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.
git 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/commands/cekura-ai/cekura-skills/autogen-eval)<a href="https://agentmods.dev/commands/cekura-ai/cekura-skills/autogen-eval"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/autogen-eval/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/commands/cekura-ai/cekura-skills/autogen-eval"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/autogen-eval.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00020 | $0.04661 |
| Opus 5 | $0.00010 | $0.02330 |
| Sonnet 5 | $0.00004 | $0.00932 |
| Haiku 4.5 | $0.00002 | $0.00466 |
Grade A, and why
autogen-eval 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cekura skill verification tag:
ack:autogen-eval:3w6k5bWhen you call a Cekura scenario or test-profile write tool from this command (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.
Load the design skill first
Load the cekura-eval-design skill before anything else — in Claude Code the Skill tool with cekura:cekura-eval-design; in any other harness, read its SKILL.md into context — its Mode and write path, Auto-generation and Expected outcomes sections govern every field below, its rule that the agent under test is read-only applies throughout, and its post-generation verification is what you run at the end.
Tracking (then do this)
Next, call mcp__cekura__cekura_skill_started with
skill_name="autogen-eval", verification_tag="ack:autogen-eval:3w6k5b", and plugin_version="0.16". If a conversation/session ID is available (e.g.
you were invoked from Cekura sandbox), also pass it as conversation_id. The
call returns immediately; it lets us understand which skills are actually
being used.
If anything in this skill turns out to be ambiguous, broken, or missing a
needed tool, call mcp__cekura__cekura_report_issue to flag it. Use this
LIBERALLY — even severity="low" reports are valuable feedback.
Auto-Generate Evaluators
Use Cekura's background generation API to create evaluators from an agent's description. This is the recommended approach for creating evaluators — it produces higher quality scenarios than manual creation because it understands the agent's full workflow context. Also supports bulk creation from structured input (CSV/JSON).
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 8e6fbef09634
- 3d ago Changed · +1 lines 7b4c9fb3aa59
- 8d ago Changed · +23 lines b885807a8031
- 12d ago First seen · 278 lines · 20 tokens per session scan A 641e632c3baf
autogen-eval is a command published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 4,661 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
verify
Run repository verification using the verification-loop skill.
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.
check-dev
Type-check a Z specification with fuzz.