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/redhuntlabs/wizard/general-research-loopnpx skills add redhuntlabs/wizard --skill general-research-loopgit clone --depth 1 https://github.com/redhuntlabs/wizardWrote 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/redhuntlabs/wizard/general-research-loop)<a href="https://agentmods.dev/skills/redhuntlabs/wizard/general-research-loop"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/general-research-loop.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 | $0.00027 | $0.01275 |
| Opus 5 | $0.00014 | $0.00638 |
| Sonnet 5 | $0.00005 | $0.00255 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
general-research-loop 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Research Loop
What this does
The default chain for serious research on any topic. Runs four bundled spells in sequence: scan the field, parallelize deep-dives on the canonical 5-8 sources, synthesize into a structured review, and verify every citation before publishing. Equivalent in spirit to a discipline-rigorous research workflow.
When to use
- Producing a research output that someone will rely on (memo, paper, brief, decision document)
- The topic is unfamiliar enough that you need to map it before deep-diving
- The output is for an audience who can check your sources
Do not use when
- A 30-minute read of one canonical source is enough — just read it
- You're already an expert on this topic — go straight to writing
- The decision deadline is in hours — use a faster, less rigorous flow
What you bring (Inputs)
- Research question (one sentence)
- Audience and depth target (memo / paper / brief)
- Time budget
- Source-access constraints (what databases, what languages)
What you get (Output)
A verified, structured research document: scope, methods, themes, evidence, gaps, and a bibliography where every citation has been opened.
How it works (Steps)
This is a chain of 4 spells. Each stage hands an artifact to the next.
Stages
Stage 1: Map the field (literature-scan)
- Skill:
literature-scan - Input: research question
- Output handoff: a one-page brief identifying the canonical 5-10 sources and the major positions
- Gate: at least 5 sources identified; positions are distinct
Stage 2: Deep-dive in parallel (researching-five-things-in-parallel)
- Skill:
researching-five-things-in-parallel - Input: the 5-8 canonical sources from Stage 1, with the same per-source extraction prompt (research question, method, finding, limitation, your one-line summary)
- Output handoff: a structured table of source-level extracts plus a compare section
- Gate: every source has a complete row; low-confidence entries are flagged for re-run
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 · 120 lines · 27 tokens per session scan A 9fa79f74d970
general-research-loop is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 1,275 once invoked, about $0.0001 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
fastapi
FastAPI - 高性能 Python Web API 框架.
glances
Skill "glances" from CN-big-cabbage/github-skill-distiller, covering glances 跨平台系统监控工具, 技能概述, 使用流程, 关键章节导航 and ai 助手能力.
lazydocker
本技能帮助用户通过 lazydocker 的终端 UI 界面管理 Docker 容器、镜像、卷和网络，支持以下场景：.
fzf
Skill "fzf" from CN-big-cabbage/github-skill-distiller, covering fzf 通用命令行模糊查找器, 技能概述, 使用流程, 关键章节导航 and ai 助手能力.
paper-checking
论文查重系统 - 一亿字次级论文库秒级查重，支持纵向查重和横向查重.
you-get
网页媒体下载助手 - 从YouTube、Bilibili等网站下载视频、音频、图片.