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/setup-mcp)<a href="https://agentmods.dev/commands/cekura-ai/cekura-skills/setup-mcp"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/setup-mcp/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/setup-mcp"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/setup-mcp.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 | $0.00016 | $0.01473 |
| Opus 5 | $0.00008 | $0.00737 |
| Sonnet 5 | $0.00003 | $0.00295 |
| Haiku 4.5 | $0.00002 | $0.00147 |
Grade B, and why
setup-mcp scanned grade B 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
If yes, merge the opt-in into `~/.claude/settings.json` (idempotent — preserves all other settings): Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- For both paths: verify connectivity to the public API with `curl -I https://api.cekura.ai/mcp` (should return a 2xx or 4xx — a connection error means a network issue). How it starts
The opening of the file, as written. The whole thing — 140 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="setup-mcp". 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.
Set Up Cekura MCP Server
Configure access to the Cekura MCP server at https://api.cekura.ai/mcp so the plugin can call Cekura API operations as MCP tools.
Process
1. Check if MCP is already working
Try calling mcp__cekura__test_simple_tool or mcp__cekura__list_available_tools. If either returns successfully, MCP is already configured — tell the user the version that's responding, and skip to step 4.
If both fail with a tools-not-available error, MCP isn't set up yet. Continue to step 2.
2. Choose the auth path
Ask the user:
"Do you want to use OAuth (recommended — one-click browser sign-in, no keys to manage) or an API key (only if you need a project-scoped credential or shared CI access)?"
3a. OAuth path (recommended)
Run:
claude mcp add --transport http cekura --scope user https://api.cekura.ai/mcp
Tell the user: "Claude Code will open a browser window. Sign into your Cekura account at https://dashboard.cekura.ai and click Authorize. The session token is managed by Claude Code automatically — no env vars or config files."
Then verify the server registered:
claude mcp list
The cekura entry should appear with status connected.
3b. API key path (alternative)
This is for users who need a project-scoped credential or want to share access via a key.
Ask: "What's your Cekura API key? Find it at https://dashboard.cekura.ai → Settings → API Keys."
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.
- 12d ago First seen · 140 lines · 16 tokens per session scan B a9b2ec301b12
setup-mcp is a command published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 1,473 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.