Instructions file CodexOpenCode
AGENTS.md instructions for LamantinAI/kaeru, covering agents.md — kaeru, part one — working agreements, git: commit locally in a batch, push squashed, commit authorship and pull requests.
Instructions file
Claude Code instructions for LamantinAI/kaeru, a project described as: Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
Command
kaeru re-entry ritual — load process state + epistemic state for an initiative.
Command
Capture a lesson learnt as durable archival memory in kaeru.
Command
Recall what kaeru knows about a topic — search then drill the top hit.
Skill Claude CodeCodex
Cognitive memory layer for LLM agents — typed graph + bi-temporal substrate + curator API, reached through the kaeru MCP server. Use when the user wants to capture, recall, reason, or trace persistent thoughts across sessions; when re-entering a multi-session project; or when the user explicitly asks to "remember"…
Skill Claude CodeCodex
Use this skill when adding a new feature vertical to this template — a domain aggregate with its port, repository, application service, DTOs, endpoint, and tests. Trigger it for requests like "add an endpoint", "add a new entity", "build the X feature", or "wire up a new service".
Skill Claude CodeCodex
Use this skill when asked to initialize, bootstrap, or set up a repository created from the Mayak template so local development is ready. Trigger it for requests like "initialize the project", "bootstrap this repo", "set up the project locally", or "prepare the repo for work".
Hook Claude Code
Runs before the agent uses a tool for Edit, Write and MultiEdit tool calls, executing pre-edit-guard.sh. From LamantinAI/mayak.
Settings file Claude Code
Agent settings declaring 1 hook event (PreToolUse) and 37 allowed tools.
Instructions file CodexOpenCode
Instructions for LamantinAI/mayak, covering agents.md, quick start, common commands, validation and testing.
Instructions file
Instructions for LamantinAI/mayak, covering claude.md, quick start, common commands, validation and testing.