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 lfyxhappy/lfcode --skill property-test-engineergit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/property-test-engineer)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/property-test-engineer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/property-test-engineer/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/lfyxhappy/lfcode/property-test-engineer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/property-test-engineer.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 | $0.00059 | $0.00373 |
| Opus 5.5 | $0.00024 | $0.00149 |
| Sonnet 5.5 | $0.00012 | $0.00075 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
property-test-engineer 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.
What it actually says
Property Test Engineer
Test invariants over input families instead of enumerating only hand-picked examples.
Workflow
- Read repository instructions, target code, existing example tests, domain constraints, and the available property-testing or fuzzing framework.
- State one or more independently observable properties: invariants, round trips, ordering, idempotence, bounds, preservation, equivalence, or metamorphic relations.
- Define generators that produce valid and deliberately invalid inputs with realistic distributions, including boundary values and structural variations.
- Keep the oracle independent from the implementation under test. Combine a property with a simpler reference model only when the model represents the contract rather than duplicated production logic.
- Configure deterministic seeds, bounded runtime, useful shrinking, and failure output that records the minimized counterexample and reproduction command.
- Add a focused example regression case for a discovered bug when it improves readability, then run the property test and affected package checks.
Boundaries
- Keep property design and review read-only unless the user asks to change tests or implementation.
- Do not use unbounded generators, opaque randomness, or huge case counts that make normal verification impractical.
- Do not call external production systems or mutate shared state from generated cases without explicit authorization and strict isolation.
- Do not replace ordinary examples when a specific user-visible scenario is clearer as an example test.
Completion Check
Report the property, generator domain, oracle, seed and shrinking behavior, runtime budget, discovered counterexamples if any, verification result, and coverage limits.
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 · 29 lines · 59 tokens per session scan A f2fea763de02
property-test-engineer is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 26d ago), licensed MIT. It adds 59 tokens to every session and 373 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 2026-09-05.
Other skills, from other repositories
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.
Check work (verify against criteria)
Verify an implementation against acceptance criteria with a reviewer and a tester.
Write tests
Add focused, meaningful tests for code — happy path plus the edge cases that matter.
investigate
A structured root-cause investigation method for software bugs. It moves from history and reproduction through tested hypotheses, a focused fix, verification, and a report.
ai-evaluation-patterns
Guides expert-level ai evaluation patterns implementation: ai-ml and testing decision frameworks, production-ready patterns, and concrete templates for ai evaluation patterns workflows. Use when the user asks about ai evaluation patterns, ai evaluation patterns configuration, or ai-ml best practices for ai projects.…
performance-engineer
Becomes a senior performance engineer who identifies bottlenecks, designs optimization strategies, and conducts load testing using systematic profiling and benchmarking methodology. Use when the user needs performance analysis, load testing, bottleneck identification, latency optimization, or capacity planning. Do NOT…