research

research is a skill for Claude Code from TorpedoD/claude-researcher. It costs 33 tokens per session (12,206 once invoked), scanned A, original, MIT.

A research workflow that scopes a question, gathers evidence, extracts supported claims, maps relationships, drafts sections, and publishes a report.

In plain words
What is it for?
Use it for structured research projects that need source collection, claim review, report writing, reproducible outputs, and optional publishing.
Why use it?
It keeps research organized and traceable by linking claims to sources and checking for missing evidence.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Good fit Use it for structured research projects that need source collection, claim review, report writing, reproducible outputs, and optional publishing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/torpedod/claude-researcher/research
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 TorpedoD/claude-researcher --skill research
Clone the repo
git clone --depth 1 https://github.com/TorpedoD/claude-researcher

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/torpedod/claude-researcher/research/github.svg)](https://agentmods.dev/skills/torpedod/claude-researcher/research)
Your own site
<a href="https://agentmods.dev/skills/torpedod/claude-researcher/research"><img src="https://agentmods.dev/badge/skills/torpedod/claude-researcher/research/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.

agentmods 80×15 button for research

Your own site · 80×15
<a href="https://agentmods.dev/skills/torpedod/claude-researcher/research"><img src="https://agentmods.dev/badge/skills/torpedod/claude-researcher/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00033 $0.12206
Opus 5 $0.00016 $0.06103
Sonnet 5 $0.00007 $0.02441
Haiku 4.5 $0.00003 $0.01221

Measured 10d ago against content hash 38f13eca1abf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

research scanned grade A with 1 finding 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 10d ago.

The scan reads SKILL.md. This mod also ships 17 executable files (scripts/build_graph.py, scripts/check_content_rules.py, scripts/gate1_validator.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(["python3", str(script), "--target=raw", str(target)], capture_output=True, text=True)
skills/research/SKILL.md · 999 lines

How it starts

The opening of the file, as written. The whole thing — 999 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Orchestrator

Accepts a freeform research request, plans scope, manages a 7-phase claim-based pipeline with 4 human checkpoint gates, and produces a polished, citation-rich research document. Every claim is traceable to its source, every gap is detected and addressed, and every run is reproducible and auditable.

The orchestrator coordinates collection, claim extraction, graph relationship enrichment, section brief synthesis, report composition, and optional publishing. output/report.md is the canonical final report; HTML, PDF, and QMD are publishing products rendered from it.

Claim Pipeline Contract

New runs use manifest.pipeline_contract_version = "claim_pipeline_v1" and these phases:

planning
→ collection
→ claim_extraction
→ graph_relationships
→ section_brief_synthesis
→ formatting
→ publishing

synthesis/claim_bank.json is the canonical research state. synthesis/raw_research.md is deprecated; if a prose diagnostic is needed, write synthesis/research_notes.md and keep it out of the main handoff.

A global file is tiny only when it is under 20KB or under 300 lines. Downstream agents must not read full claim_bank.json, full inventory.json, full graph files, or all section briefs unless the file qualifies as tiny. Otherwise they consume per-section slices.


Dependency install policy

The research pipeline must NEVER auto-install or auto-download these runtime dependencies:

  • crawl4ai (and its Playwright/browser runtime)
  • playwright / Playwright browsers
  • docling

If any of these are missing when the pipeline needs them, the skill/agent MUST:

  1. Detect the missing dependency.
  2. Emit a clear message naming the missing tool and the install command the user can run themselves (e.g., pipx install crawl4ai, pipx install docling, playwright install chromium).
  3. Stop the run — halt the phase with a non-zero exit. Do NOT proceed with a fallback collection mode.

Never execute pip install, pipx install, npm install, playwright install, crawl4ai-setup, crawl4ai-doctor --install, or any equivalent install command for these tools from within the pipeline.

Read the full file on GitHub · 999 lines

Files

What ships with it

55 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. 10d ago First seen · 999 lines · 33 tokens per session scan A 38f13eca1abf

Subscribe to this mod's changes

research is a skill published in the GitHub repository TorpedoD/claude-researcher (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 12,206 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

shogun-bloom-config

An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.

yohey-w/multi-agent-shogun · 86 tokens

shogun-model-list

A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.

yohey-w/multi-agent-shogun · 73 tokens

shogun-model-switch

A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.

yohey-w/multi-agent-shogun · 83 tokens

shogun-screenshot

A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.

yohey-w/multi-agent-shogun · 149 tokens

shogun-readme-sync

A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.

yohey-w/multi-agent-shogun · 66 tokens

shogun-agent-status

A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.

yohey-w/multi-agent-shogun · 98 tokens