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.
npx agentmods add instructions/mrgoonie/claudekit-cli/claude-mdgit clone --depth 1 https://github.com/mrgoonie/claudekit-cliWrote 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/instructions/mrgoonie/claudekit-cli/claude-md)<a href="https://agentmods.dev/instructions/mrgoonie/claudekit-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/mrgoonie/claudekit-cli/claude-md.svg" alt="Measured on agentmods" 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 | $0.04002 | $0.04002 |
| Opus 5 | $0.02001 | $0.02001 |
| Sonnet 5 | $0.00800 | $0.00800 |
| Haiku 4.5 | $0.00400 | $0.00400 |
Grade A, and why
claudekit-cli CLAUDE.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClaudeKit CLI
🎯 Core Mission
This CLI is the front door to ClaudeKit. Every command, prompt, and message serves one purpose: empower users to understand and adopt the CK stack.
The Two Imperatives
-
Educate — Users must understand what ClaudeKit is, what each kit offers, and why it matters to their workflow. No blind installation. Informed adoption.
-
Install — Zero friction from discovery to working setup. Whether Engineer, Marketing, or both — the path must be clear, fast, and successful.
Design Philosophy
- Show, don't tell — Feature previews over marketing copy
- Guide, don't gatekeep — Sensible defaults, optional depth
- Succeed, don't abandon — Every install ends with working config + clear next steps
- Respect time — Fast paths for experts, guided paths for newcomers
The Kits
| Kit | Purpose | Audience |
|---|---|---|
| Engineer | AI-powered coding: skills, hooks, multi-agent workflows | Developers building with Claude |
| Marketing | Content automation: campaigns, social, analytics | Marketers leveraging AI |
Both kits share the ClaudeKit foundation. Users can install one or both.
CLI tool (ck) for bootstrapping/updating ClaudeKit projects from GitHub releases.
🎯 Core Principle
User experience is paramount. The CLI is users' first touchpoint with ClaudeKit. Prioritize clarity over cleverness: intuitive commands, helpful errors, minimal friction from install to daily use.
CRITICAL: Quality Gate
MUST pass before ANY commit/PR. No exceptions.
bun run ci:local
bun run ci:local is the single source of truth for what passing CI means. It runs the exact same 7 steps as the Test job in .github/workflows/ci.yml, in the same order, with the same env vars. If ci:local passes, the CI Test job will pass — modulo network/env quirks.
The pre-push git hook calls into the same script, so hook ↔ CI parity can never silently drift. AI sessions MUST run bun run ci:local before pushing.
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.
- 4d ago First seen · 313 lines · 4,002 tokens per session scan A f34f932e467a
claudekit-cli CLAUDE.md is an instructions file published in the GitHub repository mrgoonie/claudekit-cli (117 stars, last pushed 1mo ago), licensed MIT. It adds 4,002 tokens to every session, about $0.0200 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.