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/nickcrew/claude-cortex/decision-makernpx skills add NickCrew/Claude-Cortex --skill decision-makergit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/decision-maker)<a href="https://agentmods.dev/skills/nickcrew/claude-cortex/decision-maker"><img src="https://agentmods.dev/badge/skills/nickcrew/claude-cortex/decision-maker.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 | $0.00059 | $0.02016 |
| Opus 5 | $0.00030 | $0.01008 |
| Sonnet 5 | $0.00012 | $0.00403 |
| Haiku 4.5 | $0.00006 | $0.00202 |
Grade A, and why
decision-maker 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 yesterday.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Maker
Overview
This skill applies proven decision-making frameworks—pros/cons analysis, weighted scoring matrices, RICE prioritization, the Eisenhower urgency-importance matrix, and pre-mortem analysis—to help you cut through ambiguity and make defensible, well-reasoned choices. By externalizing the decision into a structured format you reduce cognitive bias, surface hidden trade-offs, and create a record of your reasoning that can be revisited or shared with stakeholders.
When to Use
- You have two or more meaningful options and are unsure which to choose
- The decision has significant, lasting consequences (career, finances, product roadmap, hiring)
- Multiple stakeholders need to align around a shared rationale
- You feel emotionally stuck and want an objective framework to cut through the noise
- You need to prioritize a backlog of features, tasks, or projects
- You want to stress-test a decision you've already leaned toward
When NOT to Use
- The decision is low-stakes and reversible (where any choice is fine)
- You need licensed advice (legal, medical, financial) — frameworks support, not replace, professionals
- The situation requires immediate crisis action with no time for structured analysis
- Data needed to score criteria is completely unavailable or unknowable
- You simply want validation for a decision already firmly made
Quick Reference
| Framework | Best For | Output |
|---|---|---|
| Pros / Cons | Simple binary choices, fast gut-check | Two-column list |
| Weighted Scoring Matrix | Multi-option, multi-criteria trade-offs | Ranked score table |
| RICE | Feature or project prioritization | Priority-ranked backlog |
| Eisenhower Matrix | Task triage and time management | 4-quadrant urgency/importance grid |
| Pre-Mortem | Risk identification before committing | List of failure modes and mitigations |
Instructions
- Clarify the decision — State the decision in one clear sentence. Define what "success" looks like and the deadline by which you must decide.
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.
- yesterday First seen · 142 lines · 59 tokens per session scan A f455b5e04167
decision-maker is a skill published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 2,016 once invoked, about $0.0003 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
Decision Helper
Make better decisions using structured frameworks and mental models.
opportunity-cost
当用户纠结"要不要卖/换/止盈/止损"时激活。核心信号：用户用买入成本、浮盈浮亏、持仓时间作为卖出理由，或问"已经赚了X%该不该走"。也适用于纠结"持有A还是换B"的资产配置场景。不适用于：纯估值计算（交给 dcf-valuation）、判断公司好坏（交给 good-business）、情绪安抚（交给 equanimity-mindset）。本 skill 只解决一个问题——用机会成本统一买卖逻辑，消除"成本锚定"和"止盈止损"的伪决策。.
six-thinking-hats
Apply Edward de Bono's Six Thinking Hats methodology to software testing for comprehensive quality analysis. Use when designing test strategies, conducting test retrospectives, analyzing test failures, evaluating testing approaches, or facilitating testing discussions. Each hat provides a distinct testing perspective…
multi-research
Investigacion cruzada multi-modelo usando APIs directas. Lanza consultas paralelas a Claude + Gemini + Grok via SSH a W2, luego sintetiza con Claude. Ideal para decisiones tecnicas, evaluacion de herramientas, y analisis profundo. Use when: (1) Evaluar una herramienta/framework/libreria, (2) Tomar una decision tecnica…
Decision Helper
Make better decisions using structured frameworks and mental models.
factor-research
Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.