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.
git clone --depth 1 https://github.com/unixcrh/phuryn-pm-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/commands/unixcrh/phuryn-pm-skills/north-star)<a href="https://agentmods.dev/commands/unixcrh/phuryn-pm-skills/north-star"><img src="https://agentmods.dev/badge/commands/unixcrh/phuryn-pm-skills/north-star/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/commands/unixcrh/phuryn-pm-skills/north-star"><img src="https://agentmods.dev/badge/commands/unixcrh/phuryn-pm-skills/north-star.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 | $0.00944 |
| Opus 5 | $0.00010 | $0.00472 |
| Sonnet 5 | $0.00004 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
north-star 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 12d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/north-star -- North Star Metric Definition
Identify the single metric that best captures the value your product delivers, plus the input metrics that drive it. Classifies your business game and validates against proven criteria.
Invocation
/north-star B2B SaaS for team collaboration
/north-star Consumer fitness app monetized through subscriptions
/north-star Help me fix our North Star — we're tracking DAU but it doesn't feel right
Workflow
Step 1: Understand the Product
Ask:
- What is the product? What value does it deliver to users?
- What's the business model? (subscription, transaction, advertising, marketplace)
- Current metrics being tracked (if any)
- Why is this needed now? (new product, existing metric feels wrong, team alignment)
Step 2: Classify the Business Game
Apply the north-star-metric skill:
Identify which game the product is playing:
- Attention: Revenue from user time/engagement (media, social, ad-supported)
- Transaction: Revenue from purchases (e-commerce, marketplace)
- Productivity: Revenue from efficiency gains (SaaS, tools, B2B)
The game determines what kind of North Star makes sense.
Step 3: Define the North Star
- Propose 2-3 North Star candidates
- Validate each against 7 criteria:
- Expresses value delivered to customers
- Is a leading indicator of revenue
- Is measurable and trackable
- Is understandable by the whole team
- Is actionable (teams can influence it)
- Is not a vanity metric
- Is not gameable without delivering real value
- Recommend the strongest candidate with rationale
Step 4: Define Input Metrics
For the selected North Star, identify 3-5 input metrics:
- Each input metric should be a lever that directly drives the North Star
- Each should be ownable by a specific team
- Together, inputs should be MECE in explaining North Star movement
Step 5: Generate Metrics Framework
## North Star Framework: [Product]
**Business Game**: [Attention / Transaction / Productivity]
### North Star Metric
**Metric**: [precise name]
**Definition**: [formula or measurement method]
**Why this metric**: [explains value, leads revenue, is actionable]
**Current value**: [if known]
**Target**: [goal]
### Validation
| Criterion | Pass? | Notes |
|----------|-------|-------|
| Expresses value | [Y/N] | [explanation] |
| Leading indicator | [Y/N] | [explanation] |
| Measurable | [Y/N] | [explanation] |
| Understandable | [Y/N] | [explanation] |
| Actionable | [Y/N] | [explanation] |
| Not vanity | [Y/N] | [explanation] |
| Not gameable | [Y/N] | [explanation] |
### Input Metrics
| Input Metric | Drives North Star By | Owner | Current | Target |
|-------------|---------------------|-------|---------|--------|
### Metrics Constellation
[Visual tree showing North Star → Input Metrics → Team Actions]
### Counter-Metrics
| Metric | Protects Against |
|--------|-----------------|
### Anti-Patterns Avoided
[Why we didn't choose DAU, revenue, or other common but flawed metrics]
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.
- 12d ago First seen · 114 lines · 19 tokens per session scan A d0acb35732da
north-star is a command published in the GitHub repository unixcrh/phuryn-pm-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 944 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.