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/loopnpx skills add ngocsangyem/MeowKit --skill loopgit 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/loop)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/loop"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/loop.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 | $0.00095 | $0.02422 |
| Opus 5 | $0.00048 | $0.01211 |
| Sonnet 5 | $0.00019 | $0.00484 |
| Haiku 4.5 | $0.00010 | $0.00242 |
Grade A, and why
mk:loop 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mk:loop — Bounded Optimization Loop
Scope + mechanical metric + fast verify = bounded, git-tracked, boundary-gated improvement.
What This Skill Does
Improves ONE scalar metric (coverage %, bundle KB, lint-error count, latency ms, …)
by running bounded autonomous iterations: pick one atomic change → commit → verify →
keep if the number improved, otherwise git revert. Git history is the loop's memory;
a TSV log and summary are the artifacts. Autonomy is boundary-gated — one human
approval before the loop, then hands-off iteration up to a hard cap, with hard re-gates
on cap-reached, stuck/plateau, and scope-expansion. It never plans, never grades behavior,
never ships.
When to Use
- An objective, fast (<30s)
Verifycommand prints a single number. - A
Scopeof editable file globs is known. - You want N git-tracked trials with automatic keep-on-improve, revert-on-regress.
When NOT to Use
| Situation | Better tool |
|---|---|
| Subjective goal ("make it cleaner", "make it nicer") | mk:cook |
| Known root-cause bug to fix once | mk:fix / mk:investigate |
| Grade a running build against behavior/rubric | mk:evaluate |
| Green-field product build (generator⇄evaluator) | mk:autobuild |
| Structural review of a diff | mk:review |
| Open a PR / ship | mk:ship |
| No mechanical metric exists | mk:cook --interactive |
Configuration
Parsed from the user message. Missing required fields trigger ONE batched
AskUserQuestion — no command runs before they are supplied.
Required: Goal, Scope (globs), Metric (name + unit), Direction (higher|lower),
Verify (shell command → one number).
Optional: Guard, Iterations (default 10), Noise (low|medium|high, default medium),
Min-Delta (default derived from Noise), Stop-At.
Full contract, the batched-question template, the Verify/Metric pattern library, and
Noise/Min-Delta semantics live in references/config-and-metrics.md.
What ships with it
5 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.
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 · 208 lines · 95 tokens per session scan A b3a0a5eb1df2
mk:loop is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 2,422 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
cf:loop
Run an explicit, bounded optimization loop against a numeric metric while a separate correctness guard protects the result.
notion
Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…
slack
Use when the agent needs to send, edit, delete, or read Slack messages, add or list emoji reactions, pin or unpin messages, fetch member info, or list custom emoji in Slack channels and DMs. Handles all Slack workspace interactions including message management, reaction workflows, pinned-item management, and user…
apple-reminders
Manage Apple Reminders via the remindctl CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output. Use when the user asks about reminders, todos, tasks, to-do lists, "remind me", scheduling tasks, checking what is due today, completing or deleting reminders, or managing…
obsidian
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli. Use when the user asks about notes, vault management, PKM, knowledge base organization, wikilinks, or personal knowledge management in Obsidian.