What is cekura-create-agent?

A guided setup workflow for connecting a main AI agent to Cekura, including its provider, tools, knowledge base, and integrations. Cekura is a platform for testing and measuring AI agents.

Use it to create or connect an agent, configure provider access, add mock tools and knowledge, set variables, connect supported services, and verify the setup.

It organizes the many configuration steps involved in adding an agent, reducing missed settings and provider-specific mistakes.

cekura-create-agent — Skill for Claude Code and Codex by cekura-ai

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.

Any agent

npx skills add cekura-ai/cekura-skills --skill cekura-create-agent

Clone the repo

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

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-create-agent/github.svg)](https://agentmods.dev/skills/cekura-ai/cekura-skills/cekura-create-agent)

Your own site

<a href="https://agentmods.dev/skills/cekura-ai/cekura-skills/cekura-create-agent"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-create-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cekura-ai/cekura-skills/cekura-create-agent"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-create-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,599 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00197	$0.02599
Opus 5	$0.00098	$0.01300
Sonnet 5	$0.00039	$0.00520
Haiku 4.5	$0.00020	$0.00260

Measured 3d ago against content hash 45c16693c873, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

cekura-create-agent scanned grade C with 2 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/upload-agent.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

| 2 | [phase2-provider.md](phase2-provider.md) | Choose provider; collect all credentials upfront | **✓ required** | **✓ required** | **✓ required** (api_key + agent_id only) |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Use MCP tools, not raw API calls.** The Cekura MCP server is configured and authenticated. Use it directly for all Cekura platform operations — listing projects, creating agents, registering variables, running scenario

cekura/skills/cekura-create-agent/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cekura Create Agent

Full main agent setup flow — pick provider early, it shapes everything that follows.

LiveKit / Pipecat note: keep provider.type = livekit or pipecat regardless of how Cekura connects (phone, WebRTC, chat). Never reroute a LiveKit/Pipecat agent into self_hosted just because it has a phone number — these providers support phone-based simulations and SDK integration natively under their own type.

Standard path (KoreAI, Genesys, Cisco, self-hosted):
Phase 1  → Phase 2  → Phase 3  → Phase 4  → Phase 5  → Phase 6  → Phase 7  → Phase 8  → Phase 9  → Phase 10 → Phase 11
Project    Provider   Basics &   Description  Create     SDK        Mock       KB         Dyn Vars   Advanced   Verify
                      Conn Type               agent     (no-op)     Tools

LiveKit / Pipecat path (Phase 6 wires the Cekura SDK in the user's repo):
Phase 1  → Phase 2  → Phase 3  → Phase 4  → Phase 5  → Phase 6  → Phase 7  → Phase 8  → Phase 9  → Phase 10 → Phase 11
                                                       SDK
                                                       integration

Auto-import path (VAPI / Retell / ElevenLabs / Bland / Synthflow — configure_from_provider: true):
Phase 1  → Phase 2  → Phase 5  → Phase 10 → Phase 11
Project    Provider   Create     Advanced   Verify
           (api_key   (import,   config
           + agent_id) poll
                      progress)

The 11 Phases

Phase	File	What happens	Standard providers	LiveKit / Pipecat	Auto-import (VAPI/Retell/ElevenLabs/Bland/Synthflow)
1	phase1-project.md	List projects, pick `project_id`	✓ required	✓ required	✓ required
2	phase2-provider.md	Choose provider; collect all credentials upfront	✓ required	✓ required	✓ required (api_key + agent_id only)
3	phase3-basics.md	Main agent name, language, connection mode(s) (multi-select for LiveKit/Pipecat)	✓ required	✓ required	skipped — auto-imported
4	phase4-description.md	Collect main agent description — the full system prompt	✓ required	✓ required	skipped — auto-imported
5	phase5-create.md	Create the main agent — POST v2, full provider examples	✓ required	✓ required	✓ required (auto-import path)
6	phase6-sdk-integration.md	SDK integration in the user's repo (LiveKit / Pipecat only)	no-op	✓ required (unless explicitly refused)	no-op
7	phase7-mock-tools.md	Main agent mock tools — auto-fetch (managed provider or self-hosted MCP) or manual	✓ required	✓ required	skipped — auto-imported
8	phase8-knowledge-base.md	Main agent knowledge base — upload KB files	✓ required	✓ required	skipped — auto-imported
9	phase9-dynamic-variables.md	Main agent dynamic variables — register via API	✓ required	✓ required	skipped — auto-imported
10	phase10-advanced.md	Auto-sync, auto-import calls, outbound config	✓ required	✓ required	✓ required
11	phase11-verify.md	Verify main agent setup — checklist + summary + next-skill handoff	✓ required	✓ required	✓ required

Read the full file on GitHub · 132 lines

Files

What ships with it

19 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.

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.

3d ago Changed · +2 lines · +39 tokens per session 45c16693c873
12d ago First seen · 130 lines · 158 tokens per session scan C 1322532e89b9

Subscribe to this mod's changes

cekura-create-agent is a skill published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 197 tokens to every session and 2,599 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Testing

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.

davila7/claude-code-templates · 43 tokens

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".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

cekura-create-agent