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-eval-designgit 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-eval-design)<a href="https://agentmods.dev/skills/cekura-ai/cekura-skills/cekura-eval-design"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-eval-design/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-eval-design"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-eval-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 74 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 95 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 97 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 119 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.14177 |
| Opus 5.5 | $0.00094 | $0.05671 |
| Sonnet 5.5 | $0.00047 | $0.02835 |
| Haiku 4.5 | $0.00023 | $0.01418 |
Grade A, and why
cekura-eval-design 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 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.
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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cekura skill verification tag:
ack:cekura-eval-design:7k3m4qWhen 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-eval-design", verification_tag="ack:cekura-eval-design:7k3m4q", plugin_version="0.19", and skill_version="0.11.0". It returns immediately and lets Cekura see which skills are in use, and which revision of this one.
Cekura Eval Design
Create and improve Cekura evaluators (test scenarios) that exercise an AI voice or chat agent. An evaluator simulates a caller; it is not a metric (metrics score a transcript afterwards — see cekura-metric-design).
- Main agent — the agent under test. Testing agent — Cekura's simulated caller.
- Evaluator / scenario — one test case. Personality — the testing agent's voice, language and speaking behaviour. Test profile — identity/context data for the run. Conditional actions (CA) — turn-by-turn scripted testing-agent behaviour.
This file says what to do. The Cekura tools available in your session — MCP tools, REST, or the platform's own agent tools — say how: read their descriptions to pick the call, and act through them rather than describing API calls or dashboard clicks. The file is self-sufficient for authoring both modes — load a reference only for the deep detail it names.
Workflow
- Read the agent, and list its evaluators (mandatory, below).
- Decide mode and write path — behavioral vs conditional actions.
- One consolidated checkpoint — only for what you could not infer.
- Create a folder for the batch; never write into the project root.
- Author — generate, or create directly, per the write-path table.
- Attach metrics and supporting fields — profile, personality, tools, tags.
- Verify and say what it proves — reconcile every write from its own response; run if the user asked, and if nothing ran, say so.
What ships with it
14 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.
- agents/openai.yaml 278 B
- BUNDLE.md 87 KB
- examples/csv-eval-creation.md 2.7 KB
- examples/red-team-eval.md 2.8 KB
- examples/workflow-eval.md 1.5 KB
- references/api-reference.md 12 KB
- references/auto-generation.md 9.0 KB
- references/choosing-personality.md 16 KB
- references/conditional-actions.md 85 KB
- references/coverage-patterns.md 10 KB
- references/expected-outcomes.md 14 KB
- references/instruction-patterns.md 16 KB
- references/session-memory.md 1.6 KB
- references/test-data-design.md 18 KB
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 · +2 lines fb1676bb5ae2
- 22d ago Changed 9b1442a5651c
- 1mo ago Changed 5552aa475519
- 1mo ago Changed · +2 lines 18559ae49454
- 1mo ago Changed · +11 lines 188a3515ac61
- 1mo ago Changed 705bbee2b4da
- 1mo ago Changed · +1 lines b19b4c665cad
- 1mo ago Changed · +6 lines 40bf2ef82513
- 1mo ago Changed fae56b9b73a9
- 1mo ago First seen · 439 lines · 234 tokens per session scan A d44cebf901c5
cekura-eval-design 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 14,177 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
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.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.