A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.
This repository also configures its own agents. See what crux tells them →
Skill Claude CodeCodex
Launch and manage the crux cockpit — the read-only browser GUI over a crux research vault (crux serve). This skill runs it beginning to finish: locate the vault, start the server fresh on localhost, verify it actually serves, and hand the user one clickable URL — plus status / stop / restart, and a setup-or-demo path…
Skill Claude Code
Write the Requirements Document for a crux node — the design detail that does not fit, and should not fit, inside a 400-word question or hypothesis. An RD is one immutable design document per node, living in rd/ beside the tree, linked from the node, outside the roll-up: the estimand and its bound, the probe ladder…
Skill Claude CodeCodex
A literature wiki for a crux research vault — Andrej Karpathy's LLM-wiki pattern applied to a crux project. The PI curates immutable sources under raw/; you (the agent) compile them into a persistent, interlinked wiki/ of background, prior methods, SOTA, baselines, datasets, and definitions, and draw on it to ask…
Skill Claude CodeCodex
An agentic research companion — a scientific-method lab notebook for a research program. Organize work as a tree of Questions (what we don't know) and falsifiable Hypotheses (testable leaves), each with pre-registered verifiables and findings; a deterministic engine derives verdicts, rolls them up, and trips a human…
Skill Claude CodeCodex
Evolve crux itself — add a capability or fix a recurring flaw in the crux tool, end to end: ideate → build → validate → ship. Turns a feature idea or a "crux keeps doing X" annoyance into a signed-off PRD, a tests-first implementation, a hard validation gate (selftest green · stdlib-only · existing vaults still load ·…
Skill Claude CodeCodex
Turn one crux anchor node and everything under it into a minimal, professional, self-contained HTML slide deck — the "here's what we found" update a research group gives — where every number on a slide traces to the vault — a hashed result file or a metrics address — and crux deck --verify can prove it still matches.…
Skill Claude CodeCodex
Set up a crux flight plan with the PI, in six acts, and write it to auto/ /plan.md — the anchor question and a falsifiable goal, the null (approved by the PI, proposed by crux-null), the pre-registered checks and their control (written by crux-verifiables against that approved null), the objective address read off the…
Skill Claude CodeCodex
Set up a literature search over a crux vault with the PI, in two asks and one approval, and write it to wiki/lit/ /scope.md — what the search is for, and the 3–8 papers the PI already trusts, which are what the citation crawl walks outward from. Spends its turns getting the seeds right rather than polishing prose…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: