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 skills add ngocsangyem/MeowKit --skill autobuildgit 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/autobuild)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/autobuild"><img src="https://agentmods.dev/badge/skills/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/skills/ngocsangyem/meowkit/autobuild"><img src="https://agentmods.dev/badge/skills/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 | $0.00102 | $0.02351 |
| Opus 5.5 | $0.00041 | $0.00940 |
| Sonnet 5.5 | $0.00020 | $0.00470 |
| Haiku 4.5 | $0.00010 | $0.00235 |
Grade A, and why
mk: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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mk:autobuild — Autonomous Multi-Hour Build Orchestration
Step-file workflow that runs the complete generator/evaluator harness pipeline as an autonomous build. Handles green-field product builds (planner stage → contract stage → evaluator loop → ship decision) with adaptive scaffolding density based on detected model tier.
When to Use
Activate when:
- User runs
/mk:autobuild "build a X"(or any green-field product description) - Existing kit detection routes a green-field "build me an app" intent here instead of
mk:cook - A multi-hour autonomous build is requested with no manual handholding
Skip when:
- The task is a single feature, bug fix, or refactor → use
/mk:cookinstead - The task is a doc update → use the existing doc skills
- The request is "explain X" or "review Y" → use the appropriate single-shot skill
Hard Constraints
- Adaptive density — picks scaffolding density via
mk:scale-routing(ordensity-select.sh); honorsMEOWKIT_AUTOBUILD_MODEenv override - Budget caps — warns at $30 spent, requires explicit approval at $100, hard-blocks at user-set
--budgetvalue - 6-hour wall-clock timeout — hard limit per Anthropic's observed runs ; checkpoints every step for resumability
- Max 3 iteration rounds between generator and evaluator before escalating to human (configurable via
--max-iter) - Run report mandatory — every autobuild run produces
tasks/autobuild-runs/YYMMDD-{slug}/run.mdwith full audit trail - Coexists with
mk:cook— does not replace it; both route through Gate 1 + Gate 2 - TDD opt-in (parallel to cook): autobuild respects
--tddlike other flows. Default: no RED-phase gate. With--tdd: writes the.claude/session-state/tdd-modesentinel and the developer waits on tester before each generator iteration. Active-verification HARD GATE (Rule 8 ofharness-rules.md) is independent of TDD mode and always applies.
What ships with it
13 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.
- references/adaptive-density-matrix.md 6.4 KB
- references/advice-checkpoints.md 5.8 KB
- references/agent-teams-vs-subagents.md 5.6 KB
- scripts/budget-tracker.sh 3.2 KB runs code
- scripts/density-select.sh 3.1 KB runs code
- step-00-tier-detection.md 3.3 KB
- step-01-plan.md 2.4 KB
- step-02-contract.md 3.7 KB
- step-03-generate.md 5.4 KB
- step-04-evaluate.md 5.1 KB
- step-05-iterate-or-ship.md 11 KB
- step-06-run-report.md 5.4 KB
- workflow.md 6.5 KB
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 · 197 lines · 102 tokens per session scan A 3e240f713a46
mk:autobuild is a skill published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 2,351 once invoked, about $0.0004 per session on Opus 5.5. 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
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…
customer-journey-map
Construye un mapa de recorrido del cliente para un producto, servicio o experiencia. Úsalo cuando se te pida mapear un recorrido del cliente, crear un viaje del usuario, documentar puntos de contacto y puntos de fricción, o diseñar un mapa de experiencia. Produce un mapa de recorrido completo con etapas, puntos de…
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…
design-handoff-brief
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context…
outcome-tracker
Record the testable predictions inside a decision, then score them against reality later — so frameworks earn trust from outcomes, not vibes. Use when committing to a prioritisation, forecast, or plan (to log what it predicts), when asked to review what actually happened, or to compute how well-calibrated past RICE…
scenario-zbrush-expert
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted…