A software development kit for installing an application’s bundled Agent Skill on local coding-agent hosts. It handles host detection, validation, copying, updating, uninstalling, conflict safety, and installation reports.

Use it in a Go CLI that ships an Agent Skill, including commands for installation, dry runs, selecting user or project scope, choosing agents, status checks, and confirmed uninstallation.

It removes the need for each command-line application to implement its own skill installation logic. It also helps prevent conflicts and keeps repeated installations tied to the same application.

kitup — Skill for Claude Code and Codex by lathe-cli

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 lathe-cli/kitup --skill kitup

Clone the repo

git clone --depth 1 https://github.com/lathe-cli/kitup

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lathe-cli/kitup/kitup/github.svg)](https://agentmods.dev/skills/lathe-cli/kitup/kitup)

Your own site

<a href="https://agentmods.dev/skills/lathe-cli/kitup/kitup"><img src="https://agentmods.dev/badge/skills/lathe-cli/kitup/kitup/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lathe-cli/kitup/kitup"><img src="https://agentmods.dev/badge/skills/lathe-cli/kitup/kitup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 451 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.00451
Opus 5.5	$0.00019	$0.00180
Sonnet 5.5	$0.00009	$0.00090
Haiku 4.5	$0.00005	$0.00045

Measured 1mo ago against content hash 0e9ae7b6c91b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kitup 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 1mo 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.

skills/kitup/SKILL.md · 39 lines

What it actually says

Kitup

Use kitup as a producer-side SDK. The embedding CLI owns the bundled skill and command names. kitup owns host resolution, skill validation, copy/update/uninstall behavior, .kitup.json metadata, conflict safety, and structured reports.

Call the SDK with:

appId: stable id for the embedding CLI
skillBundle: bundled skill directory tree source containing SKILL.md
scope: user or project
agents: explicit host ids, auto, or all supported hosts

CLI surface

Recommended user-facing command:

mycli skill install
mycli skill install --dry-run

Standard install flags: --scope, repeatable --agent, --dry-run, --yes / -y, --force.

Do not add plan, update, or upgrade subcommands. --dry-run is the plan. Re-running install updates kitup-owned copies of the same appId. planBundledSkill and updateBundledSkill are that same install path, not extra commands.

Optional status and uninstall commands call statusBundledSkill and uninstallBundledSkill. Uninstall writes immediately; require --yes when stdin is not a TTY, and confirm in TTY mode. There is no uninstall force mode. Only the Go Cobra adapter ships these commands; other languages wire their own shell.

Wiring

For user-facing install, parse flags with parseInstallFlags and call runBundledSkillInstall with promptScope: true. Set stdinTTY from the process terminal. Map exits with installFlagError and installWorkflowError.

For scripts or tests that already know scope and agents, call installBundledSkill directly.

Treat conflicts as stop conditions unless the caller passed explicit --force.

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.

1mo ago First seen · 39 lines · 47 tokens per session scan A 0e9ae7b6c91b

Subscribe to this mod's changes

kitup is a skill published in the GitHub repository lathe-cli/kitup (6 stars, last pushed 8d ago), licensed Apache-2.0. It adds 47 tokens to every session and 451 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents Go Rust agent-skills cli installer sdk

better-fullstack

Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server. Use when a user asks to create, generate, or scaffold a fullstack starter; choose a Better Fullstack stack; add Better Fullstack capabilities; compare agent scaffolding paths; or avoid hand-authoring boilerplate project files.

Marve10s/Better-Fullstack · 71 tokens

scaffold-project

Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack. Use when the user wants to create, start, bootstrap, initialize, or generate a project from a stack description. Prefer the bundled Better Fullstack MCP server: guidance, schema…

Marve10s/Better-Fullstack · 80 tokens

add-to-project

Add capabilities, addons, deployment targets, generated CI, services, or stack updates to an existing Better Fullstack project. Use when the current repo has bts.jsonc or the user asks to extend a generated project. Prefer bfsplanstackupdate and bfsapplystackupdate; use legacy addon tools only for addon/deploy-only…

Marve10s/Better-Fullstack · 71 tokens

pixiv-cli-native

Change or validate pixiv-cli Rust ugoira, cgo/FFI, committed static libraries, vendored dependencies, Linux ABI, and native runner evidence. Use when native sources, library hashes, target toolchains, or encoder behavior change; not for routine Go-only or documentation edits.

FlanChanXwO/pixiv-cli · 64 tokens

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Marve10s/Better-Fullstack · 44 tokens

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…

Marve10s/Better-Fullstack · 77 tokens