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 skills/ngocsangyem/meowkit/bootstrapnpx skills add ngocsangyem/MeowKit --skill bootstrapgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/skills/ngocsangyem/meowkit/bootstrap)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/bootstrap"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/bootstrap.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 5.1 | $0.00096 | $0.00918 |
| Opus 5 | $0.00048 | $0.00459 |
| Sonnet 5 | $0.00019 | $0.00184 |
| Haiku 4.5 | $0.00010 | $0.00092 |
Grade A, and why
mk:bootstrap 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap
End-to-end project orchestrator: research → design → plan → scaffold → implement → docs.
CLI boundary: the installer = project infrastructure. mk:bootstrap = application code + full pipeline. Zero overlap. Never touch .claude/.
When to Use
Explicit only — never auto-activate.
mk:bootstrap [requirements]
mk:bootstrap [requirements] --full
mk:bootstrap [requirements] --fast
mk:bootstrap [requirements] --parallel
Do NOT invoke when: project already has source code, or you only need kit setup (use CLI).
Modes
| Mode | Flag | Gates | Research | Design | Plan flag | Cook flag |
|---|---|---|---|---|---|---|
| Auto | (default) | Design only | Parallel researchers | UI/UX if frontend | --auto |
--auto |
| Full | --full |
Every step | Parallel researchers | UI/UX if frontend | --hard |
(interactive) |
| Fast | --fast |
None | 6 parallel batch | Skip | --fast |
--auto |
| Parallel | --parallel |
Design only | Parallel researchers | UI/UX if frontend | --parallel |
--parallel |
Routing
Parse first flag from arguments:
--full→ loadreferences/workflow-full.md--fast→ loadreferences/workflow-fast.md--parallel→ loadreferences/workflow-parallel.md- default → load
references/workflow-auto.md
Each workflow file defines the exact steps for that mode. After plan + scaffold, all modes load references/shared-phases.md for implementation → docs → final report.
Planning BEFORE Scaffolding
Plan first, scaffold second. The plan tells us WHAT to scaffold.
- Plan — invoke mk:plan-creator with mode-matched flag. Plan defines: architecture, modules, file structure, acceptance criteria.
- Scaffold — generate files following the plan's architecture +
references/scaffolding-principles.md. Detect stack viascripts/detect-stack.sh. Validate withscripts/validate-bootstrap.sh.
Optional: invoke mk:plan-ceo-review on the plan (Full mode).
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- config.example.json 285 B
- references/gotchas.md 1.5 KB
- references/scaffolding-principles.md 2.7 KB
- references/shared-phases.md 1.6 KB
- references/workflow-auto.md 2.7 KB
- references/workflow-fast.md 2.1 KB
- references/workflow-full.md 3.3 KB
- references/workflow-parallel.md 2.5 KB
- scripts/detect-stack.sh 7.7 KB runs code
- scripts/validate-bootstrap.sh 1.1 KB runs code
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.
- 2d ago First seen · 100 lines · 96 tokens per session scan A 08ec54b3e871
mk:bootstrap is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 918 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
Create Matter Workspace
Use when starting a new legal matter that will span multiple skills, documents, or deadlines, to select the right matter-workspace template, gather core matter information, and produce a populated workspace draft for attorney review.
project-init
Initialize new projects using this template. Triggers: init, new, 新專案, 初始化, create project, 建立專案, bootstrap, scaffold project, setup, 設定, 起始, start, 從頭, from scratch, template, 模板, 範本, clone, fork.
project-kickstart
Scaffold any project in seconds. Generate boilerplate for Next.js, React, Python CLI, Express, FastAPI, static sites, and more. Pre-configured with git, linting, CI, README, and license. Use when the user starts a new project. Triggers on: "new project", "start a project", "scaffold", "create a new app", "init…
repo-bootstrap
Scaffold new repositories with best practices, folder structure, CI/CD, linting, and documentation. Use when someone asks to "set up a new repo", "bootstrap a project", "scaffold an app", "create a new project from scratch", or needs a production-ready starting point for any tech stack.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
golden-rss
Use when testing the rss golden build.