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/cekura-onboarding)<a href="https://agentmods.dev/commands/cekura-ai/cekura-skills/cekura-onboarding"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/cekura-onboarding/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/cekura-onboarding"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/cekura-onboarding.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 | $0.00043 | $0.03759 |
| Opus 5 | $0.00022 | $0.01879 |
| Sonnet 5 | $0.00009 | $0.00752 |
| Haiku 4.5 | $0.00004 | $0.00376 |
Grade A, and why
cekura-onboarding 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 12d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracking (do this first)
Before doing anything else, call mcp__cekura__cekura_skill_started with
skill_name="cekura-onboarding". 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.
/cekura-onboarding
Guided end-to-end setup of a Cekura agent, from MCP preflight to a first successful test run. The full walkthrough lives in the cekura-onboarding skill; this command is only the state-aware entrypoint.
Goal: the user types /cekura-onboarding once, the command resolves the variant (testing or observability), detects the current project state, asks for one confirmation, then hands the right context to the skill. Keep output crisp: do not narrate successful detection calls.
Argument Parsing
Up to three optional positional args, in any order — the parser classifies by shape:
| Token shape | Meaning |
|---|---|
testing | observability |
Variant override. If absent, default to testing. |
Numeric, e.g. 1234 |
Project ID. Skip project picker. |
| Alphabetic phase token | Phase override (testing-flow: agent | metrics | evals | run; observability-flow: agent | ingest | evaluate | review). Detection still runs to populate handoff context. |
| Anything else | Ask one short clarifying question with AskUserQuestion. |
The variant determines which set of phase tokens is valid:
testing→agent,metrics,evals,runobservability→agent,ingest,evaluate,review
If the user passes a phase token that doesn't match the resolved variant, ask one clarifying question (don't silently re-route).
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.
- 12d ago First seen · 305 lines · 43 tokens per session scan A 05e1df7a96b0
cekura-onboarding is a command published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 3,759 once invoked, about $0.0002 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.