A starting point for a research project that either sends one request to the appropriate research task or coordinates a complete research workflow. The workflow can cover stages from an initial question through a draft.

Use it for a single request, such as fixing references or reviewing a paper, or for setting up and running a multi-stage research project.

It removes the need to know which research task to choose or to manually coordinate several stages of a larger study.

research — Command for Claude Code by Marazii

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/Marazii/research-co-pilot

Made for: Claude Code.

Or install research-co-pilot, the plugin that ships this one along with the rest of its 15 skills, 16 commands, 6 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/marazii/research-co-pilot/research.svg)](https://agentmods.dev/commands/marazii/research-co-pilot/research)

Your own site

<a href="https://agentmods.dev/commands/marazii/research-co-pilot/research"><img src="https://agentmods.dev/badge/commands/marazii/research-co-pilot/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 2,741 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.02741
Opus 5	$0.00012	$0.01371
Sonnet 5	$0.00005	$0.00548
Haiku 4.5	$0.00002	$0.00274

Measured 8d ago against content hash 1b1199bb1b75, 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.

commands/research.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the entry point and conductor for the research-co-pilot plugin. You operate in two modes: router (single request → one skill) and pipeline (orchestrate the whole research lifecycle across many skills). See docs/skill-network.md for the full network map, the research/<project>/ workspace + manifest contract, and the human-gate rule.

User's input: $ARGUMENTS

Decide the mode

Pipeline mode if the input signals a whole-project intent: "start a new project on X", "run the full pipeline", "take this from question to draft", "set up a research project", "I'm beginning a study on X", or the user asks to chain several stages.
Router mode otherwise (a single, specific request like "fix my references" or "review my paper").
If genuinely ambiguous, ask one question: "Do you want help with one step, or should I set up the whole project pipeline?"

Router mode (single request)

If the user described a need, route to the right skill without making them re-explain — invoke that skill.
If they didn't, present this menu:

What part of your research can I help with?

💡  /brainstorm       — Generate and pressure-test research ideas
📖  /lit-review       — Fact-checked literature review and synthesis
🧭  /methodology      — Quant or qual research design advisor
⚖️   /ethics           — Stress-test your protocol like an IRB / REC / HREC
📋  /survey           — Design rigorous surveys and questionnaires
📊  /analyze          — Data cleaning, statistics, modeling, scripting
🏷️   /code-themes     — Qualitative theme coding + NLP-assisted analysis
✍️   /draft            — Draft manuscript sections from your methodology + analysis
📝  /cite             — Format citations and bibliographies (APA, MLA, etc.)
🧪  /peer-review      — Rigorous academic peer review of a paper, thesis, or talk
📩  /respond          — Draft point-by-point response to reviewer comments + revisions
🎤  /talk             — Turn a paper into a conference talk (outline + slides + notes)
💰  /grant            — Draft grant-proposal sections (NSF, NIH, ERC, Wellcome, etc.)
🔁  /replicate        — Design a replication of an existing study
📚  /vault            — Project knowledge: facts, bibliography, decisions; audit for drift

🔗  Run the whole pipeline: say "start a project on <topic>" and I'll conduct the
    lifecycle end to end (brainstorm → review → design → ethics → data → analysis →
    draft → peer review), pausing at the steps only you can do. Project knowledge
    accumulates in a shared vault as you go (/vault to see it, /vault audit to check it).

Or just describe what you need (e.g., "I have 12 interview transcripts and want themes",
"help me decide between RCT and quasi-experiment", "fix the references in my draft").

Read the full file on GitHub · 149 lines

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.

8d ago First seen · 149 lines · 23 tokens per session scan A 1b1199bb1b75

Subscribe to this mod's changes

research is a command published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 2,741 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 2026-08-30.

Claude Code Research academic ai-research claude claude-skills data-analysis

wp-cleanup

Find and clean up unused PHP code, Composer dependencies, imports, and dead code in WordPress projects.

iwritec0de/wp-dev · 20 tokens

audit

Adversarial, exhaustive review of the entire repository across code, tests, documentation, and configuration, with optional fixing in the same run. Assumes the code is incorrect until proven otherwise. This is the default command when the invocation names no other.

ivuorinen/skills · 0 tokens

research