research-lab

research-lab is a skill for Claude Code, Codex from ooooooooooooooooooop/agent-tools. It costs 115 tokens per session (1,145 once invoked), scanned A, original, MIT.

A research workflow for questions that can be tested with evidence, such as comparing models or software. It defines the question, baseline, candidates, data, measurements, and decision rules before running or resuming an experiment.

In plain words
What is it for?
Model comparisons, software evaluations, baseline tests, replacement decisions, ablation studies, blind reviews, evidence audits, and continuing interrupted research.
Why use it?
It prevents conclusions based only on opinion or a single result. It keeps experiments reproducible and links conclusions to recorded evidence and outputs.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ooooooooooooooooooop/agent-tools/research-lab
Any agent
npx skills add ooooooooooooooooooop/agent-tools --skill research-lab
Clone the repo
git clone --depth 1 https://github.com/ooooooooooooooooooop/agent-tools

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for research-lab

README.md
[![agentmods](https://agentmods.dev/badge/skills/ooooooooooooooooooop/agent-tools/research-lab.svg)](https://agentmods.dev/skills/ooooooooooooooooooop/agent-tools/research-lab)
Your own site
<a href="https://agentmods.dev/skills/ooooooooooooooooooop/agent-tools/research-lab"><img src="https://agentmods.dev/badge/skills/ooooooooooooooooooop/agent-tools/research-lab.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,145 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00115 $0.01145
Opus 5 $0.00057 $0.00573
Sonnet 5 $0.00023 $0.00229
Haiku 4.5 $0.00012 $0.00114

Measured 3d ago against content hash 5b85ddd36cba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-lab 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 3d 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.

skills/research-lab/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Lab

目标

Research Skill 是独立 Research Runtime 的使用协议,不是研究系统本体。它负责识别研究任务、约束研究设计、调用稳定 research_ 前缀工具,并依据 Evidence 返回结论;实验、统计、Workspace、同步和恢复由 Research Core 负责。

触发门禁

满足任一条件时使用:

  • 用户要求比较模型、方案或系统,且需要质量、成本或延迟证据。
  • 用户提出“能否替代”“是否显著更好”“哪个更可靠”等可证伪问题。
  • 结论依赖数据集、Baseline、重复运行、盲评、消融或环境记录。
  • 用户要求恢复、复现、审计或跨设备继续既有 Research。

不要用于简单事实查询、单一确定答案、无需实证的文案建议或低成本可逆选择。

硬规则

  1. 不得从用户问题直接跳到结论;先建立或验证 ResearchSpec。
  2. Spec 至少明确 question、hypotheses、单个 baselinecandidates、dataset/cases、metrics、decision rules 和 adapters;执行字段以当前 research validate 为准。
  3. 不具备所需模型、数据或执行能力时返回 UNSUPPORTED,不得模拟实验结果。
  4. Spec 或执行过程无效时返回 INVALID;有效实验但证据不足时返回 INCONCLUSIVE
  5. 结论必须引用 Evidence、Run 和 Artifact digest;不能只复述模型输出。
  6. 不把 API key、token、私钥、绝对用户路径或 credential value 放入 Spec、Workspace、CAS 或工具参数;只使用设备本地配置或 credential reference。
  7. 多设备 revision 冲突必须显式呈现,禁止静默选择最后写入版本。

标准流程

  1. 识别任务:把问题改写成可证伪 question;明确候选方案与 Baseline。
  2. 建立 Spec:若用户已有 Spec,调用 research_validate;否则生成便携 JSON 文件后调用 research_create
  3. 执行前检查:用 research_inspect 检查 revision、数据集、Adapter 和决策阈值。缺关键条件时停止执行并返回结构化缺口。
  4. 执行或恢复:调用 research_execute。已有 run 时传入 run id;中断后调用 research_continue,不要创建重复研究冒充恢复。
  5. 检查状态:用 research_status 查看已完成/失败/待执行项,不进行热轮询;等待真实执行反馈。
  6. 比较与证据:调用 research_compare,再用 research_evidence 获取支撑与限制。
  7. 返回结论:只使用 Runtime 的 Decision 枚举:SUPPORTEDREJECTEDINCONCLUSIVEUNSUPPORTEDINVALID

LLM 对比最小 Spec

{
  "protocolVersion": "1.0",
  "researchId": "model-replacement-evaluation",
  "question": "Candidate 是否可替代 Baseline 完成指定任务?",
  "taskType": "llm-comparison",
  "hypotheses": [{"id": "h1", "statement": "candidate 质量不低于 baseline 且成本更低"}],
  "baseline": {"id": "baseline", "adapter": "command"},
  "candidates": [{"id": "candidate", "adapter": "command"}],
  "dataset": {
    "cases": [{"id": "case-1", "input": "...", "expected": "..."}]
  },
  "metrics": ["exact_match", "latency_ms", "cost"],
  "decisionRules": {
    "minDelta": 0.0,
    "preferred": "candidate"
  },
  "adapters": {
    "command": {
      "type": "command",
      "command": ["python", "path/to/adapter.py"]
    }
  }
}

Read the full file on GitHub · 92 lines

Files

What ships with it

2 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.

Changes

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.

  1. 3d ago First seen · 92 lines · 115 tokens per session scan A 5b85ddd36cba

Subscribe to this mod's changes

research-lab is a skill published in the GitHub repository ooooooooooooooooooop/agent-tools (2 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 1,145 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

zlog

Multi-agent session log compressor and storage optimizer. Compresses .log, .out, .txt, .trace (>10KB) to .zst, .xz, or .gz (saving 77%-99.9% disk space) across /.gemini, /.config/Cursor, /.ollama, /.claude, /.windsurf, /.codex, etc. Auto-discovers AI log dirs, purges empty 0-byte logs. Safe for concurrent…

sebin-gg/zlog · 150 tokens

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

muapi-media-editing

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.

SamurAIGPT/Generative-Media-Skills · 41 tokens

ctf-malware

Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…

ljagiello/ctf-skills · 101 tokens

research

Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.

Weizhena/Deep-Research-skills · 25 tokens