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/eval-results)<a href="https://agentmods.dev/commands/cekura-ai/cekura-skills/eval-results"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/eval-results/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/eval-results"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/eval-results.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 | $0.00014 | $0.00889 |
| Opus 5 | $0.00007 | $0.00445 |
| Sonnet 5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
eval-results 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 3d 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 — 84 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="eval-results". 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.
Eval Results & Analysis
Fetch evaluation results and provide analysis of common workflow issues.
Process
-
Get results: Fetch recent results for an agent or a specific result set: Use
mcp__cekura__results_listwith agent or scenario filters. Usemcp__cekura__results_retrievefor a specific result. -
Parse results: For each result, extract:
- Scenario name and tags
- Pass/fail status —
successis the project rubric's verdict when rubric rules exist (all rules ANDed by default); otherwise it follows Expected Outcome and any failed binary metric - Expected outcome score vs actual behavior, reported separately from
success: a run with Expected Outcome passed butsuccess: falsefailed a project-wide rubric rule (rubricnames it), possibly a metric the scenario never exercised - Metric evaluations (if metrics were attached)
-
Summarize by category: Group results by category tag:
Scheduling: 8/10 passed Cancellation: 5/6 passed Verification: 6/7 passed Safety: 7/9 passed -
Identify patterns: Look for common failure themes:
- Which workflow areas have the most failures?
- Are failures concentrated in specific scenarios (edge cases, tool errors)?
- Do failures share common root causes?
-
Generate issue report: Provide a structured summary:
- Critical issues: Failures in must-have scenarios
- Patterns: Recurring failure types across multiple scenarios
- Recommendations: Specific improvements to the agent's description or tools
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.
- 3d ago Changed · +2 lines 36b95aa1556f
- 12d ago First seen · 82 lines · 14 tokens per session scan A b3562e8d4672
eval-results is a command published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 889 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.