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 steph-dove/klaussy-agents --skill fastapi-testgit clone --depth 1 https://github.com/steph-dove/klaussy-agentsWrote 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/steph-dove/klaussy-agents/fastapi-test)<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/fastapi-test"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/fastapi-test/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/steph-dove/klaussy-agents/fastapi-test"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/fastapi-test.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 | $0.00052 | $0.00788 |
| Opus 5 | $0.00026 | $0.00394 |
| Sonnet 5 | $0.00010 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
fastapi-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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- httpx-test — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write tests for the current changes. Follow these steps:
- Read CLAUDE.md to understand the project's test framework, conventions, and test commands.
- Read any
.claude/rules/*.mdwhosepaths:glob matches the changed files — they capture testing conventions specific to this layer (e.g. how API tests are structured vs. how DB tests are structured). - Identify what changed with
git diff master...HEAD(the whole branch's work), plusgit diffandgit diff --cachedfor any uncommitted edits — not a baregit diff, which would miss everything already committed on the branch. Classify the change:- Pure refactor (code moved/renamed, no behavior change): update existing tests' imports and call sites; do NOT invent new tests for behavior that already had coverage.
- New behavior or modified behavior: continue to step 4.
- Find existing test files for the modules you're testing. Read them fully — match their patterns:
- File naming and location conventions.
- Fixtures, factories, helpers, and setup/teardown patterns.
- Assertion style and test structure.
- How similar features are tested (use as a template).
- Write focused tests that cover:
- Happy path — the expected behavior works correctly.
- Edge cases — empty inputs, boundary values, null/nil, large inputs.
- Error cases — invalid input, missing data, permission failures. Test that errors are handled, not just that they don't crash.
- Behavior, not implementation — test what the code does, not how it does it. Tests should survive a refactor that preserves behavior.
- Run the test suite to verify everything passes, including your new tests.
Rules
- Match existing patterns. If the codebase uses factories, use factories. If it uses fixtures, use fixtures. Don't introduce a new testing pattern.
- Mock only: (1) external network services (HTTP APIs, payment gateways, third-party SDKs), (2) slow I/O without a fast fixture (real databases, filesystems), (3) non-deterministic sources (current time, randomness). Do NOT mock the code under test. Do NOT mock internal modules just to avoid setting them up.
- Don't under-test. If you changed a conditional, test both branches. If you added error handling, test the error path. "Happy path only" is not adequate coverage.
- Each test should test one thing. If a test name needs "and" in it, split it into two tests.
- Tests must be deterministic. No reliance on timing, ordering, or random data without seeds.
- A test that can't fail is worthless. For your key behavioral tests, make sure the assertion would actually break if the behavior were wrong — a green test against code you never verified can fail is false confidence. If a test passes no matter what, it's testing the mock or nothing.
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.
- 10d ago First seen · 39 lines · 52 tokens per session scan A 43026bf1480c
fastapi-test is a skill published in the GitHub repository steph-dove/klaussy-agents (16 stars, last pushed 13d ago), licensed MIT. It adds 52 tokens to every session and 788 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
api-endpoint
Generate a complete REST API endpoint with validation, tests, and documentation.
generate-tests
Generate comprehensive tests for a file or function.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…