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 liqiongyu/lenny_skills_plus --skill writing-north-star-metricsgit clone --depth 1 https://github.com/liqiongyu/lenny_skills_plusWrote 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/liqiongyu/lenny_skills_plus/writing-north-star-metrics)<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/writing-north-star-metrics"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/writing-north-star-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/liqiongyu/lenny_skills_plus/writing-north-star-metrics"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/writing-north-star-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 | $0.00019 | $0.01808 |
| Opus 5 | $0.00010 | $0.00904 |
| Sonnet 5 | $0.00004 | $0.00362 |
| Haiku 4.5 | $0.00002 | $0.00181 |
Grade A, and why
writing-north-star-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 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing North Star Metrics
Scope
Covers
- Defining or refreshing a product/company North Star and North Star Metric
- Translating a qualitative value model into measurable, decision-useful metrics
- Creating a simple driver tree: leading input/proxy metrics + guardrails
- Producing a “North Star Metric Pack” teams can use as a decision tie-breaker
When to use
- “We need one metric that defines success.”
- “Teams are optimizing different KPIs.”
- “We’re setting quarterly OKRs and need leading indicators.”
- “We’re launching a new strategy and need a metric that aligns decisions.”
When NOT to use
- You only need OKRs for an already-agreed North Star -> use
setting-okrs-goals - You need a full analytics taxonomy/event tracking plan from scratch
- Stakeholders haven’t aligned on the customer value model / mission at all -> use
defining-product-visionfirst - You’re choosing a single experiment metric for a one-off test
- You need to diagnose retention or engagement patterns, not define the top-level metric -> use
retention-engagement - You need to assess whether you have product-market fit -> use
measuring-product-market-fit
Inputs
Minimum required
- Product/company + primary customer segment
- The “value moment” (what the customer gets when things go well)
- Business model + strategic goal (growth, activation, retention, margin, trust, etc.)
- Time horizon (next quarter vs next year)
- Measurement constraints (what you can measure today; data latency; known gaps)
Missing-info strategy
- Ask up to 5 questions from references/INTAKE.md.
- If still missing, proceed with clearly labeled assumptions and provide 2–3 options.
Outputs (deliverables)
Produce a North Star Metric Pack in Markdown (in-chat; or as files if the user requests):
- North Star Narrative (value model, tie-breaker, scope)
- Candidate metrics (3–5) + selection rationale (evaluation table)
- Chosen North Star Metric spec (definition, formula, window, segmentation, owner, data source)
- Driver tree (leading input/proxy metrics + guardrails)
- Validation & rollout plan (instrumentation checks, dashboard cadence, decision rules)
- Risks / Open questions / Next steps (always included)
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.
- eval/eval_config.json 437 B
- eval/SHOWCASE.md 5.6 KB
- eval/with_skill.md 31 KB
- eval/without_skill.md 19 KB
- README.md 1.7 KB
- references/CHECKLISTS.md 2.9 KB
- references/EXAMPLES.md 4.9 KB
- references/INTAKE.md 1.8 KB
- references/RUBRIC.md 3.1 KB
- references/SOURCE_SUMMARY.md 1.8 KB
- references/TEMPLATES.md 2.4 KB
- references/WORKFLOW.md 3.0 KB
- skillpack.json 402 B
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 · 137 lines · 19 tokens per session scan A 9228ff3f30f1
writing-north-star-metrics is a skill published in the GitHub repository liqiongyu/lenny_skills_plus (52 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,808 once invoked, about $0.0001 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
cangjie-skill
A process for turning a book, course, podcast, interview, long video, or other long material into reusable instructions for an AI agent. It extracts methods and principles, checks them, and packages them as skills.
plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…
loop-library
Compatibility alias for Loopy. Use only when an existing installation or older instruction explicitly invokes loop-library; use Loopy for new installations and requests. Provides the same discovery, recommendation, audit, repair, adaptation, guided crafting, bounded execution, run debrief, project loop saving, and…
naval-almanack
A reference guide for applying ideas from The Almanack of Naval Ravikant, a book about wealth, work, happiness, judgment, and long-term thinking. It routes questions to the relevant topic guidance and notes when professional help is needed.
decision-heuristics
A set of heuristics for making difficult personal decisions such as changing jobs, buying a home, moving, forming a partnership, or getting married. It is intended for major choices, not everyday decisions.
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.