires actual evidence of code working, not just passing tests.