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 agentmods add skills/lfyxhappy/lfcode/contract-test-engineernpx skills add lfyxhappy/lfcode --skill contract-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/contract-test-engineer)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/contract-test-engineer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/contract-test-engineer.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.00353 |
| Opus 5 | $0.00027 | $0.00177 |
| Sonnet 5 | $0.00011 | $0.00071 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
contract-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 today.
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
Contract Test Engineer
Make cross-boundary expectations explicit and executable.
Workflow
- Read repository instructions, authoritative schemas or specifications, versioning policy, provider and consumer code, and existing compatibility tests.
- Identify the contract surface: endpoints or topics, request and response fields, defaults, nullability, errors, ordering, encoding, authorization, and version behavior.
- Choose the authoritative source of truth and record which fields are guaranteed, deprecated, optional, or implementation-specific.
- Create focused examples covering valid requests, invalid input, error payloads, omitted and unknown fields, backward compatibility, and forward-compatible parsing where the product supports it.
- Exercise the provider and consumer through their real serialization or transport boundary, using generated or local isolated artifacts when available.
- Verify the affected producer and consumer checks. Flag any required coordinated deployment, migration window, or remote validation instead of assuming it is safe.
Boundaries
- Keep contract assessment read-only unless the user asks to change tests, schemas, or implementation.
- Do not infer a compatibility promise from one implementation detail or a single happy-path sample.
- Do not publish schemas, mutate a shared registry, call production endpoints, or change compatibility versions without explicit authorization.
- Preserve unknown fields and error semantics when the documented compatibility policy requires them.
Completion Check
Report the contract source, producer and consumer coverage, compatibility assumptions, breaking-change findings, verification evidence, and remaining coordination work.
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.
- today First seen · 29 lines · 54 tokens per session scan A 1d9271eaec76
contract-test-engineer is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 353 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 2026-09-05.
Other skills, from other repositories
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
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.
Review changes (multi-agent)
Delegate read-only reviewers over the local changes/branch and consolidate findings.