A command that checks a project for structural, naming, configuration, and security problems using fixed rules. Its checks run locally without an AI model.

Use it to find missing files, naming violations, configuration problems, and security anti-patterns, with reported file paths, line numbers, and severity.

It provides repeatable results, so the same project state produces the same findings. This makes it easier to catch common issues and verify changes quickly.

upgrade — Command for Claude Code by ngocsangyem

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.

Clone the repo

git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

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/commands/ngocsangyem/meowkit/upgrade/github.svg)](https://agentmods.dev/commands/ngocsangyem/meowkit/upgrade)

Your own site

<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/upgrade"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/upgrade/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/commands/ngocsangyem/meowkit/upgrade"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 519 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	$0.00000	$0.00519
Opus 5	$0.00000	$0.00260
Sonnet 5	$0.00000	$0.00104
Haiku 4.5	$0.00000	$0.00052

Measured 8d ago against content hash edb4a0e7ff85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

upgrade 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 8d 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.

.claude/commands/mk/upgrade.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/upgrade — Self-Update Toolkit

Usage

/upgrade
/upgrade --check
/upgrade --beta

Behavior

Self-update the installed toolkit to the latest version. Preserves learned knowledge in .meowkit/memory/.

Execution Steps

Check current version. Read the workflow config for the current installed version.
Fetch latest version. Query npm registry for the latest published toolkit version.
Compare versions. If current version matches latest:
- Print: "Toolkit is up to date (vX.Y.Z)"
- Exit.
If update is available:
- Print: "Update available: vX.Y.Z → vA.B.C"
- Download the new version.
- Replace .claude/ files with updated versions: commands, modes, rules, skills, scripts, agents, hooks.
- NEVER overwrite .meowkit/memory/. Topic files, cost logs, and learned patterns are preserved across updates.
- Update version in the workflow config.
Post-update validation. Run /validate to confirm the update installed correctly and all scripts are functional.

Flags

Flag	Behavior
`--check`	Check for updates only. Print whether an update is available without installing.
`--beta`	Install the latest beta version instead of stable. Use for early access to new features.

Safety

The .meowkit/memory/ directory is NEVER overwritten. This ensures:
- The canonical JSON stores (fixes.json, review-patterns.json, architecture-decisions.json) persist — these are the authoritative curated memory (see .claude/rules/memory-read-rules.md)
- The matching .md files (fixes.md, review-patterns.md, architecture-decisions.md, security-notes.md) also persist — these are generated/non-authoritative views; they can be regenerated via mewkit memory render-views from the JSON stores
- .meowkit/telemetry/cost-log.json (cost history) persists
- Any other accumulated knowledge is preserved
If the update fails mid-way, the previous version's files remain intact.
After update, /validate confirms everything works.

Read the full file on GitHub · 56 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.

8d ago First seen · 56 lines · 0 tokens per session scan A edb4a0e7ff85

Subscribe to this mod's changes

upgrade is a command published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 519 tokens. 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.

Claude Code Debugging Security ai ai-agents automation claude claude-skills

techdebt

Find and report technical debt in the codebase.

oliver-kriska/claude-elixir-phoenix · 13 tokens

ux-audit

Walk a live web app AS a real user — interaction-first methodology. Hard gates (console / network / layout-collapse), Persona Lock, Interaction Manifest enforcement, multi-pane stress, visual polish, perfection checklist, 11 scenarios (judgement-density-ordered), Top 5 + self-critique pass + smallest-possible-patch +…

jezweb/claude-skills · 101 tokens

upgrade