Turn Claude Code into a personal AI agent with persistent memory. Interactive setup, 9 skills, 8 hooks, role-agnostic. Verified against v2.1.220.
Skill Claude CodeCodex
Create one new skill end to end - asks about purpose, trigger phrases, tools and context, then writes .claude/skills/ /SKILL.md with valid frontmatter and registers it in CLAUDE.md. Use when user says "create a skill", "make a slash command for this", "turn this workflow into a skill", "new skill for X". Do NOT use…
Skill Claude CodeCodex
Close a work session - asks what was completed, what was learned and what comes next, then updates dashboard, todo, learnings, errors and writes memory/daily/YYYY-MM-DD.md. Use when user says "end session", "wrap up", "I'm done for today", "save progress", "let's close", "log this session". Do NOT use for a week-level…
Skill Claude CodeCodex
Add one new capability to an existing ALBA setup - skill, hook, rule, slash command or MCP integration - interactively, then wire it into CLAUDE.md and settings.json. Use when user says "add a skill", "add a hook", "I want a rule for X", "connect Trello/Gmail/Linear", "extend my agent", "can ALBA also do X". Do NOT…
Skill Claude CodeCodex
Cross-session pattern analysis - reads recent daily logs, errors and learnings to surface recurring problems, then proposes rules, skills or hooks with evidence. Runs in a forked subagent. Use when user says "reflect", "find patterns", "what keeps going wrong", "how can I improve my workflow", "analyze my sessions"…
Skill Claude CodeCodex
Structured web research with cited sources and confidence levels; runs in a forked subagent, quick (3-5 sources) or deep (8-10 sources, saved to memory/research/). Use when user says "research X", "look into X", "find information about X", "investigate X", "what's the state of X". Do NOT use for questions answerable…
Skill Claude CodeCodex
One-time bootstrap of a personal ALBA agent system - asks 7 discovery questions, then generates CLAUDE.md, the memory tree, skills, hooks, rules and .claude/settings.json. Use when the user explicitly types /setup, has just cloned ALBA, and has no CLAUDE.md yet. Do NOT use to add a single skill, hook or rule to a…
Skill Claude CodeCodex
Open a work session - reads dashboard and todo, checks for a resumable daily log, prints today's top priorities in under 10 lines. Use when user says "start", "let's begin", "good morning", "what am I working on today", "open the session", or types /start at the top of a session. Do NOT use for a mid-session check…
Skill Claude CodeCodex
Read-only snapshot of the current focus, active/completed task counts and blockers, in under 8 lines. Use when user says "status", "where are we", "what's left", "any blockers", "quick check", or wants a mid-session pulse without changing anything. Do NOT use to open a session (use /start, which also looks for a…
Skill Claude CodeCodex
Weekly retrospective - gathers this week's daily logs, learnings and errors, asks 3 questions, saves memory/state/weekly-reviews/YYYY-Www.md and refreshes the dashboard priorities. Use when user says "weekly review", "review my week", "how did this week go", "plan next week", "wrap up the week", or it is the end of…
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: