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/askroundtable/expert-skills/expert-enginenpx skills add AskRoundtable/expert-skills --skill expert-enginegit clone --depth 1 https://github.com/AskRoundtable/expert-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/askroundtable/expert-skills/expert-engine)<a href="https://agentmods.dev/skills/askroundtable/expert-skills/expert-engine"><img src="https://agentmods.dev/badge/skills/askroundtable/expert-skills/expert-engine.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 | $0.00042 | $0.06010 |
| Opus 5 | $0.00021 | $0.03005 |
| Sonnet 5 | $0.00008 | $0.01202 |
| Haiku 4.5 | $0.00004 | $0.00601 |
Grade A, and why
expert-engine 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 — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Thinking Engine
A cognitive framework for expert-level analysis based on Gary Klein's Recognition-Primed Decision (RPD) model.
When to Load
Load this skill when:
- Analyzing complex decisions or problems
- Needing structured expert thinking (not just opinions)
- Combining with an expert module (expert-munger, expert-feynman, etc.)
Required Companion
This skill provides the thinking process. Load with an expert module to provide:
- Domain-specific patterns
- Mental models
- Cue sensitivity
Example: npx openskills read expert-engine,expert-munger
Output Style
Default: Conversational
The 6-step process is internal reasoning scaffolding. The user should experience a conversation, not a report.
Unless the user explicitly asks for a "full analysis" or "detailed report":
- Do NOT show step labels (## Step 0, ## Pattern Recognition, etc.) in output
- Ask ONE question at a time — never bundle multiple questions in one turn
- Present insights as flowing prose, not formatted tables
- Surface confidence only when uncertainty is decision-relevant — omit numeric scores unless they change what the user should do
- Earn more detail: start with the sharpest single insight; expand only if user asks
The full structured format (tables, all steps labeled, confidence matrix) is reserved for:
- User explicitly requests "full analysis" or "structured breakdown"
- Complex multi-stakeholder decisions where a written record has value
For Step 0 specifically: one reframing question → wait for answer → then proceed. Never ask two questions in the same turn.
The 6-Step Cognitive Process
Step 0: Discovery (Situation Clarification)
Before analyzing, clarify the situation and assess information quality. This step uses frameworks from references/communication-frameworks.md.
Process:
- Read the problem statement carefully
- Apply appropriate inquiry technique (Open-to-Specific, Timeline, Perspective Shift)
- Monitor conversation quality (confidence score)
- Identify critical information gaps
- Decide: proceed, ask more, or escalate
What ships with it
3 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.
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 · 652 lines · 42 tokens per session scan A 58c9426e27f3
expert-engine is a skill published in the GitHub repository AskRoundtable/expert-skills (51 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 6,010 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 2026-08-30.
Other skills, from other repositories
thinking-partner
A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says "help me think through X", "challenge my thinking", "what am I missing", "apply mental models to this", "play devil's advocate"…
blindspot-check
Checks a big decision for blind spots against a catalogue of 95 cognitive biases before the user commits. Use when the user is about to make or has just justified a major life decision and wants to be checked for self-deception — buying a house, relocating, signing a long lease or contract, quitting or taking a job…
council
Evidence-bound multi-agent council for high-stakes decisions. Scout uses last30days, Advocate and Skeptic debate, Fact Checker uses deep-research Quick mode. Delivers ranked options with #1 marked, dissent preserved, and the condition that would flip the verdict. Use when user says council this, /council, run the…
thinking-toolkit
A toolkit of 30 decision-making, problem-solving, systems-thinking, and communication models, plus a /logic mode that audits an argument's validity. This skill should be used when a user names a specific model, or describes a situation that calls for one: framing or reframing a problem, comparing options, setting…
munger-mental-models
查理·芒格多元思维模型决策分析工具（v1.6）。 v1.6 新增：跨学科综合引擎（Latticework Synthesis Engine）——把「模型库」升级为真正的「思维格栅」。 强制学科覆盖（防「拿着锤子的人」，≥3 学科含 1 硬科学、不许心理+经济两科占满）→ Latticework 交互矩阵 （模型两两对照标 🟢共振/🔴冲突/⚪独立）→ 共振协议（多个独立学科收敛升置信，但剔除假收敛/回声） → 冲突协议（冲突只裁决不平均：前提审计 + D4 不可逆否决，方向归前提在场者、刹车归输不起的一方）。 v1.5 新增：Lollapalooza 效应（独立核心模型 + 4 步风险扫描协议）——识别 3+ 偏误/激励同向作用…
reflect
Think through any decision — code, business, personal — and get a straight answer. Fires on "reflect on X", "start from first principles", "reflect"; AND fire it YOURSELF, unprompted, whenever the work hits a choice whose undo cost exceeds a bad day (architecture, dependencies, pricing, public commitments, people) or…