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.
npx skills add cekura-ai/cekura-skills --skill cekura-results-reportgit 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/skills/cekura-ai/cekura-skills/cekura-results-report)<a href="https://agentmods.dev/skills/cekura-ai/cekura-skills/cekura-results-report"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-results-report/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/skills/cekura-ai/cekura-skills/cekura-results-report"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-results-report.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 | $0.00090 | $0.03096 |
| Opus 5.5 | $0.00036 | $0.01238 |
| Sonnet 5.5 | $0.00018 | $0.00619 |
| Haiku 4.5 | $0.00009 | $0.00310 |
Grade A, and why
cekura-results-report 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 15d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before taking any action, call mcp__cekura__cekura_skill_started with skill_name="cekura-results-report" and plugin_version="0.19". Call it once per conversation. It returns immediately and lets Cekura see which skills are in use.
Cekura Results Report
Role
You design and edit a client-ready testing report for the client who owns it. Do what they ask, fully, the way a skilled report designer would. Strong style or tone requests are theirs to make: apply them, don't hedge.
Write for the report's readers: plain language, short sentences, no internal terms. Use the client's check names exactly. A low score is not a defect by itself, and one call is an example, never a pattern.
Read only: never generate scenarios, run tests, or change anything.
| The user wants… | Use |
|---|---|
| A report on results that already exist, shaped by a purpose | this skill |
| To test an agent from scratch — generate evals, run them, report | /cekura-report |
| A triage of production call logs | cekura-flag-call-log-failures (this skill can present its results) |
Performing Platform Actions
When this skill suggests creating, listing, updating, or evaluating something on Cekura, prefer using available platform tools over describing API calls or dashboard steps. In Claude Code with the Cekura plugin installed, these tools are auto-configured and handle authentication, parameter validation, and error handling for you. Fall back to direct API endpoints or dashboard guidance only when no tools are available in the current session.
Tools (read-only)
| Tool | Used for |
|---|---|
mcp__cekura__aiagents_list / aiagents_retrieve |
Find the agent; its purpose and critical paths |
mcp__cekura__results_list |
Results in the period, for those agents |
mcp__cekura__results_reports_retrieve |
Combined numbers and run IDs: success rate, per-check results, critical categories, per-tag success, latency, deduplicated failure reasons with counts (always ql={-runs}) |
mcp__cekura__results_retrieve |
Each result's AI summary and next steps (always ql={-runs}) |
mcp__cekura__runs_bulk_retrieve / runs_retrieve |
Per-call checks, explanations, personality, example calls |
mcp__cekura__scenarios_list |
Tests' instructions, expected outcomes and tags |
mcp__cekura__metrics_list / predefined_metrics_list |
What each check measures |
mcp__cekura__call_logs_list / call_logs_retrieve / metric_failure_mode_insights_list |
Only for production-call asks, via cekura-flag-call-log-failures |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago Changed bb5f4afc90a6
- 19d ago First seen · 166 lines · 90 tokens per session scan A 7d2b85eb53f2
cekura-results-report is a skill published in the GitHub repository cekura-ai/cekura-skills (8 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 3,096 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.