research

research is an agent for Claude Code from TorpedoD/claude-researcher. It costs 23 tokens per session (376 once invoked), scanned A, original, MIT.

A research workflow coordinator that breaks research into seven phases, uses separate agents to collect and combine evidence, and keeps track of progress and research files.

In plain words
What is it for?
Use it to plan research, gather sources and claims, review progress at required user checkpoints, validate research files, and produce section briefs.
Why use it?
It gives a structured process for research tasks that need evidence, checkpoints, validation, and a record of what has been done.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Good fit Use it to plan research, gather sources and claims, review progress at required user checkpoints, validate research files, and produce section briefs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/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.

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/agents/torpedod/claude-researcher/research.svg)](https://agentmods.dev/agents/torpedod/claude-researcher/research)
Your own site
<a href="https://agentmods.dev/agents/torpedod/claude-researcher/research"><img src="https://agentmods.dev/badge/agents/torpedod/claude-researcher/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 376 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 $0.00023 $0.00376
Opus 5 $0.00012 $0.00188
Sonnet 5 $0.00005 $0.00075
Haiku 4.5 $0.00002 $0.00038

Measured 8d ago against content hash c5f3c2632235, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

research 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 8d 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.

agents/research.md · 38 lines

What it actually says

Behavior

  1. On activation, read ~/.claude/skills/research/SKILL.md for full pipeline instructions
  2. Follow the 7-phase claim-based pipeline exactly as documented in SKILL.md
  3. Manage manifest.json phase transitions using init_run.py functions
  4. Present checkpoint gates via AskUserQuestion per checkpoint_protocol.md
  5. Validate structured artifacts (plan.json, inventory.json, claim_bank.json, section briefs, formatter audit) using validate_artifact.py

Tool Usage

  • Read/Write/Edit: Manage pipeline files (scope.md, plan.json, manifest.json, run_log.md)
  • Bash: Run init_run.py, validate_artifact.py, quarto render, invoke graphify
  • Glob/Grep: Inspect evidence files, search for patterns
  • Agent: Spawn research-collector and research-synthesizer subagents
  • AskUserQuestion: Present checkpoint gates to user

Constraints

  • Never skip checkpoint gates -- all 4 are mandatory
  • Never proceed past a gate without user confirmation
  • Always update manifest.json phase_status at each transition
  • Always log significant actions to logs/run_log.md
  • No WebSearch or WebFetch -- all web access is via collector agent's crwl CLI
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. 8d ago First seen · 38 lines · 23 tokens per session scan A c5f3c2632235

Subscribe to this mod's changes

research is an agent published in the GitHub repository TorpedoD/claude-researcher (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 376 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.