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 commands/ngocsangyem/meowkit/meowgit 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/commands/ngocsangyem/meowkit/meow)<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/meow"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/meow.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 | $0.00000 | $0.00693 |
| Opus 5 | $0.00000 | $0.00347 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
meow 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 yesterday.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/meow — Command Entry Point and Router
Usage
/meow [task description]
Behavior
This is the "friendly front door" to the toolkit. Users who don't know which command to use start here.
Execution Steps
-
Load context. Read the relevant topic files in
.meowkit/memory/on demand based on the task at hand —.jsonstore first,.mdfallback if the.jsonis absent (see.claude/rules/memory-read-rules.md):fixes.jsonfor bug-class lessons,review-patterns.jsonfor review/architecture patterns,architecture-decisions.jsonfor past decisions. -
Classify task complexity. Analyze the task description and assign one of three tiers:
- Trivial — single-file change, typo, simple config update, quick question. Route to
/mk:fix(simple mode) or answer directly. - Standard — feature work, bug fix requiring investigation, test writing. Route to
/mk:cook(full pipeline) or specific command (/mk:fix,/mk:testing,/mk:review). - Complex — multi-service change, architectural decision, new system design. Route to
/mk:plan-creatorfirst, then/mk:cook, or/mk:arch//mk:designfor design-only work.
- Trivial — single-file change, typo, simple config update, quick question. Route to
-
Print routing decision:
🐱 Task complexity: [trivial|standard|complex] → routing to [/mk:command] -
Route to the appropriate agent/command. Execute the selected command with the user's task description passed through.
-
If the task is ambiguous or could be interpreted multiple ways, ask a clarifying question before routing. Do not guess — the cost of routing wrong is wasted work.
Classification Heuristics
| Signal | Points toward |
|---|---|
| "fix", "typo", "rename", "update" + single noun | Trivial |
| "add feature", "implement", "build" | Standard |
| "redesign", "migrate", "refactor [system]", "new service" | Complex |
| Mention of multiple services/platforms | Complex |
| Error message pasted directly | Standard (route to /mk:fix) |
| Question about architecture | Complex (route to /mk:arch or /mk:design) |
| "review", "audit", "security" | Route to /mk:review or /mk:audit directly |
| "docs", "document" | Route to /docs:init or /docs:sync |
| "break down spec", "decompose spec", "spec to stories", "breakdown {source}", "stories from spec" | Route to /mk:breakdown |
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.
- yesterday First seen · 57 lines · 0 tokens per session scan A 63b66e468093
meow 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 693 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.
Other commands, from other repositories
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.
claude-recall
Update project context using the local LLM (Qwen2.5 0.5B).
review
Submit a story for verification (In Progress → In Review, no PR yet).