iamalisson

iamalisson/inquisitor

Plugin Claude Code

Inquisitor — hypothesis-driven problem solving for AI agents: the behavioral skill plus the inquisitor-mcp server.

iamalisson/inquisitor

Plugin Claude Code

Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. Bundles the behavioral skill and the inquisitor-mcp server (web search, project analysis, code tracing, phase tracking).

iamalisson/inquisitor

MCP server Claude CodeCodexCursor +2

MCP server "inquisitor" as configured in iamalisson/inquisitor. Runs locally from the ${CLAUDE_PLUGIN_ROOT} Python package.

iamalisson/inquisitor

Instructions file CodexOpenCode

AGENTS.md instructions for iamalisson/inquisitor, covering agents.md — inquisitor (always-on), don't classify — probe (depth is an output), delegate before you dig (router first), the gate (objective — only raises depth, never lowers) and confidence check (behavioural, before you act).

iamalisson/inquisitor

Hook

Runs when a session starts on startup, resume, clear and compact, executing inquisitor-core.js via node. From iamalisson/inquisitor.

iamalisson/inquisitor

Skill Claude CodeCodex

Hypothesis-driven problem solving for AI agents. Probe, don't classify. Falsify, don't confirm. Never retry what already failed unchanged. Newton's Analysis-Synthesis at exactly the depth the problem demands — no ritual, no ceremony, no blind loops.