kaneo-cli

kaneo-cli is a skill for Claude Code, Codex from usekaneo/kaneo. It costs 73 tokens per session (1,315 once invoked), scanned C, original, MIT.

A command-line interface for managing Kaneo tasks, projects, comments, and time records. Kaneo is a task-management service that can be hosted by its provider or run on your own server.

In plain words
What is it for?
Use it to list, create, update, assign, or close tasks; add comments; record time; and automate work in a Kaneo workspace.
Why use it?
It lets scripts and coding agents work with project data without relying on interactive terminal prompts, while checking the current account and workspace first.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to list, create, update, assign, or close tasks; add comments; record time; and automate work in a Kaneo workspace.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/usekaneo/kaneo/kaneo-cli
About the project

Kaneo is an open-source project-management application for organizing work with kanban boards, issues, and issue tracking. Teams use it to manage projects, and its self-hosted design lets them keep the application and data under their control. The catalogue contains skills, rules, instructions, and an MCP integration for working with Kaneo.

usekaneo/kaneo · 9,492 stars · on GitHub · kaneo.app

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 usekaneo/kaneo --skill kaneo-cli
Clone the repo
git clone --depth 1 https://github.com/usekaneo/kaneo

Made for: Claude Code, Codex.

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 kaneo-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/usekaneo/kaneo/kaneo-cli/github.svg)](https://agentmods.dev/skills/usekaneo/kaneo/kaneo-cli)
Your own site
<a href="https://agentmods.dev/skills/usekaneo/kaneo/kaneo-cli"><img src="https://agentmods.dev/badge/skills/usekaneo/kaneo/kaneo-cli/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 kaneo-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/usekaneo/kaneo/kaneo-cli"><img src="https://agentmods.dev/badge/skills/usekaneo/kaneo/kaneo-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,315 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.01315
Opus 5.5 $0.00029 $0.00526
Sonnet 5.5 $0.00015 $0.00263
Haiku 4.5 $0.00007 $0.00131

Measured 5d ago against content hash 22fe030d4c19, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

kaneo-cli 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 5d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- `kaneo: command not found`: ask the user to install it in their own terminal, where they can read the script first: `curl -fsSL https://kaneo.app/cli/install.sh | sh` (Windows: `irm https://kaneo.app/cli/install.ps1 |

Makes network callslowCapability

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

- `kaneo: command not found`: ask the user to install it in their own terminal, where they can read the script first: `curl -fsSL https://kaneo.app/cli/install.sh | sh` (Windows: `irm https://kaneo.app/cli/install.ps1 |
skills/kaneo-cli/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kaneo CLI

kaneo is the official command line for Kaneo. Run from an agent, stdout is not a terminal, so every command answers in JSON and never prompts.

Check the setup first

Run kaneo context. It prints the server, user, workspace and project in use, and where each value came from.

  • kaneo: command not found: ask the user to install it in their own terminal, where they can read the script first: curl -fsSL https://kaneo.app/cli/install.sh | sh (Windows: irm https://kaneo.app/cli/install.ps1 | iex), brew install usekaneo/tap/kaneo with Homebrew, or npm install -g @kaneo/cli with Node.js 20 or newer. The script's binary lands in ~/.local/bin/kaneo (Windows: %LOCALAPPDATA%\Programs\kaneo\kaneo.exe). Your shell may not have that folder on its PATH yet, so call it by that full path until it does.
  • No user: kaneo login is a browser approval only a person can finish. Ask the user to run it in their own terminal. Headless and CI runs use an API key in KANEO_API_KEY instead (created in Kaneo under Settings, Account, API Keys).
  • No workspace: list them with kaneo workspace list --jq '.[] | "\(.id) \(.name)"' and pass -w <id>, or ask the user to pick a default with kaneo workspace use.
  • Server or compatibility errors: kaneo doctor explains what is wrong.

You are ready when kaneo context shows a user and the workspace you mean to act in.

Output contract

  • Success prints exactly one JSON value on stdout and exits 0.
  • Failure prints {"error": "message"} on stdout and exits 1. The message names what went wrong, such as a missing project, so fix that and retry. A message saying something needs confirmation means rerunning with --yes once the user has agreed.
  • --jq '<expr>' filters the JSON with a built-in jq. Strings print raw, one result per line. Reach for it to keep large results small.
  • Writes print JSON describing the change: task create returns the new task (--jq .ticketId gives its ticket id), and task status returns the from and to columns. Run kaneo task view to see the full task afterwards.
  • task list stops at 50 tasks. Pass --all when you need every match, for example to count.
  • task mine returns at most 100 tasks per workspace, soonest due first, and cannot page further. For a complete list, run kaneo task list -p <KEY> --mine --all for each project.

Read the full file on GitHub · 62 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. 5d ago Changed 22fe030d4c19
  2. 6d ago First seen · 62 lines · 73 tokens per session scan C 4e2614262737

Subscribe to this mod's changes

kaneo-cli is a skill published in the GitHub repository usekaneo/kaneo (9,492 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,315 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.

Related

Other skills, from other repositories

kaneo

An open-source project-management platform that combines kanban boards, issues, projects, and labels. It can be self-hosted with Docker Compose, Coolify, or a Helm chart, and its TypeScript code is kept in one repository.

AvalonLee/AstraCraft-Program · 0 tokens

dootask

An open-source task and project management system built with PHP and Vue. It combines tasks, boards, team chat, files, workflows, and online diagram editing in a self-hosted installation, meaning your team runs the service itself.

AvalonLee/AstraCraft-Program · 0 tokens

stacking-prs

Create and manage GitHub native Stacked PRs in this repo with the gh stack CLI. Use when asked to stack PRs, split a large change into a stack, add a layer to a stack, restack or rebase a stack, adopt existing branches or PRs into a stack, check out someone else's stack, or land a stack. Covers creating and submitting…

PostHog/posthog · 136 tokens

auditing-endpoints

Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints…

PostHog/posthog · 96 tokens

setting-up-support-slack-locally

Connect a real Slack workspace to local PostHog Conversations (the SupportHog Slack app) so Slack messages become support tickets and replies post back. Use when the user wants to test the conversations Slack integration locally, hits "Support Slack OAuth client ID is not configured", gets a white screen or "Network…

PostHog/posthog · 132 tokens

managing-endpoint-versions

Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query history, deactivate a specific version. Use when the user asks "how do I roll back my endpoint", "preview my changes before publishing", "I want to fix v5 without…

PostHog/posthog · 111 tokens