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 Rheinmir/setup --skill dym-arex-skill-chay-viec-researchergit clone --depth 1 https://github.com/Rheinmir/setupWrote 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/rheinmir/setup/dym-arex-skill-chay-viec-researcher)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-arex-skill-chay-viec-researcher"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-arex-skill-chay-viec-researcher/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/rheinmir/setup/dym-arex-skill-chay-viec-researcher"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-arex-skill-chay-viec-researcher.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 | $0.00057 | $0.01504 |
| Opus 5.5 | $0.00023 | $0.00602 |
| Sonnet 5.5 | $0.00011 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
dym-arex-skill-chay-viec-researcher 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-arex-skill-chay-viec-researcher — Chạy việc nghiên cứu ở Researcher mode (shell)
Vì sao dùng: Đây là đường dùng chính hằng ngày — giao một mục tiêu nghiên cứu cụ thể, để router chọn skill và agent tự chạy + tự kiểm chứng.
Sinh ra cái gì: Session file, sản phẩm thật trong thư mục làm việc (script, config, số đo), và output trên stdout theo --mode.
File này chỉ có lệnh shell. Lệnh gõ trong TUI nằm ở
08-lenh-chat-trong-tui.md.
1. Tương tác
disco # Researcher là mode MẶC ĐỊNH
disco --researcher # nói rõ ra, cho session mới
Ví dụ prompt gõ ở dấu nhắc:
Use the installed skills to benchmark vLLM and SGLang on this machine under the same model, workload, and hardware constraints. Report verified throughput and preserve the commands and measurements needed to reproduce the comparison.
2. Một phát rồi thoát (-p / --print)
disco -p "Fix the failing tests in this repository and run the relevant test suite"
disco --researcher -p "Benchmark vLLM and SGLang with the same model and workload on this machine. Tune each server under identical hardware and memory constraints, report the best verified throughput for each, and preserve the commands and measurements needed to reproduce the comparison."
Exit code của print mode (đọc từ modes/print-mode.ts, không phải từ README):
| Tình huống | Exit |
|---|---|
| Hoàn tất bình thường | 0 |
Message cuối của assistant có stopReason là error hoặc aborted — lỗi in ra stderr |
1 |
Nhận SIGHUP |
129 |
Nhận SIGTERM |
143 |
Nghĩa là: exit 0 không đảm bảo nhiệm vụ nghiên cứu thành công, chỉ đảm bảo phiên agent kết thúc không lỗi. Muốn gác chất lượng thì phải tự kiểm sản phẩm nó tạo ra.
3. Gọi thẳng một skill khi đã biết chính xác cần gì
disco --researcher -p "/skill:vllm determine and verify the highest-throughput vLLM configuration for <model and workload>"
Quy ước tên lệnh là skill:<tên-skill> (dựng trong agent-session.ts / interactive-mode.ts / rpc-mode.ts). Gọi thẳng thì bỏ qua bước router, tiết kiệm lượt và dễ audit hơn.
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 · 118 lines · 57 tokens per session scan A 2f5122aac875
dym-arex-skill-chay-viec-researcher is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 57 tokens to every session and 1,504 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
dym-arex-skill-chay-viec-researcher compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-arex-skill-chay-viec-researcherRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 57 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |