evaluate-calls

evaluate-calls is a command for Claude Code from cekura-ai/cekura-skills. It costs 19 tokens per session (603 once invoked), scanned A, original, MIT.

A command for running selected Cekura evaluation measures against chosen AI-agent calls. These measures score specific aspects of an agent’s performance.

In plain words
What is it for?
Use it to select calls and metrics, then evaluate recent or specified calls and review their scores.
Why use it?
It helps check or recheck agent results against defined criteria instead of relying only on manual review.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the cekura plugin — 13 skills, 14 commands, 3 hooks, 1 MCP server shipped together

Good fit Use it to select calls and metrics, then evaluate recent or specified calls and review their scores.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cekura-ai/cekura-skills/evaluate-calls
Install

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.

Clone the repo
git clone --depth 1 https://github.com/cekura-ai/cekura-skills

Made for: Claude Code.

Or install cekura, the plugin that ships this one along with the rest of its 13 skills, 14 commands, 3 hooks, 1 MCP server.

Wrote 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.

agentmods badge for evaluate-calls

README.md
[![agentmods](https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/evaluate-calls/github.svg)](https://agentmods.dev/commands/cekura-ai/cekura-skills/evaluate-calls)
Your own site
<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.

agentmods 80×15 button for evaluate-calls

Your own site · 80×15
<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>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash d641089c932c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

cekura/commands/evaluate-calls.md · 50 lines

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

  1. 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_list with agent or project filters.
    • If the user wants specific metrics, list them: Use mcp__cekura__metrics_list with agent or project filters.
  2. 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
  3. Run evaluation: Use mcp__cekura__call_logs_evaluate_metrics_create with call IDs and metric IDs. For re-evaluation: Use mcp__cekura__call_logs_rerun_evaluation_create.

  4. Check results: After evaluation completes, offer to fetch results: Use mcp__cekura__call_logs_retrieve with 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
Changes

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.

  1. 12d ago First seen · 50 lines · 19 tokens per session scan A d641089c932c

Subscribe to this mod's changes

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.