By ribeirogab
Memex slash commands: spec, learn, sweep, review-spec. Wraps the memex agent-memory workflow as Claude Code plugin commands.
Investigate a topic in the project and save what you learn to the vault
External evaluator that reviews a spec against the constitution and the vault, flagging violations, vagueness, and duplication
Turn the current conversation into a spec using the memex-brainstorming flow
Manual garbage-collection pass over the vault — orphans, broken links, stale specs, uncited rules
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Analyze the vault for missing related: frontmatter cross-links and present suggestions interactively. Conservative: only surfaces high-evidence (wikilink already in body) and medium-evidence (filepath/title in body, or shared title/H2 terms) candidates. Never edits without explicit per-item user confirmation. Use when the user asks to find missing related: links in the vault, when /memex:sweep flags an isolated spec, or as part of the After-completing-a-spec reflection.
Search the vault for context on a topic
Use when you have a spec or requirements for a multi-step task, before touching code
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An externalized, navigable project memory for coding agents — Claude Code, Codex, Cursor, OpenCode, Gemini CLI, Aider, and any other tool that supports the open agent skills standard. memex is a single skill that idempotently scaffolds a .vault/ knowledge vault, an AGENTS.md (with a CLAUDE.md symlink for back-compat), spec/plan/task templates, and a set of bundled companion skills + slash commands into any repository — then dogfoods that same memory on its own development.
Personal project, solo maintenance, best-effort, no SLA. Published so anyone can install it.
npx skills add ribeirogab/memex --skill memex
Point an agent at any repo where you want the memex installed:
"Audit the memex in this repo and scaffold whatever is missing."
The skill is audit-first, autonomous-fix, and safe to re-run. After the first run the repo has a working .vault/ vault, the bundled memex-* companion skills, the /memex:* slash commands, and an AGENTS.md — all dogfood-tested by the memex's own Phase-5 validator.
Source: skills/memex/SKILL.md
memex/
├── skills/memex/ # the skill: SKILL.md, references/, scaffold/, scripts/
├── plugins/memex/ # Claude Code plugin — the /memex:* slash commands
├── .claude-plugin/ # marketplace manifest
├── LICENSE # MIT
├── NOTICE.md # attribution for vendored validator scripts
├── CONTRIBUTING.md
├── CODE_OF_CONDUCT.md
├── SECURITY.md
└── README.md
The repository also contains .agents/, .claude/, and .vault/ — local dirs used to dogfood memex on its own development (the bundled companion skills, the per-agent symlinks, and the maintainer's knowledge vault). They are not what npx skills add installs.
This repository's original work is licensed under the MIT License. The vendored validator scripts under skills/memex/scripts/ are Apache-2.0; see NOTICE.md for attribution.
Pull requests welcome — see CONTRIBUTING.md for scope, the quality bar, and the per-PR checklist. By participating, you agree to the Code of Conduct. Security concerns go to SECURITY.md.
npx claudepluginhub ribeirogab/memex --plugin memexHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development