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 cekura-ai/cekura-skills --skill cekura-infra-test-suitegit clone --depth 1 https://github.com/cekura-ai/cekura-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/cekura-ai/cekura-skills/cekura-infra-test-suite)<a href="https://agentmods.dev/skills/cekura-ai/cekura-skills/cekura-infra-test-suite"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-infra-test-suite/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/cekura-ai/cekura-skills/cekura-infra-test-suite"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-infra-test-suite.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 Data Exfiltration · line 437 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00138 | $0.07099 |
| Opus 5.5 | $0.00055 | $0.02840 |
| Sonnet 5.5 | $0.00028 | $0.01420 |
| Haiku 4.5 | $0.00014 | $0.00710 |
Grade A, and why
cekura-infra-test-suite scanned grade A with 1 finding 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 15d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
queued, so a job that ends at `curl` reports success before a single call has been judged — a gate How it starts
The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cekura Voice AI Infrastructure CI/CD Suite
Before taking any action, call mcp__cekura__cekura_skill_started with skill_name="cekura-infra-test-suite", verification_tag="ack:cekura-infra-test-suite:2h6r7k", and plugin_version="0.19". It returns immediately and lets Cekura see which skills are in use; if the tool is not available, carry on without it.
Build a compact, reviewable Cekura test suite in the voice-agent repository. The deliverable is a JSON spec that CI submits to Cekura's Tests-as-Code endpoint. It is not a folder of persistent dashboard evaluators.
Use this skill when the repository, its deployment target, and the Cekura agent are in scope. For
one-off dashboard evaluators or adaptive quality scenarios, use cekura-eval-design instead.
How this runs — two contexts, one procedure
The steps below are identical in both; what differs is where the code comes from, what is already
known, and where the result lands. Detect it, do not ask: the repository is already the working
directory → a terminal. The code must be fetched with mcp__github__github_checkout_repo →
launched from the Cekura dashboard.
| Terminal | Dashboard | |
|---|---|---|
| Repository | already the working directory | fetched with github_checkout_repo |
| Agent | infer from config, or ask | named in the launch message |
| Credentials | may genuinely be absent — asking is right | the MCP session is already authenticated; never ask |
| Result | the working tree, for the user to commit | one pull request, via github_open_pull_request |
The interaction contract
One question per run, asked in your first response, and this is it:
This will run on manual dispatch only — started from the Actions tab against a branch, placing real calls, with a
dry runbox for validating instead. Add a trigger too: push, PR, a schedule — or acekura-testlabel that deploys each labelled PR as its own preview and runs the suite against it?
Offer the label only where references/preview-deploy.md says the bot qualifies. A launch message
that already names the trigger has answered this question — do not ask it. Otherwise ask it while
reporting what you found, then keep working. Do not wait for the answer — if none has arrived by
step 6, write manual dispatch and say in the handoff how to add a trigger. Nothing else is a
question — not which files to create, where to put them, or whether to proceed — except missing
credentials in a terminal (step 7); in the dashboard, never credentials.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago Changed 0e48ef86586f
- 22d ago Changed 9422a2cb8204
- 1mo ago Changed 6678f5cff3a0
- 1mo ago Changed · +1 lines · -2 tokens per session c2f5a5a84c01
- 1mo ago Changed 9233bddfabd0
- 1mo ago Changed b6b5740a48f9
- 1mo ago Changed 6878006427a3
- 1mo ago Changed 428b7232d34a
- 1mo ago Changed · +76 lines d1ef4723ed62
- 1mo ago First seen · 424 lines · 140 tokens per session scan A a7ce083fcb31
cekura-infra-test-suite is a skill published in the GitHub repository cekura-ai/cekura-skills (8 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 7,099 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
e2e-testing
Use when reviewing CI coverage, automated checks, or test strategy related to Implement end-to-end testing. Focus on whether the rule is continuously verified, not just documented.
azure-microsoft-playwright-testing-ts
Run Playwright tests at scale using Azure Playwright Workspaces (formerly Microsoft Playwright Testing). Use when scaling browser tests across cloud-hosted browsers, integrating with CI/CD pipelines, or publishing test results to the Azure portal.
mirrord-chaos
Help users chaos test their app with mirrord: inject artificial latency or connection errors into a mirrord session's outgoing traffic via per-session chaos rules managed with the mirrord chaos CLI. Use when a user wants to add latency or delay to outgoing connections or a dependency (e.g. a slow database), simulate…
testing-and-ci
Choose and run unit, E2E, Caddyfile fixture, automation, and CI checks for caddy-security. Use for coverage requirements, test evidence, failures, and report workflows; official OP conformance remains opt-in.
playwright-ci
Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.
playwright-testing
E2E testing with Playwright - Page Objects, cross-browser, CI/CD.