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 fzfclee/consulting-skills --skill metrics-treegit clone --depth 1 https://github.com/fzfclee/consulting-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/fzfclee/consulting-skills/metrics-tree)<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/metrics-tree"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/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/fzfclee/consulting-skills/metrics-tree"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/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 | $0.00048 | $0.00745 |
| Opus 5 | $0.00024 | $0.00373 |
| Sonnet 5 | $0.00010 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00075 |
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 11d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metrics Tree
Use this skill to run Metrics Tree as a practical consulting method, not as a generic framework explanation.
Method Notes
- Start with one outcome, then decompose drivers and leading indicators.
- Add guardrails to prevent gaming or local optimization.
Required Inputs
Collect or infer these inputs before execution:
- north-star outcome
- business model or process
- available data
- owners
If an input is missing, do not block automatically. Mark it as missing, state the assumption used, and add a validation action.
When Not To Use
Do not use before the outcome metric and decision purpose are defined, or when proposed driver relationships cannot be tested. A metrics tree explains performance logic; it is not a dashboard inventory.
Adjacent Methods
north-star-metric: select one leading expression of delivered value.balanced-scorecard: balance financial, customer, process, and capability objectives.
Step-by-Step Execution
| Step | Required input | How to execute | Output |
|---|---|---|---|
| Define top outcome | Business/product objective and time window. | Write the outcome metric and why it matters. | Top metric. |
| Decompose drivers | Business model, funnel, process, user behavior. | Break the outcome into mathematical or causal drivers. | Driver tree. |
| Add leading indicators | Driver tree and process timing. | Identify measures that move before the top outcome changes. | Leading indicator set. |
| Add guardrails | Risk, quality, cost, customer experience, fairness constraints. | Choose metrics that prevent gaming. | Guardrail metrics. |
| Define operating use | Owners, data sources, review cadence. | Set formula, owner, threshold, and action trigger. | Metric operating plan. |
Output Template
### 1. Outcome Definition
Top outcome:
Population / scope:
Time window:
Unit:
### 2. Driver Tree
| Level | Metric | Formula | Causal rationale | Owner |
|---|---|---|---|---|
| | | | | |
### 3. Leading Signals And Guardrails
| Metric | Type | Threshold | Data source | Risk controlled |
|---|---|---|---|---|
| | | | | |
### 4. Operating Cadence
| Review | Frequency | Decision triggered | Owner |
|---|---|---|---|
| | | | |
### Evidence And Next Decision
- Confirmed facts:
- Assumptions:
- Missing evidence:
- Next action, owner, and timing:
- Expected signal and decision threshold:
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.
- 11d ago First seen · 86 lines · 48 tokens per session scan A 9d32fc9d62f5
metrics-tree is a skill published in the GitHub repository fzfclee/consulting-skills (4 stars, last pushed 22d ago), licensed Apache-2.0. It adds 48 tokens to every session and 745 once invoked, about $0.0002 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
taxue-solve
A thinking aid that turns a vague problem or difficult choice into a clear plan of action. It first examines what the real problem is, including whether emotions are hiding the main question.
meme-interpreter
An internet-meme and slang interpreter that explains online jokes, expressions, images, group jargon, and references in their real social context.
taxue-calm
A problem-framing guide that turns anxiety, stress, overthinking, low energy, or emotional overwhelm into a specific practical question.
taxue-career-resume
A resume and job-description tool for comparing a person’s experience with a specific job opening. It can create a reusable master resume and tailored versions for individual applications.
taxue-career
A career-planning guide covering the full path from choosing a direction to starting, settling into, changing, or leaving a job.
taxue-industry
A three-level method for understanding an industry: a broad overview, deeper research, and business judgement. It examines the supply chain, competitors, and market structure.