Collab Plugins — AI skill for Claude Code
Plugins from the Collaborator project — bring persistent AI judgment into your coding tools.
How to install Collab Plugins
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open collaborator-ai/collab-plugins and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Collab Plugins does
Plugins from the Collaborator project — bring persistent AI judgment into your coding tools.
Alternatives in AI
- Claudian — An Obsidian plugin that embeds Claude Code as an AI collaborator in your vault 7.7k ★
- Cumora — Where agent teams gather 3.2k ★
- Agentmemory — #1 Persistent memory for AI coding agents based on real-world benchmarks 1.9k ★
README
Collaborator
Reflection and ontology pipelines for collections of user notes. Turn any folder of markdown into actionable insight.
Skills
`/collaborator:initiative`
Run the Initiative pipeline against a notes collection — an Obsidian vault, a Seedvault collection, or any folder of markdown. The pipeline surveys your notes, infers your goals, identifies what's stuck, derives prioritized actions, synthesizes a cross-cutting brief, and proposes concrete work to do next.
**Pipeline:** Scan → Goals → Blockers → Actions → Brief → Proposals
Point it at a directory of markdown files and it produces:
- A goal tree grounded in your actual notes, not assumptions
- Blockers with severity ratings and meta-insights about patterns of change
- Prioritized actions scored by leverage and momentum
- A brief identifying the critical path — the one thing that unblocks everything else
- Proposals for work an AI agent can do immediately (research, drafts, analysis)
`/collaborator:ontology`
Run the Ontology pipeline against a notes collection. Extracts a three-layer knowledge structure that maps where your thinking is coherent and where unresolved tensions live.
**Pipeline:** Extract → Relations → Alignments → Synthesis
This is not a classical knowledge graph. The value is in the third layer:
- Entities — concepts, decisions, products, people, principles, goals, and problems extracted from your notes
- Relations — directed connections between entities (enables, blocks, contradicts, replaced, depends-on, etc.)
- Alignments — edges between relations that reveal whether two connections confirm each other (positive) or pull against each other (negative/tension)
The synthesis identifies:
- Load-bearing beliefs — the strongest positive alignments, where conviction is highest
- Active tensions — unresolved negative alignments that demand decisions
- Implications for action — where the ontology suggests you need to act
Inst
Related Skills
Soulcraft
Give your agent a soul that survives model swaps. Identity kit for persistent AI agents: character, memory, an
Claude Codex Collab
Two AI coding agents. One orchestrator. Zero API costs.
Fable Soul
A judgment layer for AI coding agents - make your AI think, verify, and communicate like a senior engineer
Hakim
A judgment layer for AI coding agents: smaller safe changes, native host integrations, and evidence-bound comp
Evidence Driven Engineering
A lightweight evidence-first engineering judgment framework (Agent Skill) for AI coding agents — debugging, co
Collab Synthesizer System
You are the AI Council Collaborative Synthesizer. You receive outputs from multiple AI agents that each worked
Related Agents
Rememora Triage
Use this agent when triaging issues, feature requests, or bugs for the Rememora project — a cross-agent persis
Workflow Collab Planner
Collaborative planner working within pre-allocated task ID ranges
Collab
Project-focused personal agent that preserves continuity across long work sessions.