memx
01Skill Claude CodeCodex
Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.
407 3mo ago A 26 tokens
original MIT
Skill Claude CodeCodex
Install the official Waggle plugin locally for Codex from the latest stable Abhigyan-Shekhar/Waggle-mcp GitHub Release. Use for explicit requests such as "Install Waggle", "Set up Waggle", "Install Waggle for Codex", or "Enable Waggle". Do not use for Waggle operation, repair, updates, configuration, or memory…
37 yesterday A 84 tokens
original Apache-2.0
Skill Claude CodeCodex
Checkpoint durable decisions, fixes, constraints, results, and open next steps from the current Codex task into scoped Waggle project memory.
37 yesterday A 32 tokens
copy · 100% Apache-2.0
Skill Claude CodeCodex
Use Waggle automatically as portable, local project memory during meaningful coding work; retrieve prior decisions and constraints, then store only durable outcomes.
37 yesterday A 31 tokens
copy · 100% Apache-2.0
analyze
05Skill Claude CodeCodex
Analyze a large file (CSV, Excel, PDF, JSON, code) and return a token-efficient summary. Instead of reading thousands of rows or pages, get schema + statistics + sample in under 500 tokens. Use when user mentions a file path, asks to analyze data, pastes many rows, or references a CSV/Excel/PDF/JSON file.
29 13d ago A 76 tokens
original MIT
checkpoint
06Skill Claude CodeCodex
Save the current session to TokenMizer graph memory. Creates a persistent checkpoint with all tasks, decisions, files, and errors — resumable in any future session. Use when user says "save", "checkpoint", "remember this", "I'm done for today", or session is getting long.
29 13d ago A 61 tokens
original MIT
resume
07Skill Claude CodeCodex
Load a previous session from TokenMizer graph memory. Returns a compact context block (100-600 tokens) covering goals, completed work, decisions, open tasks, and files. Inject this as system context to continue exactly where you left off. Use when user says "resume", "continue from last time", "load my project", "what…
29 13d ago A 86 tokens
original MIT
seed-reader
08Skill Claude CodeCodex
Render evaluation run reports and interpret gate metrics. Use for: reading eval JSONL logs as a markdown report (uv run python -m eval.seedreader --run-id ID), listing available run-ids, scoring the GO/STOP/ITERATE gate decision, understanding what each metric means, diagnosing why an arm won or lost, reviewing probe…
12 11d ago A 128 tokens
original MIT
Skill Claude CodeCodex
A set of instructions for flushing a Cognee queue by first reading its queue file.
2 3mo ago B 134 tokens