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 stefanoskarakasis/Product-Marketing-Skills --skill pmm-metricsgit clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-SkillsWrote 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/stefanoskarakasis/product-marketing-skills/pmm-metrics)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/pmm-metrics"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/pmm-metrics/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/stefanoskarakasis/product-marketing-skills/pmm-metrics"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/pmm-metrics.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 | $0.00094 | $0.03831 |
| Opus 5.5 | $0.00038 | $0.01532 |
| Sonnet 5.5 | $0.00019 | $0.00766 |
| Haiku 4.5 | $0.00009 | $0.00383 |
Grade A, and why
pmm-metrics 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 8d 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 — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PMM Metrics
How This Works
Picks one North Star Metric that predicts customer value and revenue, names the 3-5 Input Metrics that move it, then rounds out a scorecard across four categories (Financial, Customer, Product & GTM, Process & Growth), capped at 2-4 metrics per category — 8-16 total, small enough that a team actually updates it every 1-2 weeks instead of abandoning it by Q2.
Every target and current value comes from the user — this skill doesn't
invent numbers. If brain Section 2 (ICP/Beachhead) is loaded, it uses
that to check whether a metric is a real leading indicator for the
confirmed segment or just generic. Output is chat-only, disposable —
the brain has no Metrics section to write to (all 6 existing sections
are claimed), same treatment experiment-ideas (pmm-growth) gives its
output.
Step 0 — Load brain Sections 1 (Product), 2 (ICP/Beachhead) if
present, and guardrails from /context/meta-patterns.md.
Step 1 — Classify the business game: Attention, Transaction, or Productivity.
Step 2 — Define the North Star Metric and validate it against 7 criteria.
Step 3 — Define 3-5 Input Metrics that most directly move the North Star.
Step 4 — Build the supporting scorecard: 2-4 metrics per category across Financial, Customer, Product & GTM, and Process & Growth, each with a target, weight, and cadence.
Step 5 — Self-check the full set against sprawl and vanity-metric traps.
Step 6 — Deliver the scorecard as a markdown table the user saves themselves — this skill has no durable output file of its own.
Step 7 — Learning Close: log the session to /context/skill-sessions.md.
Trigger
- When: Choosing a North Star Metric, building a measurement framework from scratch, auditing an existing metrics list that's sprawled past what anyone tracks, or preparing a scorecard for leadership/exec reporting.
- Not for: Quarterly OKRs once metrics exist →
pmm-okrs(pmm-execution) expresses target change in metrics this skill defines; run this skill first if no North Star exists yet. Launch tier assignment →go-to-market-strategy. Pressure-testing one experiment's hypothesis →experiment-doc(pmm-execution) — feed it this skill's metric as the guardrail, don't invent a new one. Post-launch metrics review →retro(pmm-execution) looks backward at what this skill's scorecard already tracks. - Example prompts:
- "What should we be measuring?"
- "Help me define our North Star metric"
- "Build a PMM scorecard for leadership"
- "What metrics should Product Marketing track?"
- "Our metrics list has 25 things on it and nobody updates it"
- "Set up a measurement framework for Q1"
What ships with it
1 file 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.
- 8d ago Changed · -4 lines · -33 tokens per session 09a74c657f77
- 16d ago Changed 9c197a204ea0
- 20d ago Changed · +1 lines ecd3dfa77f63
- 21d ago Changed · +2 lines e8159760ac68
- 22d ago Changed · +12 lines 4781f47ffc61
- 1mo ago First seen · 397 lines · 127 tokens per session scan A e39b1af9fd7a
pmm-metrics is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 3,831 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 2026-09-15.
Other skills, from other repositories
report
A way to export a chat card or reply as a standalone HTML report, meaning a file that can open in a browser without the chat application. It preserves the card template, including right-to-left Persian or left-to-right English layouts.
k8s-rightsize
Right-size Kubernetes CPU and memory requests from Prometheus usage (p95 CPU, p98 memory over 7 days), size the node count, tune KEDA autoscaling. Use when asked to rightsize workloads, cut node cost, or "how many nodes do we need".
owasp-security
Deep OWASP reference: Top 10 2025, ASVS 5.0, secure patterns, per-language quirks, LLM Top 10 and agentic AI security. Use for an in-depth security review, auth work, or hardening an LLM or agent app. For the everyday baseline use secure-coding.
fig
One self-contained HTML file holding a looping animated SVG, for ideas that move: flows, loops, retries, queues, fan-outs. Use when the user says "fig" or a diagram would be better animated.
brand
A project-specific visual identity for chat cards and saved reports, using the project's colors, logo, and fonts. It finds these details in the repository or asks the user for them, then stores the result in a committable `.readable/` folder.
workspace-rules
A set of guidelines for deciding which rules belong in a repository's workspace instructions and which should be enforced by its build or checks.