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.
git 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/autobuild)<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/autobuild"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/autobuild/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.
<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/autobuild"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/autobuild.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00443 |
| Opus 5.5 | $0.00000 | $0.00177 |
| Sonnet 5.5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
autobuild 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.
What it actually says
/mk:autobuild — Autonomous Product-Build Pipeline
Usage
/mk:autobuild [product description]
/mk:autobuild --resume [run-id]
/mk:autobuild --tier [MINIMAL|FULL|LEAN]
/mk:autobuild --budget [amount-usd]
/mk:autobuild --max-iter [N]
Behavior
Runs mk:autobuild skill — the autonomous generator/evaluator build pipeline for green-field products. Preferred over /mk:cook for product-level builds ("build me a kanban app").
Adaptive scaffolding density per model tier:
- MINIMAL (Haiku) — short-circuits to
/mk:cook - FULL (Sonnet, Opus 4.5) — contract + 1–3 iterations + context resets
- LEAN (Opus 4.6+) — single-session, contract optional
Execution Steps
- Tier detection — detect model, select density
- Plan — product-level spec via
mk:plan-creator --product-level - Contract — negotiate sprint contract (FULL density) or skip (LEAN/MINIMAL)
- Generate — developer builds per contract/spec
- Evaluate — evaluator grades running build against rubric criteria
- Iterate or ship — loop (max 3 rounds) or ship if passing
- Run report — final report with metrics
Flags
| Flag | Behavior |
|---|---|
--resume |
Resume a previous autobuild run from last checkpoint |
--tier |
Override auto-detected density (MINIMAL/FULL/LEAN) |
--budget |
Set session budget cap in USD (overrides $100 default) |
--max-iter |
Override iteration cap (default: 3) |
Output
- Product build with passing evaluator verdict
- Run report at
tasks/autobuild-runs/ - Budget tracking in
session-state/budget-state.json
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 · 46 lines · 0 tokens per session scan A c5fd1abec9bb
autobuild is a command published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 443 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 2026-08-30.
Other commands, from other repositories
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
review
Submit a story for verification (In Progress → In Review, no PR yet).
standup
Alias of /board — the async sprint snapshot.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.