Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
Project hierarchy management — filesystem discovery, parent-child relationships, tagging, and layout orchestration
npx claudepluginhub mistakeknot/interagency-marketplace --plugin intertreeProject hierarchy management for Claude Code.
intertree discovers projects on your filesystem, maps parent-child relationships (monorepo → subprojects), applies classification tags, and orchestrates layout — the directory structure that makes a multi-project workspace navigable.
The /intertree:layout skill walks you through interactive project discovery: scan a directory tree, review what was found, classify projects by type, and register them in the hierarchy database.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install intertree
/intertree:layout
Or ask naturally:
"scan my projects directory and organize it"
"show the project hierarchy"
skills/
layout/SKILL.md Interactive discovery + classification workflow
server/src/
discovery.ts Filesystem tree walking (pure function)
signals.ts Signal gathering for classification (pure function)
Currently uses interkasten's MCP tools for hierarchy operations (interkasten_scan_preview, interkasten_set_project_parent, interkasten_set_project_tags, etc.). These will migrate to a dedicated intertree MCP server in a future release.
intertree was extracted from interkasten to separate the hierarchy concern (filesystem-level) from the Notion sync concern (cloud-level). The pure discovery and signal-gathering functions live here; the database-backed MCP tools remain in interkasten until the DaemonContext dependency is decoupled.
Reorganizes project structure by cleaning root clutter, creating logical folder hierarchies, and moving files to optimal locations. Tracks dependencies and fixes broken imports/paths. Use PROACTIVELY when project structure becomes unwieldy or needs architectural cleanup.
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Cognitive layer for Claude Code — code navigation, conversation recall, safety hooks, behavioral learning
Camada compilada de contexto multi-layer para Claude Code. Compila projetos desconhecidos em uma estrutura .first-plan/ com discovery por stack, reuse index invertido, reconciliação spec-código, git intelligence e estado vivo. Resolve re-implementação cega, phantom features, drift e cross-session amnesia em projetos complexos.
Maintain FILETREE.md — one-line description per file with content hashes for staleness detection.
Folder structure + collaboration protocol so AI sessions can resume project context after compaction or window switch. One brain/ folder, 5 core files (PROJECT/MAP/STATUS/DECISIONS/HANDOFF), and a topic taxonomy.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
[DEPRECATED — use intervoice] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervoice, which reads one global multi-register profile instead of per-project glob-routed files.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
Self-improving agent rig: codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, monitors its own docs, and surfaces conservative update drift. Orchestrates Claude, Codex, and Oracle through 6 agents, 52 commands, 19 skills, 0 MCP servers. Factory substrate: CXDB turn DAG, scenario bank with satisfaction scoring, evidence pipeline, agent capability policies. Companions: interspect, interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.
Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim