cekura-skills: Instructions file for Gemini CLI

GEMINI.md

cekura-skills GEMINI.md is an instructions file for Gemini CLI from cekura-ai/cekura-skills. It costs 9,158 tokens per session, scanned A, original, MIT.

Guidance for using Cekura, a platform for testing and scoring AI voice agents. It explains simulated callers, post-call transcript scoring, test data, personalities, and basic API use.

In plain words
What is it for?
Creating test scenarios and scoring rules, setting caller details, analyzing results, and making authenticated requests to the Cekura API.
Why use it?
It helps an assistant distinguish between running a simulated test and evaluating the resulting conversation, avoiding confusion when creating tests or metrics.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is cekura-ai/cekura-skills's own configuration. It tells Gemini CLI how to work on cekura-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cekura-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cekura-ai/cekura-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cekura-ai/cekura-skills/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/cekura-ai/cekura-skills

Made for: Gemini CLI.

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 cekura-skills GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cekura-ai/cekura-skills/gemini-md/github.svg)](https://agentmods.dev/instructions/cekura-ai/cekura-skills/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/cekura-ai/cekura-skills/gemini-md"><img src="https://agentmods.dev/badge/instructions/cekura-ai/cekura-skills/gemini-md/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 cekura-skills GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cekura-ai/cekura-skills/gemini-md"><img src="https://agentmods.dev/badge/instructions/cekura-ai/cekura-skills/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,158 This file is loaded in full into every session.
When invoked 9,158 The same file — it is already loaded in full.
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 $0.09158 $0.09158
Opus 5 $0.04579 $0.04579
Sonnet 5 $0.01832 $0.01832
Haiku 4.5 $0.00916 $0.00916

Measured 2d ago against content hash 82b50769e422, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cekura-skills GEMINI.md 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 2d 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.

GEMINI.md · 606 lines

How it starts

The opening of the file, as written. The whole thing — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cekura Platform — Agent Guidelines

You are an expert at working with the Cekura platform for AI voice agent testing and evaluation. Follow these guidelines when helping users create metrics, evaluators, test profiles, or analyze results.

Core Concepts

  • Main agent: The client's AI voice agent being tested
  • Testing agent: Cekura's simulated caller that exercises the main agent
  • Metric: A post-call evaluation that scores a transcript against defined criteria
  • Evaluator/Scenario: A test case defining what the simulated caller does and what success looks like
  • Test Profile: Identity and context data passed to the testing agent (and the main agent in chat/websocket/outbound runs)
  • Personality: The simulated caller's voice layer — voice (which is what sets its accent), language, speed, interruption and idle timing, background noise, volume, network conditions, plus a persona prompt. Reused across evaluators. accent is a read-only label derived from the voice, not a setting

Source-Controlled CI/CD Test Suites

For a repository-owned Cekura Tests-as-Code suite, inspect the real runtime path before authoring coverage. Record each behavior's source evidence, seat (simulated caller vs agent under test), transport, transcript-observable assertion, and stable spec key. A test that covers only one seat does not cover a different pipeline assembly on the other.

Keep the spec self-contained where possible: test_profile.agent_variables configure the agent under test and caller_variables configure the simulated caller. Preserve both blobs exactly when they come from working configuration. Do not create persistent scenarios, profiles, metrics, or personalities for a source-controlled suite; use only run_scenarios_json?dry_run=true until the user explicitly authorizes live calls.

Use deterministic conditional actions for CI regression checks: every condition on both seats has fixed_message: true; conditional-actions cases set language; and outcomes assert only transcript observable behavior. Do not assert unobservable audio effects such as volume, speed, ambience, or spelling. Keep terminal end-call/max-duration assertions last, preserve strict assertions, and mark unsupported transport or fixture-dependent behavior explicitly uncovered rather than pretending it is tested.

Read the full file on GitHub · 606 lines

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. 2d ago Changed · +5 lines · +153 tokens per session 82b50769e422
  2. 3d ago Changed · +2 lines · +161 tokens per session ffc1c379b8ce
  3. 8d ago Changed · +20 lines · +255 tokens per session f7698a7eded3
  4. 12d ago First seen · 579 lines · 8,589 tokens per session scan A 43350cebbbb6

Subscribe to this mod's changes

cekura-skills GEMINI.md is an instructions file published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 9,158 tokens to every session, about $0.0458 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens