anhe2021212-spec/Turritopsis

Shared project knowledge and handoff for coding agents across long-running projects

14Stars on the repository
6Mods indexed here, across every type
16d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

anhe2021212-spec/Turritopsis

Skill Codex

Design, review, or repair Turritopsis Stages for Agent memory systems, shared project memory, long-term recall, evidence ingestion, retrieval indexes, corrections, retention, and memory maintenance. Use when a project stores knowledge across sessions or agents and must keep raw evidence, canonical truth, summaries…

not rated 14 +1 16d ago A 74 tokens original MIT

anhe2021212-spec/Turritopsis

Skill Codex

Design, review, or repair Turritopsis Stages for a PWA or web interface that is a person's first-class entry into an Agent or service. Use for interaction contracts, source-of-truth boundaries, browser state, offline and retry behavior, service-worker caches, responsive verification, privacy, deployment, and the…

not rated 14 +1 16d ago A 81 tokens original MIT

anhe2021212-spec/Turritopsis

Skill Codex

Scan and map a software project with the currently installed Agent, design durable project-specific Stages, validate and apply skeletons, retrieve only relevant truth, and maintain evidence-backed knowledge without replaying chats or sending repository evidence to a second LLM. Use when joining, resuming…

not rated 14 +1 16d ago A 77 tokens original MIT

anhe2021212-spec/Turritopsis

Skill Codex

Design, review, or repair Turritopsis Stages for a long-running Agent runtime with sessions, relays, schedulers, tools, queues, channels, recovery, and continuity constraints. Use when operators must distinguish live authority from mirrors, process health from functional health, ordinary service restarts from identity…

not rated 14 +1 16d ago A 82 tokens original MIT

anhe2021212-spec/Turritopsis

Skill Codex

Design, review, or repair Turritopsis Stages for a private or personal AI assistant, including human-assistant roles, consent and authority, proactive behavior, tool actions, relationship continuity, private channels, memory correction, visible explanations, and human direction. Use when the system's value depends on…

not rated 14 +1 16d ago A 83 tokens original MIT

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: