Co-Researcher v2.1 — Claude Code · Gemini CLI · OpenAI Codex · OpenCode
Fifteen research protocols — literature review, critical analysis, hypothesis testing, systematic review — installed natively into your AI CLI.
The problem
It invents citations that sound plausible. It conflates correlation with causation. It calls a literature review "comprehensive" after sampling a fraction of the field. These aren't random hallucinations — they're method gaps. The model was never given the protocol that trained researchers follow.
The principle
Systemic Honesty
Co-Researcher's core rule: accuracy over output count. Every skill requires the agent to flag uncertainty, refuse unverified sources, and distinguish what the evidence shows from what you might wish it showed. When it doesn't know, it says so.
Research skills
Each skill is a defined workflow. Type the command, and the agent follows the same steps a trained researcher takes: systematic search, explicit coding, verified citations, uncertainty quantification.
Research Orchestration
Intelligent multi-agent coordination. Analyzes your question, selects the right agents, executes a phased research plan.
Critical Analysis
Fallacy detection, bias identification, contradictory evidence handling. Evaluates the strength of an argument, not just its surface coherence.
Literature Review
Systematic search, citation chaining, hallucination detection, gap analysis. Refuses to cite sources it cannot verify.
Hypothesis Testing
Variable mapping, falsification criteria, experimental controls. Distinguishes testable claims from unfalsifiable ones.
Quantitative Analysis
Statistical method selection, effect size interpretation, Simpson's paradox detection, power analysis.
Qualitative Research
Thematic analysis, coding strategy, leading-question detection, theoretical saturation assessment.
Peer Review
Manuscript critique with methodological rigor scoring. Structures feedback the way a journal reviewer would.
Ethics Review
IRB compliance assessment, participant privacy risk, dual-use research concerns.
Systematic Review
PRISMA-standard protocol, inclusion/exclusion criteria, Risk of Bias assessment.
Research Synthesis
Narrative synthesis with explicit uncertainty quantification. Distinguishes strong evidence from weak consensus.
Research Methodology
Design selection and validation — matches your research question to appropriate methods, sampling strategies, and validity controls.
Grant Writing
Funding strategy, Specific Aims development, alignment with agency priorities.
Lateral Thinking
Cross-domain analogies, constraint satisfaction, first-principles reasoning for novel research problems.
Academic Writing
Eliminates AI-isms from research prose — hedging, passive-voice defaults, vague transitions. Produces writing that reads like a human expert wrote it.
Multi-Source Investigation
Triangulates complex claims across three or more independent sources. Checks credibility, funding sources, and institutional bias for every source it cites.
Telling a model "don't fabricate" improves outputs until the task gets hard. Co-Researcher embeds verification into the method itself — at search, at citation, at synthesis — so the constraint doesn't depend on a single instruction holding under pressure.
Never fabricate a citation. If a source cannot be verified, say so.
Distinguish what the evidence shows from what it suggests.
Quantify uncertainty — "likely," "insufficient evidence," "conflicting findings."
Refuse to produce a "comprehensive" review when coverage is partial.
Flag methodological limits before presenting conclusions.
Installation
Co-Researcher installs as a native plugin or extension. Your existing agent gets research-grade method added to its repertoire.
Claude Code
/plugin marketplace add poemswe/co-researcher
Gemini CLI
gemini extension install https://github.com/poemswe/co-researcher
OpenAI Codex
Tell Codex: "Fetch and follow https://raw.githubusercontent.com/poemswe/co-researcher/main/.codex/INSTALL.md"
From source
git clone github.com/poemswe/co-researcher
After installing, run /using-co-researcher to orient Claude to all available skills.
Claude and Codex scored across literature search, critical analysis, quantitative reasoning, and research design. Not demos — actual outputs with full rubric breakdowns.