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 Waddling-Penguin/mogkit --skill metrics-treegit clone --depth 1 https://github.com/Waddling-Penguin/mogkitWrote 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/waddling-penguin/mogkit/metrics-tree)<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/metrics-tree"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/metrics-tree/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/waddling-penguin/mogkit/metrics-tree"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/metrics-tree.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 | $0.00002 | $0.01056 |
| Opus 5 | $0.00001 | $0.00528 |
| Sonnet 5 | $0.00000 | $0.00211 |
| Haiku 4.5 | $0.00000 | $0.00106 |
Grade A, and why
metrics-tree 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 9d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A PM has been handed (or has set) a vague goal: "increase activation", "improve retention", "grow revenue". Before they can plan against it, they need to know what the goal actually measures, what inputs move it, and what they can observe sooner than the lagging outcome. This skill produces that structure.
It does NOT recommend targets, benchmarks, or "industry-standard" numbers. It will not say "good activation is 30%." Those numbers are situational; inventing them lets the PM plan against a fake target. The skill maps the structure of the goal and tells the PM what to measure. The PM (or the data team) supplies the numbers.
Procedure
- Read the PM's stated goal. If it is two or more goals stuffed into one sentence, split them and ask the PM to pick one before continuing.
- Define the top metric. State it as a single measurable quantity and write its defining equation. If the goal admits more than one plausible top metric (e.g. "activation" could be % of signups completing setup, or % reaching first value), name them, pick one as the primary, and note the others as competing definitions the PM should resolve.
- Decompose the top metric into its input metrics — the multiplicands or addends in its equation. Each input must be something instrumentable, not a vibe.
- For each input metric, name 1–2 leading indicators — earlier signals that predict movement in the input. Leading indicators are observable on a shorter time horizon than the input itself.
- List instrumentation gaps: every metric in the tree the PM probably cannot measure today without new tracking. Mark each "you must measure this before you can act on it."
- Identify the single metric most worth moving first. Justify it in one short paragraph: why it has the highest expected leverage on the top metric given what the tree shows. If the tree is too thin to support that pick honestly, say so and name what would need to be known to choose.
- Emit the output contract. Do not emit target numbers, benchmarks, or comparisons to other companies.
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.
- 9d ago First seen · 93 lines · 2 tokens per session scan A 5cca03a8f9cd
metrics-tree is a skill published in the GitHub repository Waddling-Penguin/mogkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 2 tokens to every session and 1,056 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.