kbagent -- Keboola Agent CLI Agent Skill

Use when working with Keboola Connection projects via the kbagent CLI.

Context cost
248.6k tokensestimated from the bundle; more than a 200k window holds
Bundle
37 files · 994.5 kBtext throughout, nothing executable
Licence
Apache-2.0the author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Use for Keboola projects via the kbagent CLI. Covers: searching configurations, job history, data lineage, dev branches, merge requests, workspace SQL debugging, GitOps sync, bucket sharing/linking, encrypting secrets, Storage tables/files/snapshots, large (200 GB) file uploads, data apps, flows/schedules, invitations, feature flags, OTLP data streams, scoped Storage tokens, semantic layer, Developer Portal, first-time setup and logout.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

agentcloud
Filed under

Cloud & DevOps

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md58.0 kB · preview
--- name: kbagent ---
26# kbagent -- Keboola Agent CLI
27
28## How to use this skill
29
30This skill contains everything you need. The decision table below maps goals to commands.
31For detailed workflows, see the references/ docs linked at the bottom.
32
33For **command flags and parameters**, use kbagent <command> --help (e.g. kbagent config new --help).
34
35If kbagent is not installed or you need the full standalone reference, run kbagent context.
36
37## Rules
38
391. **Always use --json**: kbagent --json <command> for parseable output
402. **Set conversation ID**: pass --conversation-id "<unique-id>" (e.g. session UUID) on every kbagent call -- kbagent --json --conversation-id <id> <command>. All API requests include it as the X-Conversation-ID header for platform observability. **Do not use a standalone export**: agent harnesses (Claude Code included) do not persist shell state between tool calls, so the variable is gone by the next command -- and prefixing each command with export ... stops it matching a Bash(kbagent ...) permission allow-rule. For a whole session, set KBAGENT_CONVERSATION_ID in the harness's own env block (Claude Code: settings.json -> env) instead.
413. **Multi-project by default**: read commands query ALL connected projects in parallel -- no need to loop
424. **Write commands need --project**: specify the target project alias
435. **Tokens are always masked** in output -- this is expected, not an error
446. **Always fetch fresh before write**: configs change between commands and across users. Re-fetch from the API immediately before any update; never reuse a config dump from earlier in the session. Stale local files are how vN+1 silently overwrites someone else's vN changes.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md8,357 words
Files37
LicenceApache-2.0
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈270
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
248,355
on trigger
The instruction body and 36 supporting files, read only when the skill fires.
1.2×
a 200k window
It does not fit in the window: loaded whole, it would need more room than the model has.
050k100k150k200k context window

248.6k tokens, estimated from the bundle at four bytes to the token — more than the whole window, so it cannot all be held at once: the model reads SKILL.md when the skill fires and the other files only as the instructions call for them. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

37 files, 994.5 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md58.0 kB
  • references/agent-tasks-cli-workflow.md8.8 kB
  • references/agent-tasks-rest-workflow.md8.6 kB
  • references/auth-workflow.md24.3 kB
  • references/billing-workflow.md7.0 kB
  • references/branch-workflow.md3.7 kB
  • references/commands-reference.md173.3 kB
  • references/config-metadata-workflow.md7.7 kB
  • references/config-state-workflow.md10.2 kB
  • references/data-app-workflow.md25.5 kB
  • references/dev-portal-workflow.md5.1 kB
  • references/encrypt-workflow.md4.5 kB
  • references/flow-workflow.md7.8 kB
  • references/gotchas.md395.4 kB
  • references/kai-workflow.md2.5 kB
  • references/library-workflow.md9.3 kB
  • references/lineage-deep-workflow.md6.0 kB
  • references/member-workflow.md6.2 kB
  • references/permissions-workflow.md10.1 kB
  • references/reading-synced-data.md7.5 kB
  • references/safe-write-workflow.md9.7 kB
  • references/scaffold-workflow.md5.9 kB
  • references/schedule-workflow.md10.7 kB
  • references/semantic-layer-workflow.md23.7 kB
  • references/sharing-workflow.md3.2 kB
  • references/snapshot-workflow.md4.1 kB
  • references/sql-migration-workflow.md7.6 kB
  • references/storage-describe-workflow.md15.7 kB
  • references/storage-files-workflow.md7.5 kB
  • references/storage-types-workflow.md18.3 kB
  • references/stream-workflow.md4.7 kB
  • references/sync-rows-workflow.md11.7 kB
  • references/sync-workflow.md40.3 kB
  • references/transformation-workflow.md3.3 kB
  • references/typify-table-workflow.md21.5 kB
  • references/variables-workflow.md10.2 kB
  • references/workspace-workflow.md14.9 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 37 files you can review in full before installing. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# kbagent -- Keboola Agent CLI · 248.6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/kbagent-keboola-agent-cli/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/kbagent-keboola-agent-cli" ] && { [ ! -e .claude/skills/kbagent-keboola-agent-cli ] || { mv .claude/skills/kbagent-keboola-agent-cli "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/kbagent-keboola-agent-cli" .claude/skills/ && echo "Installed .claude/skills/kbagent-keboola-agent-cli"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add padak/kbagent-keboola-agent-cli

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/kbagent-keboola-agent-cli/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/kbagent-keboola-agent-cli/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/kbagent-keboola-agent-cli" ] && { [ ! -e ~/.claude/skills/kbagent-keboola-agent-cli ] || { mv ~/.claude/skills/kbagent-keboola-agent-cli "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/kbagent-keboola-agent-cli" ~/.claude/skills/ && echo "Installed ~/.claude/skills/kbagent-keboola-agent-cli" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/kbagent-keboola-agent-cli/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as kbagent in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, kbagent-keboola-agent-cli.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencepadak/kbagent-keboola-agent-cli

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

PA
padak

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill