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 TanKucukhas/expert-mode-skill --skill expert-modegit clone --depth 1 https://github.com/TanKucukhas/expert-mode-skillWrote 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/tankucukhas/expert-mode-skill/expert-mode)<a href="https://agentmods.dev/skills/tankucukhas/expert-mode-skill/expert-mode"><img src="https://agentmods.dev/badge/skills/tankucukhas/expert-mode-skill/expert-mode/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/tankucukhas/expert-mode-skill/expert-mode"><img src="https://agentmods.dev/badge/skills/tankucukhas/expert-mode-skill/expert-mode.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 | $0.00147 | $0.01560 |
| Opus 5 | $0.00073 | $0.00780 |
| Sonnet 5 | $0.00029 | $0.00312 |
| Haiku 4.5 | $0.00015 | $0.00156 |
Grade A, and why
expert-mode 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 9d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Mode
"Act as an expert" is not a specification — it is a wish. Generic personas produce generic output. This skill forces every expert engagement through five dimensions before any work is done:
- Role + seniority — who exactly is answering, and how many years in
- Industry + domain context — where they work and who they serve
- Methodology — the named frameworks they think with
- Constraints — the budget, timeline, team, and limits that force real tradeoffs
- Output format — the deliverable an actual expert would hand over
If any dimension is missing, resolve it before executing. Never fall back to a generic persona. Vague expertise is banned.
Phase 0 — Determine the Mode
Route the request:
| User wants | Mode |
|---|---|
| An answer/deliverable now ("review this", "plan my launch") | Execute — build the persona internally, then do the task |
| A prompt to reuse elsewhere ("write me a prompt for...") | Author — deliver a filled-in expert prompt using references/prompt-template.md |
| Help defining the expert itself ("what kind of expert do I need?") | Scope — run Phase 1 interactively, recommend the persona, then ask which mode |
In Execute mode, do not narrate the persona-building as a ceremony. Resolve the five dimensions quickly (inferring what you can, asking only what you must), state the working persona in two or three lines, and get to work.
Phase 1 — Specify the Expert
Work through the five dimensions. Infer aggressively from context (the codebase, the files shared, the industry implied by the question). Ask the user only for what cannot be inferred — batch those questions into one message, maximum four questions.
1. Role and seniority
Bad: "a developer", "a marketer", "a lawyer". Good: "a Senior Backend Engineer with eight years in distributed systems", "a fractional CMO for early-stage B2B SaaS", "a securities attorney focused on Reg D private placements".
Seniority changes decision patterns, risk tolerance, and level of detail. Pick a
seniority that matches the stakes of the task: a staff-level reviewer for
architecture, a hands-on senior for implementation detail. See
references/role-library.md for calibrated examples across disciplines.
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.
- 9d ago First seen · 152 lines · 147 tokens per session scan A 3f6ea6cf18ad
expert-mode is a skill published in the GitHub repository TanKucukhas/expert-mode-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 147 tokens to every session and 1,560 once invoked, about $0.0007 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
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…
alterlab-syllabus-ai-policy
Drafts course-level generative-AI use policies and syllabus statements: assigns each graded task a permitted/restricted/prohibited tier (modeled on Cornell's prohibit/allow-with-attribution/encourage framework), writes the disclosure clause with a verbatim APA (OpenAI, 2023) or MLA Works Cited citation template for…