cekura-skills: Instructions file for Claude Code

CLAUDE.md

cekura-skills CLAUDE.md is an instructions file for Claude Code from cekura-ai/cekura-skills. It costs 5,655 tokens per session, scanned A, original, MIT.

Developer instructions and project notes for Cekura Skills, a package that adds Cekura voice-agent testing knowledge to several coding assistants.

In plain words
What is it for?
Maintaining the Cekura Skills repository, its assistant integrations, and the skills that explain Cekura's voice-agent testing platform.
Why use it?
They give contributors one shared source of truth for the package structure, installation methods, content rules, and update process.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is cekura-ai/cekura-skills's own configuration. It tells Claude Code 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 →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

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

Made for: Claude Code.

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 CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cekura-ai/cekura-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/cekura-ai/cekura-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,655 This file is loaded in full into every session.
When invoked 5,655 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.05655 $0.05655
Opus 5 $0.02828 $0.02828
Sonnet 5 $0.01131 $0.01131
Haiku 4.5 $0.00566 $0.00566

Measured yesterday against content hash 9e88583371cd, 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 CLAUDE.md scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

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

- Body is **public-facing**: no internal endpoints (e.g., `localhost:8001`), no MCP-bug curl workarounds, no `cekura-internal:*` skill references, no customer-specific facts. `mcp__cekura__*` tool references are allowed
CLAUDE.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cekura Skills — Developer Guide

Repository Structure

This is a Claude Code marketplace that doubles as an Agent Skills package — a single plugin that encodes domain expertise for the Cekura voice AI testing and evaluation platform.

cekura-skills/
  .claude-plugin/
    marketplace.json             # Claude Code marketplace registry (source: "./cekura")
  .cursor-plugin/
    marketplace.json             # Cursor marketplace registry (source: "./cekura")
  .agents/plugins/
    marketplace.json             # Codex/generic registry (git-subdir → ./cekura)
  .github/plugin/
    marketplace.json             # GitHub Copilot CLI registry (source: "./cekura")
  gemini-extension.json          # Gemini CLI extension manifest (inline MCP + GEMINI.md)
  GEMINI.md                      # Gemini context file — kept identical to codex/AGENTS.md
  cekura/                        # The plugin lives here (the manifests above point to this dir)
    .claude-plugin/
      plugin.json                # Claude plugin manifest
    .codex-plugin/
      plugin.json                # Codex plugin manifest (skills: ./skills/, mcpServers: ./.mcp.json)
    .cursor-plugin/
      plugin.json                # Cursor plugin manifest (inlines mcpServers with the hosted MCP URL)
    .github/plugin/
      plugin.json                # GitHub Copilot plugin manifest (Open Plugin Spec; skills + mcpServers paths)
    .mcp.json                    # MCP auto-config shared by Claude Code and Codex (camelCase mcpServers)
    skills/                      # Single source of truth for skills
      cekura-coordinator/
      cekura-onboarding/
      cekura-create-agent/
      cekura-self-improving-agent/
      cekura-metric-design/
      cekura-metric-improvement/
      cekura-predefined-metrics/
      cekura-eval-design/
      cekura-personality-design/
      cekura-infra-test-suite/
      cekura-bot-test-writer/
      cekura-flag-call-log-failures/
      cekura-generate-scenarios/
    commands/                    # Slash commands (Claude Code only)
    hooks/                       # MCP failure detection + session-start auto-update (Claude Code CLI only)
  _template/                     # SKILL.md.tmpl scaffold for new skills (dev-only)
  codex/
    AGENTS.md                    # Single-file behavior preset for Codex/Cursor/other agents
  package.json                   # npm package metadata (used by Agent Skills validators)
  README.md                      # User-facing installation and platform setup guide
  CLAUDE.md                      # This file — developer context for contributors

Read the full file on GitHub · 262 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. yesterday Changed · +2 lines · +41 tokens per session 9e88583371cd
  2. 2d ago Changed · +2 lines · +37 tokens per session 121b4ed52e01
  3. 3d ago Changed · -7 lines · -74 tokens per session f8dcb17f6473
  4. 8d ago Changed · -14 tokens per session f0c7652dddba
  5. 12d ago First seen · 265 lines · 5,665 tokens per session scan A ac3fee55c6b8

Subscribe to this mod's changes

cekura-skills CLAUDE.md is an instructions file published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 5,655 tokens to every session, about $0.0283 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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