structured-research-workflow

structured-research-workflow is a skill for Claude Code, Codex from aiming-lab/MetaClaw. It costs 42 tokens per session (206 once invoked), scanned A, original, MIT.

A step-by-step guide for researching a question from scratch, such as reviewing academic literature, comparing products, or checking technical facts. It covers defining the question, finding sources, judging relevance, combining findings, citing sources, and noting uncertainty.

In plain words
What is it for?
It is for literature reviews, competitive research, technical due diligence, and other open-ended fact-finding tasks.
Why use it?
It reduces the risk of relying on the first search result or allowing research to drift away from the original question.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for literature reviews, competitive research, technical due diligence, and other open-ended fact-finding tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiming-lab/metaclaw/structured-research-workflow
About the project

MetaClaw is an AI-agent system that learns from conversations and evolves its behavior over time. It provides memory and learning modes for users who want an agent that adapts across interactions, with support for multiple claw-based agent projects.

aiming-lab/MetaClaw · 3,496 stars · on GitHub · arxiv.org

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.

Any agent
npx skills add aiming-lab/MetaClaw --skill structured-research-workflow
Clone the repo
git clone --depth 1 https://github.com/aiming-lab/MetaClaw

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 structured-research-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiming-lab/metaclaw/structured-research-workflow.svg)](https://agentmods.dev/skills/aiming-lab/metaclaw/structured-research-workflow)
Your own site
<a href="https://agentmods.dev/skills/aiming-lab/metaclaw/structured-research-workflow"><img src="https://agentmods.dev/badge/skills/aiming-lab/metaclaw/structured-research-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.00206
Opus 5 $0.00021 $0.00103
Sonnet 5 $0.00008 $0.00041
Haiku 4.5 $0.00004 $0.00021

Measured 7d ago against content hash 3ee1ab045966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

structured-research-workflow 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 7d 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.

memory_data/skills/structured-research-workflow/SKILL.md · 18 lines

What it actually says

Structured Research Workflow

  1. Define scope — Write the specific question you are trying to answer. Avoid scope creep.
  2. Search broadly first — Use multiple search strategies and keywords.
  3. Filter ruthlessly — Keep only sources that directly address the question.
  4. Read deeply — Skim abstracts/intros; read in full only when clearly relevant.
  5. Synthesize, don't transcribe — Group findings by theme; note agreements and conflicts.
  6. Cite — Record source URL/DOI at time of reading; don't reconstruct later.
  7. Flag uncertainty — Clearly separate what is established vs. contested vs. unknown.

Anti-pattern: Reporting the first search result without checking alternatives.

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. 7d ago First seen · 18 lines · 42 tokens per session scan A 3ee1ab045966

Subscribe to this mod's changes

structured-research-workflow is a skill published in the GitHub repository aiming-lab/MetaClaw (3,496 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 206 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.

Related

Other skills, from other repositories

llama-factory

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.

davila7/claude-code-templates · 51 tokens

tinker-fine-tuning

Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.

synthetic-sciences/openscience · 62 tokens

tinker-training-cost

Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.

synthetic-sciences/openscience · 55 tokens

transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…

synthetic-sciences/openscience · 63 tokens

colab-finetuning

Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.

synthetic-sciences/openscience · 67 tokens

llm-integration

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.

yonatangross/orchestkit · 58 tokens