by assafkip · Claude Skill · ★ 119
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Research Mode for Claude Code Anti-hallucination toggle for Claude Code. Activates citation constraints from Anthropic's documentation that force Claude to cite sources, say "I don't know" when unsure, and ground responses in direct quotes. Using Kipi Founder OS? Research mode is already built into kipi-core. Just run . No extra install needed. Install Works in Claude Code CLI, the macOS desktop app, and the VS Code extension. Open Claude Code and run these two commands: Step 1 -- Add the marketplace: Step 2 -- Install the plugin: That's it. To confirm it installed, run and check that appears in your list. Alternative -- install as a standalone skill: If you prefer not to use the plugin system, clone this repo and copy the file into your project's directory. Use Or with a topic: Say "exit research mode" to turn it off. What it does Three constraints activate simultaneously: Say "I don't know" -- no guessing, no inferring. If there's no credible source, Claude says so. Cite e
| Stars | 119 |
| Forks | 12 |
| Category | Claude Skill |
| Quality Score | 67.2613246894075/100 |
| Open Issues | 2 |
| Last Updated | 2026-04-16 |
| Created | 2026-03-23 |
| Platforms | claude-code |
| Est. Tokens | ~1k |
These tools work well together with research-mode for enhanced workflows:
Looking for a research-mode alternative? If you're comparing research-mode with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Pure instruction-pack skill wrapping Ai2's Asta MCP server (Semantic Scholar). Intent-to-tool routing, safe de
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
Explore other popular claude skill tools:
research-mode is Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.. It is categorized as a Claude Skill with 119 GitHub stars.
You can find installation instructions and usage details in the research-mode GitHub repository at github.com/assafkip/research-mode. The project has 119 stars and 12 forks, indicating an active community.
The top alternatives to research-mode on Agent Skills Hub include adversarial-spec, smart-ralph, claude-emporium. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.