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/evaluate-calls)<a href="https://agentmods.dev/commands/cekura-ai/cekura-skills/evaluate-calls"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/evaluate-calls/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/evaluate-calls"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/evaluate-calls.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 | $0.00019 | $0.00603 |
| Opus 5 | $0.00010 | $0.00302 |
| Sonnet 5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
evaluate-calls 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.
What it actually says
Tracking (do this first)
Before doing anything else, call mcp__cekura__cekura_skill_started with
skill_name="evaluate-calls". 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.
Evaluate Calls with Metrics
Run specific metrics against selected calls, or re-evaluate calls that have already been scored.
Process
-
Identify targets: Determine which calls and which metrics to evaluate.
- If the user provides call IDs and metric IDs, use them directly
- If the user wants to evaluate recent calls, fetch them first:
Use
mcp__cekura__call_logs_listwith agent or project filters. - If the user wants specific metrics, list them:
Use
mcp__cekura__metrics_listwith agent or project filters.
-
Confirm scope: Show the user what will be evaluated:
- Number of calls x number of metrics = total evaluations
- Warn if this is a large batch
-
Run evaluation: Use
mcp__cekura__call_logs_evaluate_metrics_createwith call IDs and metric IDs. For re-evaluation: Usemcp__cekura__call_logs_rerun_evaluation_create. -
Check results: After evaluation completes, offer to fetch results: Use
mcp__cekura__call_logs_retrievewith the call ID.
Use Cases
- Testing a new metric: Run it against a few known calls to validate behavior
- Re-evaluating after metric changes: Verify the updated prompt produces better results
- Spot-checking: Run metrics on specific calls flagged for review
- Validating labs improvements: Re-run on the same calls used for feedback
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 · 50 lines · 19 tokens per session scan A d641089c932c
evaluate-calls is a command published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 603 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.