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/0xranx/agentbrief/metrics-frameworknpx skills add 0xranx/agentbrief --skill metrics-frameworkgit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/metrics-framework)<a href="https://agentmods.dev/skills/0xranx/agentbrief/metrics-framework"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/metrics-framework.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 | $0.00076 | $0.00646 |
| Opus 5 | $0.00038 | $0.00323 |
| Sonnet 5 | $0.00015 | $0.00129 |
| Haiku 4.5 | $0.00008 | $0.00065 |
Grade A, and why
metrics-framework 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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metrics Framework Design
You are designing a metrics framework that drives better decisions — not a dashboard that looks impressive.
Process
1. Identify the Business Question
Before choosing any metric, answer:
- What decision will this metric inform?
- Who is the audience? (CEO, PM, engineer, investor)
- What action will we take if the metric goes up/down?
If there's no action tied to the metric, it's a vanity metric. Skip it.
2. Choose the North Star Metric
One metric that best captures the value your product delivers to users:
| Business Type | Example North Star |
|---|---|
| SaaS | Weekly active workspaces |
| Marketplace | Transactions completed |
| Media/Content | Time spent reading |
| E-commerce | Purchases per month |
| Developer Tool | Builds triggered |
The north star must be:
- Measurable (can you actually track it?)
- Actionable (can the team influence it?)
- Leading (predicts future revenue, not just reports past)
3. Build the Metric Tree
Break the north star into a tree of input metrics:
North Star: Weekly Active Workspaces
├── New workspace activations
│ ├── Signups
│ ├── Signup → Activation rate
│ └── Time to activation
├── Returning workspaces
│ ├── D7 retention
│ ├── D30 retention
│ └── Feature engagement score
└── Resurrected workspaces
├── Re-engagement emails sent
└── Re-engagement conversion rate
4. Set Baselines and Targets
For each metric:
- Current value (baseline)
- Target (where we want to be)
- Timeline (by when)
- Owner (who is responsible)
5. Define the Dashboard
Three tiers:
- Executive dashboard — 5-7 metrics, updated weekly
- Team dashboard — 10-15 metrics, updated daily
- Operational alerts — Thresholds that trigger notifications
Output Format
## Metrics Framework: [Product/Feature]
### North Star
[Metric name]: [Current value] → [Target] by [Date]
### Input Metrics
| Metric | Current | Target | Owner | Update Frequency |
|--------|---------|--------|-------|-----------------|
| ... | ... | ... | ... | ... |
### Alerts
- [Metric] drops below [threshold] → notify [team]
### What We're NOT Tracking (and why)
- [Metric] — [reason it's not useful right now]
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.
- 4d ago First seen · 91 lines · 76 tokens per session scan A 1873fd36e1c5
metrics-framework is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 646 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.