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 flurdy/agent-skills --skill contract-testgit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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/flurdy/agent-skills/contract-test)<a href="https://agentmods.dev/skills/flurdy/agent-skills/contract-test"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/contract-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/flurdy/agent-skills/contract-test"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/contract-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00034 | $0.01345 |
| Opus 5.5 | $0.00014 | $0.00538 |
| Sonnet 5.5 | $0.00007 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
contract-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 4d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract Test — Pact-Lite Runner
Run existing project-owned contract commands. Pact-lite exchanges JSON contracts through local files, without a broker. This skill owns execution, not health auditing, adoption, scaffolding, application/test repair, Git commits or publication. Project-facing integration belongs to the separately authorized setup contract.
No build or mutation command is preapproved by this skill's tool declaration. Explicit run intent selects phases; harness permissions, repository ownership and confirmation rules still apply.
Usage and phase boundaries
/contract-test # current service's existing contract target; ask if ambiguous
/contract-test consumer # generate for current consumer only
/contract-test sync # copy current consumer's existing output only
/contract-test provider # verify current provider's existing input only
/contract-test full # current consumer → affected providers
/contract-test full all # all declared consumers → all declared providers
/contract-test full <svc> ... # named consumers → their affected providers
/contract-test status # compatibility alias, read-only
consumer stops after generation; sync stops after copying; provider stops after verification.
Only full sequences generation → sync → optional normalization → verification. Standalone sync
neither regenerates nor normalizes files and never implies compatibility. Reject other arguments.
Status compatibility alias
Delegate /contract-test status wholly to /contract-check status, including its rendering and
unknown/error semantics. Use Skill(contract-check) or read
~/.agents/skills/contract-check/SKILL.md and follow it. If the authority is missing or unavailable,
stop with unavailable status; do not reconstruct health evidence or run tests as a fallback.
Preflight each run
- Read the owning repository instructions and actual project topology. Resolve the service and requested roles from existing documentation, test suites and recipes. A service may have both roles; do not guess which target runs consumer versus provider tests.
- Discover and inspect existing Makefile targets, package scripts or documented native commands,
including delegated scripts and hooks. Target names and language detection alone are not proof
of command behavior. In particular,
pact-publishmay contact a broker: only verified local copy commands belong to this runner. Network publication, deploys, dependency installation and setup require a separate handoff, not an expanded run. - Identify exact input/output paths, expected pairs, normalization behavior and affected provider repositories. Reuse project relationship evidence and the audit's matrix when needed; do not recreate a staleness, CI-coverage or health collector here.
- Show the execution plan: repository paths, ordered commands, phases, write destinations and affected consumer/provider pairs. Proceed only within explicit task ownership. Confirm any unresolved expansion or overwrite decision before executing it. A request for one consumer does not authorize unrelated services or repairs.
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.
- 4d ago Changed d055f9b709c1
- 1mo ago Changed · -223 lines · -5 tokens per session 3773531faebf
- 1mo ago First seen · 342 lines · 39 tokens per session scan A bb8e02bdba46
contract-test is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,345 once invoked, about $0.0001 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
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
prowler-test-api
Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
convex-test
Generate convex-test tests for the app's Convex functions.
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.