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-generate-scenariosgit 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-generate-scenarios)<a href="https://agentmods.dev/skills/cekura-ai/cekura-skills/cekura-generate-scenarios"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-generate-scenarios/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-generate-scenarios"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-generate-scenarios.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00234 | $0.11609 |
| Opus 5.5 | $0.00094 | $0.04644 |
| Sonnet 5.5 | $0.00047 | $0.02322 |
| Haiku 4.5 | $0.00023 | $0.01161 |
Grade A, and why
cekura-generate-scenarios 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.
How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cekura skill verification tag:
ack:cekura-generate-scenarios:7q3n6vWhen you call a Cekura scenario or test-profile write tool from this skill (scenarios_*/test_profiles_*create and update calls), pass this exact string as theskill_ackargument on that tool call. It confirms to the Cekura MCP server that this design playbook is loaded in context. Metric writes (metrics_create,metrics_bulk_create,metrics_partial_update) use a metric-family tag instead — loadcekura-metric-designfirst and pass its tag there.
Before taking any action, call mcp__cekura__cekura_skill_started with skill_name="cekura-generate-scenarios", verification_tag="ack:cekura-generate-scenarios:7q3n6v", and plugin_version="0.19". It returns immediately and lets Cekura see which skills are in use.
generate-scenarios
Convert real production failures into evaluator scenarios so the next regression run catches them. Signal is mined from call logs — what real callers did, where the agent broke, and what the right behavior would have been. Every scenario produced traces back to at least one call log; nothing is invented.
This skill is read-first: it never creates a scenario without an explicit user OK on the proposed set.
Write path — decided by scenario_type, not by preference
scenario_type |
Write path |
|---|---|
conditional_actions — drop, tool_error, workflow_miss (turn-by-turn replays) |
mcp__cekura__scenarios_create with the drafted conditions — the evidence call dictates the turn sequence, which is the one case that outranks generation. When you have the failure mode but not the turns, scenarios_generate_bg with simulation_type: "conditional_actions" emits grounded, validated conditions. |
instruction — drift, hallucination, comprehension, refusal, safety (free-form) |
Generate: mcp__cekura__call_logs_create_scenarios (preferred — grounded in the evidence calls) or scenarios_generate_bg, passing the drafted expected_behavior + failure mode as extra_instructions. Behavioral instructions are never hand-authored. |
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 Changed cd7fe552455f
- 15d ago Changed 0fda3ad72749
- 22d ago Changed beff71624e2c
- 1mo ago Changed 8d67cb4cf399
- 1mo ago Changed 766d2b52bcf2
- 1mo ago Changed 6897264e813c
- 1mo ago Changed 23f6234972ed
- 1mo ago Changed bd6d3f54b7f2
- 1mo ago First seen · 499 lines · 234 tokens per session scan A b22bbcbb9224
cekura-generate-scenarios is a skill published in the GitHub repository cekura-ai/cekura-skills (8 stars, last pushed today), licensed MIT. It adds 234 tokens to every session and 11,609 once invoked, about $0.0009 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.