monomind 2.7.12 → 2.7.14

package/packages/@monomind/cli/.claude/commands/monoes/monoclip.md

@@ -1,64 +0,0 @@
----
-name: monoes:monoclip
-description: Drive mono-clip's CLI sidecar (`mclip`) — read/write clipboard history and folders, or run its MCP stdio server
----
-
-# monoes monoclip
-
-Interact with **mono-clip** — a macOS menu-bar clipboard manager (Tauri + SvelteKit, app bundle `MonoClip.app`). The GUI app itself has **no CLI flags, deep-link scheme, or HTTP/IPC surface** — the only scriptable surface is a separate sidecar binary, **`mclip`**, that talks directly to the same SQLite database the GUI reads/writes (`~/.monoclip/monoclip.db`). `mclip` works whether or not the GUI is currently running, as long as the app has been launched at least once (so the DB exists).
-
-Not installed, or `mclip` not on PATH? Run `/monoes:install` first — after installing `mono-clip.app`, launch it once (its own startup hook symlinks `mclip` into `~/.local/bin/mclip`), then make sure `~/.local/bin` is on `PATH`.
-
-## Command tree
-
-```
-mclip list [--folder NAME] [--search QUERY] [--limit N]
-mclip add "text" [--folder NAME]
-mclip get <id>                     # prints raw content — pipeable, e.g. mclip get 7 | pbcopy
-mclip remove <id>
-mclip pin <id> / unpin <id>
-
-mclip folder list
-mclip folder add "Name" [--icon ICON --color COLOR]
-mclip folder remove "Name"
-
-mclip context                       # prints a canned AI-context block (for pasting into CLAUDE.md/.cursorrules)
-mclip mcp                           # starts a JSON-RPC-over-stdio MCP server (see below)
-```
-
-## Examples
-
-```bash
-# Save something to a folder, then recall it
-mclip add "ssh user@example.com" --folder "Snippets"
-mclip list --folder "Snippets"
-
-# Pull a clip straight into the system clipboard
-mclip get 12 | pbcopy
-
-# Pin an important clip so auto-cleanup never removes it
-mclip pin 12
-
-# Organize folders
-mclip folder add "Work" --icon "briefcase" --color "#4287f5"
-mclip folder list
-```
-
-## MCP server mode
-
-`mclip mcp` starts a hand-rolled JSON-RPC-over-stdio MCP server exposing: `list_clips`, `add_clip`, `get_clip`, `remove_clip`, `pin_clip`, `list_folders`, `create_folder`, `delete_folder`. To use it from an MCP client (e.g. Claude Desktop), register it as a stdio server with `"command": "mclip", "args": ["mcp"]` in that client's config — this is a separate integration path from shelling out to individual `mclip` subcommands above, and mostly relevant outside Claude Code itself (which already has direct Bash access to `mclip`).
-
-## What this app is (for context, not directly scriptable)
-
-Menu-bar-only clipboard manager: background watcher (polls every 300ms), auto-detects content type (text/url/email/color/code), multi-folder organization with per-folder global shortcuts (press hotkey → captures selection straight into that folder), a master shortcut (`⌘⇧V` default) toggling a floating panel, pin/soft-delete, image & file-path capture with thumbnails, search, configurable auto-cleanup retention (always keeps the last 10 Inbox items), local-only SQLite storage, no network/telemetry, self-update.
-
-## Gotchas (verified against source)
-
-- There is genuinely no way to control the running GUI app from outside it — no deep link (`monoclip://...`), no HTTP/Unix-socket API (that's on the project's own TODO list, not implemented), no `tauri-plugin-cli`. Don't invent flags for the main `monoclip`/`MonoClip.app` binary — everything scriptable lives in `mclip`.
-- `mclip` requires the app to have been launched at least once (so `~/.monoclip/monoclip.db` exists) — a fresh install with the GUI never opened will fail.
-- If `mclip` isn't found after install, it's almost always a `PATH` issue — the symlink at `~/.local/bin/mclip` is created automatically on first GUI launch (or via the GUI's Settings → "Install mclip CLI"), but `~/.local/bin` isn't always on `PATH` by default.
-
-## See Also
-
-- `/monoes:install` — install mono-clip if `MonoClip.app` / `mclip` aren't found
-- `../mono-clip/README.md` — Homebrew cask / build-from-source instructions

package/packages/@monomind/cli/.claude/commands/monoes/monotask.md

@@ -1,137 +0,0 @@
----
-name: monoes:monotask
-description: Drive the monotask CLI — a local-first, P2P kanban board (boards/columns/cards, spaces, GitHub/Linear/mail sync)
----
-
-# monoes monotask
-
-Interact with **monotask** — a Rust CLI (binary `monotask`, source at `../monotask`) for a local-first, P2P kanban board. Not installed? Run `/monoes:install` first.
-
-Given the user's request in `$ARGUMENTS`, pick the matching command(s) below and run them via Bash. When uncertain, run `monotask ai-help --json` — it introspects the live CLI definition, so it never drifts from the real command surface (unlike hand-written docs).
-
-## Model
-
-- Local-first: every board/column/card lives as an Automerge CRDT doc in SQLite in the OS data dir (Linux: `~/.local/share/monotask/`; **macOS: `~/Library/Application Support/monotask/`**; Windows: `%APPDATA%\monotask\`) — override with global `--data-dir`.
-- Identity is an Ed25519 keypair, auto-generated on first use (or `profile import-ssh-key`).
-- **Boards must belong to a Space** — `board create` requires `--space <SPACE_ID>`, so `space create` comes first.
-- The CLI does **not** sync between users by itself — that needs the `monotask sync` daemon or the desktop (Tauri) app running.
-- IDs are UUID v4 for everything except: Attachment IDs (6-char hex, `img:<id>`) and the human-readable card number (`<prefix>-<seq>`, display-only, not a valid ID for commands).
-- Pass `--json` on any command for structured output — recommended when scripting (e.g. piping through `jq`).
-
-## Command tree
-
-```
-monotask [--data-dir PATH] init | version | ai-help [--json] [--section commands|schemas|workflows|gotchas]
-
-monotask board create <title> --space SPACE_ID [--json]
-monotask board list|rename <id> <new-title>|delete <id> --space SPACE_ID|schema <id>|undo <id>|redo <id>
-
-monotask column create|list|rename|delete <board-id> [...]
-
-monotask card create <board-id> <col-id> <title> [--field NAME=VALUE ...] [--json]
-monotask card list <board-id> [--col ID] [--label L] [--where "FIELD_REF(=|!=|>|>=|<|<=|~)VALUE" ...]
-monotask card view|rename|delete|archive <board-id> <card-id>
-monotask card copy|move <board-id> <card-id> <target-col-id>
-monotask card set-description|set-cover|set-due-date <board-id> <card-id> <value>
-monotask card set-priority <board-id> <card-id> low|medium|high|none      # legacy string priority
-monotask card set-impact|set-effort <board-id> <card-id> 0-10             # priority = floor((impact+10-effort)/2)
-monotask card set-direct-priority <board-id> <card-id> [0-10] [--clear]
-monotask card clear-priority <board-id> <card-id>                        # clears impact+effort+direct_priority
-monotask card set-assignee <board-id> <card-id> <pubkey-hex|none>
-monotask card attach-image <board-id> <card-id> <file>                   # png/jpg/jpeg/gif/webp/svg
-monotask card list-attachments|save-attachment <board-id> <card-id> [<attachment-id>]
-monotask card mentions <board-id> <card-id>
-monotask card field-set <board-id> <card-id> <field-ref> <value>
-monotask card field-get|field-clear <board-id> <card-id> <field-ref>
-monotask card field-list <board-id> <card-id>
-monotask card upsert <board-id> <col-id> <title> --match-field REF --match-value V [--field NAME=V ...]
-monotask card label add|remove|list <board-id> <card-id> [label]
-monotask card comment add|list|delete|edit <board-id> <card-id> [...]
-monotask card subtask add <parent-board> <parent-card> <child-board> <col-id> <title> | list <board-id> <card-id>
-monotask card link add|list|remove <board-id> <card-id> <target-board> <target-card>
-monotask card prerequisite add|list|remove <board-id> <card-id> <prereq-board> <prereq-card>
-
-monotask checklist add <board-id> <card-id> <title>
-monotask checklist item-add|item-check|item-uncheck|item-delete <board-id> <card-id> <checklist-id> [item-id] [text]
-monotask checklist delete <board-id> <card-id> <checklist-id>
-
-monotask field create <board-id> <name> [--field-type text|number|date|select|multi_select|checkbox] [--option V ...] [--default-value V] [--auto-apply]
-monotask field list <board-id>
-monotask field rename <board-id> <field-ref> <new-name>
-monotask field delete|backfill <board-id> <field-ref>
-monotask field update <board-id> <field-ref> [--default-value V] [--auto-apply true|false]
-
-monotask space create <name>
-monotask space list|info <id>
-monotask space invite generate <id> | export <id> <output.space> | revoke <id>
-monotask space join <token-or-file>
-monotask space boards add|remove|list <space-id> [<board-id>]
-monotask space members list <space-id> | kick <space-id> <pubkey>
-
-monotask profile show | set-name <name> | set-avatar <path> | import-ssh-key [path]
-
-monotask github connect [token]        # prefer: echo "$TOKEN" | monotask github connect
-monotask github status | link <board-id> <owner> <repo> --done-col COL | unlink <board-id> | sync <board-id>
-
-monotask linear connect [token]        # prefer stdin
-monotask linear status | teams | projects <team-id>
-monotask linear link <board-id> --team ID --project ID [--done-col COL] | unlink <board-id> | sync <board-id>
-
-monotask mail gmail-connect --client-id ID [--no-wait]
-monotask mail outlook-connect --client-id ID [--tenant-id common] [--no-wait]
-monotask mail oauth-complete --provider gmail|outlook --code CODE     # finishes a --no-wait flow
-monotask mail status | disconnect gmail|outlook
-monotask mail link <board-id> [--provider both|gmail|outlook|imap] [--inbox-col COL] [--keep-last 2] [...]
-monotask mail imap-connect --host H --username U [--port 993] [--password P] [--folder INBOX]
-monotask mail imap-status | imap-disconnect | unlink <board-id> | sync <board-id>
-
-monotask app open <url>                # monotask://board/<id> or monotask://board/<id>/card/<id>
-
-monotask chat send <space-id> <text> | list <space-id> [--limit 50]
-
-monotask sync [--detach] [--stop] [--status] [--port 0] [--peer /ip4/.../tcp/... ...]
-```
-
-## Examples
-
-```bash
-# First-time setup: identity, space, board, column, card
-monotask profile set-name "Ada"
-SPACE=$(monotask space create "Personal" --json | jq -r .id)
-BOARD=$(monotask board create "Sprint 1" --space $SPACE --json | jq -r .id)
-TODO=$(monotask column create $BOARD "Todo" --json | jq -r .id)
-monotask card create $BOARD $TODO "Write onboarding docs" --json
-
-# Triage: list, prioritize, move
-monotask card list $BOARD --col $TODO --json
-monotask card set-impact $BOARD $CARD 8
-monotask card set-effort $BOARD $CARD 3
-monotask card move $BOARD $CARD $DOING_COL
-
-# Invite a teammate into a shared space
-monotask space invite export $SPACE team-invite.space
-# teammate runs: monotask space join team-invite.space
-
-# Wire up GitHub Issues sync
-echo "$GITHUB_TOKEN" | monotask github connect --json
-monotask github link $BOARD myorg myrepo --done-col $DONE_COL --json
-monotask github sync $BOARD --json
-
-# When unsure, ask the CLI itself
-monotask ai-help --section commands
-```
-
-## Gotchas (verified against source)
-
-- The clap `Parser` name is `monotaskcli` and `ai-help`'s own examples print that name — but invoke it as `monotask`. **This is only automatic for a source build that renames the binary during install** (per the tool's own README) — the Homebrew formula installs the raw binary as `monotaskcli` verbatim and does not create a `monotask` alias, and won't even auto-link it into `PATH` if the `monotask` cask (desktop app) is also installed. If `command -v monotask` comes up empty after `brew install monoes/tap/monotask`, symlink it manually: `ln -sf "$(brew --cellar)"/monotask/*/bin/monotaskcli "$(brew --prefix)/bin/monotask"`.
-- Exit codes: `0` success, `1` generic error, `2` not_found, `3` invalid_input, `4` io_error. **With `--json`, errors print to stdout** as `{"ok":false,"error":"...","kind":"..."}`; without it, errors go to stderr as plain text.
-- `card create` currently stamps a placeholder `"aaaa"` card-number prefix — known incomplete, per the tool's own gotchas.
-- `card view --json`'s `number` field is `{"prefix":..,"seq":..}`, not the display string.
-- `field backfill` only fills cards with **no** existing value — never overwrites a stale one.
-- Pipe secrets via stdin (`echo "$TOKEN" | monotask github connect`), not as a positional arg — avoids shell-history/`ps` exposure. Same for `linear connect` and `mail imap-connect --password`.
-- Real cross-machine sync requires `monotask sync` (a daemon, not automatic) or the desktop app — the CLI alone only mutates the local CRDT store.
-
-## See Also
-
-- `/monoes:install` — install monotask if the `monotask` binary isn't found
-- `../monotask/README.md`, `crates/monotask-cli/src/main.rs` — source of truth if `ai-help` output looks incomplete

package/packages/@monomind/cli/.claude/commands/monograph/README.md

@@ -1,102 +0,0 @@
----
-name: monograph:README
-description: Monograph skills index — build, search, and explore the knowledge graph across code, docs, and PDFs using real CLI subcommands and MCP tools
----
-
-# Monograph Commands
-
-Knowledge graph for code and documents — build, search, and explore relationships across your entire codebase and documentation.
-
-Alias: `monomind kg`
-
-## CLI Subcommands
-
-| Subcommand | Description |
-|---|---|
-| `monograph build` | Build knowledge graph from code + docs + PDFs |
-| `monograph wiki` | Scan all docs and PDFs into a searchable knowledge graph |
-| `monograph search` | Search the graph (BM25 / semantic / hybrid) |
-| `monograph stats` | Show node/edge counts and top concepts |
-| `monograph watch` | Watch for file changes and rebuild incrementally |
-
-## Quick Reference
-
-```bash
-# First-time build (code + all docs)
-npx monomind monograph build
-
-# Doc/wiki-focused build with Claude semantic extraction
-npx monomind monograph wiki --llm
-
-# Search
-npx monomind monograph search -q "authentication flow"
-npx monomind monograph search -q "pipeline" --mode semantic --label Section
-
-# Stats
-npx monomind monograph stats --top 20
-
-# Auto-rebuild on changes
-npx monomind monograph watch
-```
-
-## Files
-
-- [monograph-build.md](./monograph-build.md) — Full build (code + docs + PDFs)
-- [monograph-wiki.md](./monograph-wiki.md) — Doc/PDF-focused wiki build
-- [monograph-search.md](./monograph-search.md) — Search the knowledge graph
-- [monograph-stats.md](./monograph-stats.md) — Graph statistics
-- [monograph-watch.md](./monograph-watch.md) — Watch mode (incremental rebuild)
-
-## MCP Tools
-
-The monograph MCP tools (available in Claude Code via monomind MCP server) provide programmatic access to the graph without invoking the CLI:
-
-| Tool | Use When |
-|---|---|
-| `mcp__monomind__monograph_build` | Build/rebuild the graph |
-| `mcp__monomind__monograph_query` | BM25 keyword search; returns file + line number |
-| `mcp__monomind__monograph_suggest` | Start every task — returns relevant files ranked by task description |
-| `mcp__monomind__monograph_god_nodes` | Find high-centrality internal files |
-| `mcp__monomind__monograph_stats` | Node/edge counts |
-| `mcp__monomind__monograph_report` | Generate GRAPH_REPORT.md |
-| `mcp__monomind__monograph_shortest_path` | How two modules are connected |
-| `mcp__monomind__monograph_community` | Files forming a cohesive cluster |
-| `mcp__monomind__monograph_surprises` | Unexpected cross-community edges |
-| `mcp__monomind__monograph_export` | Export graph in various formats |
-| `mcp__monomind__monograph_watch` | Start watch mode via MCP |
-| `mcp__monomind__monograph_watch_stop` | Stop watch mode |
-| `mcp__monomind__monograph_context` | 360-degree view of a file: importers, imports, siblings |
-| `mcp__monomind__monograph_health` | Index staleness (commits behind HEAD) |
-
-## Node Types
-
-| Type | Description |
-|---|---|
-| `File` | Source code or document file |
-| `Section` | Markdown heading or document section |
-| `Function` | Code function or method |
-| `Class` | Code class or interface |
-| `Concept` | Extracted semantic concept |
-| `PDF` | PDF document chunk |
-
-## Edge Types
-
-| Relation | Meaning |
-|---|---|
-| `IMPORTS` | Code import dependency |
-| `DEFINES` | File defines symbol |
-| `TAGGED_AS` | Section tagged with concept |
-| `CO_OCCURS` | Concepts appear together |
-| `INFERRED` | Claude-extracted semantic relationship |
-| `DESCRIBES` / `CAUSES` / `PART_OF` | LLM-enriched semantic edges |
-
-## When to Use CLI vs MCP
-
-- **CLI** (`npx monomind monograph ...`) — One-time builds, manual searches, watching from terminal
-- **MCP tools** (`mcp__monomind__monograph_*`) — Claude Code integration, programmatic queries during tasks
-
-## See Also
-
-- `memory` — Vector memory storage (separate from graph)
-- `hooks intelligence` — Pattern learning
-- CLAUDE.md Knowledge Graph section — workflow guidance for multi-file tasks

package/packages/@monomind/cli/.claude/commands/monograph/monograph-build.md

@@ -1,79 +0,0 @@
----
-name: monograph:monograph-build
-description: Build the knowledge graph from code, docs (md/txt/rst), and PDFs — full index with optional Claude LLM semantic extraction
----
-
-# monograph build
-
-Build the knowledge graph from code, docs (md/txt/rst), and PDFs.
-
-## Usage
-
-```bash
-npx monomind monograph build [options]
-```
-
-## Options
-
-| Flag | Short | Type | Default | Description |
-|---|---|---|---|---|
-| `--path` | `-p` | string | cwd | Root path to index |
-| `--code-only` | — | boolean | `false` | Index only code files, skip documents |
-| `--llm` | — | boolean | `false` | Enable Claude semantic extraction (requires `ANTHROPIC_API_KEY`) |
-| `--llm-sections` | — | number | `50` | Max sections to enrich with LLM |
-| `--force` | `-f` | boolean | `false` | Force full rebuild even if index is fresh |
-
-## Examples
-
-```bash
-# Build code + all documents (default)
-npx monomind monograph build
-
-# Code only — skip docs and PDFs
-npx monomind monograph build --code-only
-
-# With Claude semantic extraction
-npx monomind monograph build --llm
-
-# Enrich up to 200 sections with Claude
-npx monomind monograph build --llm --llm-sections 200
-
-# Index a specific path
-npx monomind monograph build -p ./src
-
-# Force full rebuild
-npx monomind monograph build --force
-```
-
-## What Gets Indexed
-
-- **Code files** — functions, classes, imports, exports → structured graph nodes
-- **Markdown/MDX** — headings become `Section` nodes; links become edges
-- **Plain text / RST** — chunked into `Section` nodes
-- **PDFs** — text extracted and chunked into nodes
-
-Ignored directories: `node_modules`, `.git`, `dist`, `build`, `__pycache__`, `.cache`, `coverage`, `.monomind`, `vendor`, `target`
-
-## LLM Enrichment
-
-When `--llm` is passed and `ANTHROPIC_API_KEY` is set, Claude extracts typed semantic relationships between sections (e.g. `DESCRIBES`, `CAUSES`, `PART_OF`). These become `INFERRED` edges in the graph, enabling richer semantic search.
-
-## Output
-
-After build, the graph is stored at `.monomind/monograph.db`. Run `monograph stats` to see node/edge counts.
-
-## MCP Tool
-
-```javascript
-mcp__monomind__monograph_build({
-  path: "./",
-  codeOnly: false,
-  force: false
-})
-```
-
-## See Also
-
-- `monograph wiki` — doc/PDF-focused build with better output for documentation projects
-- `monograph stats` — view what was indexed
-- `monograph watch` — auto-rebuild on file changes

package/packages/@monomind/cli/.claude/commands/monograph/monograph-search.md

@@ -1,96 +0,0 @@
----
-name: monograph:monograph-search
-description: Search the knowledge graph using BM25 keyword search, semantic (embedding) search, or hybrid RRF-merged results — filter by node type (Section, Function, Class, File, Concept)
----
-
-# monograph search
-
-Search the knowledge graph using BM25 keyword search, semantic (embedding) search, or hybrid RRF-merged results.
-
-## Usage
-
-```bash
-npx monomind monograph search [options]
-```
-
-## Options
-
-| Flag | Short | Type | Default | Required | Description |
-|---|---|---|---|---|---|
-| `--query` | `-q` | string | — | yes | Search query text |
-| `--limit` | `-l` | number | `15` | no | Maximum results to return |
-| `--label` | — | string | — | no | Filter by node type: `Section`, `Function`, `Concept`, `File`, `Class` |
-| `--mode` | `-m` | string | `hybrid` | no | Search mode: `bm25`, `semantic`, `hybrid` |
-| `--path` | `-p` | string | cwd | no | Root path (location of `.monomind/monograph.db`) |
-
-## Examples
-
-```bash
-# Hybrid search (default) — best general-purpose
-npx monomind monograph search -q "authentication flow"
-
-# Keyword search — exact term matching
-npx monomind monograph search -q "JWT" --mode bm25
-
-# Semantic search — concept/meaning matching
-npx monomind monograph search -q "pipeline architecture" --mode semantic
-
-# Filter to doc sections only
-npx monomind monograph search -q "API design" --label Section
-
-# Find function definitions
-npx monomind monograph search -q "parseToken" --label Function
-
-# More results
-npx monomind monograph search -q "error handling" -l 30
-```
-
-## Search Modes
-
-| Mode | Algorithm | Best For |
-|---|---|---|
-| `hybrid` | RRF merge of BM25 + semantic | General purpose (recommended) |
-| `bm25` | Full-text BM25 ranking | Exact term matching, known symbol names |
-| `semantic` | Embedding cosine similarity | Conceptual queries, meaning-based lookup |
-
-Hybrid mode runs both BM25 and semantic internally, then merges with Reciprocal Rank Fusion (RRF).
-
-## Node Labels (--label filter)
-
-| Label | Represents |
-|---|---|
-| `File` | Source or document files |
-| `Section` | Markdown headings / doc sections |
-| `Function` | Code functions and methods |
-| `Class` | Code classes and interfaces |
-| `Concept` | Extracted semantic concepts |
-
-## Prerequisites
-
-Run `monograph build` or `monograph wiki` first to create the index.
-
-```bash
-# If you see "No knowledge graph found":
-npx monomind monograph build
-```
-
-## MCP Tool
-
-The MCP equivalent for Claude Code integration:
-
-```javascript
-mcp__monomind__monograph_query({
-  query: "authentication flow",
-  limit: 15,
-  label: "Section",
-  mode: "hybrid"
-})
-```
-
-Use `mcp__monomind__monograph_suggest` for task-oriented lookup that returns files ranked by relevance to your current work.
-
-## See Also
-
-- `monograph build` — build the graph index
-- `monograph stats` — see what's indexed
-- `monograph wiki` — doc-focused build

package/packages/@monomind/cli/.claude/commands/monograph/monograph-stats.md

@@ -1,53 +0,0 @@
----
-name: monograph:monograph-stats
-description: Show knowledge graph statistics — node counts by type, edge type breakdown, and top concepts by importance score
----
-
-# monograph stats
-
-Show knowledge graph statistics — node counts by type, edge type breakdown, and top concepts by importance.
-
-## Usage
-
-```bash
-npx monomind monograph stats [options]
-```
-
-## Options
-
-| Flag | Short | Type | Default | Description |
-|---|---|---|---|---|
-| `--path` | `-p` | string | cwd | Root path (location of `.monomind/monograph.db`) |
-| `--top` | — | number | `10` | Number of top concepts to show |
-
-## Examples
-
-```bash
-# Show graph statistics
-npx monomind monograph stats
-
-# Show top 20 concepts
-npx monomind monograph stats --top 20
-
-# Stats for a different project path
-npx monomind monograph stats -p ./other-project
-```
-
-## Output
-
-- **Nodes table** — count per node type (`File`, `Section`, `Function`, `Class`, `Concept`) with bar chart
-- **Edges table** — count per relation type (`IMPORTS`, `TAGGED_AS`, `CO_OCCURS`, `INFERRED`, etc.)
-- **Top N Concepts** — ranked by importance score and section count, shown with star ratings
-- **Summary line** — CO_OCCURS edge count and LLM-inferred edge count
-
-## MCP Tool
-
-```javascript
-mcp__monomind__monograph_stats()
-```
-
-## See Also
-
-- `monograph build` — build or rebuild the graph
-- `monograph search` — search across nodes
-- `monograph watch` — auto-rebuild on changes

package/packages/@monomind/cli/.claude/commands/monograph/monograph-watch.md

@@ -1,63 +0,0 @@
----
-name: monograph:monograph-watch
-description: Watch for file changes and incrementally rebuild the knowledge graph — keeps the graph fresh during active development or documentation writing
----
-
-# monograph watch
-
-Watch for file changes and incrementally rebuild the knowledge graph. Keeps the graph fresh during active development.
-
-## Usage
-
-```bash
-npx monomind monograph watch [options]
-```
-
-## Options
-
-| Flag | Short | Type | Default | Description |
-|---|---|---|---|---|
-| `--path` | `-p` | string | cwd | Root path to watch |
-| `--llm` | — | boolean | `false` | Enable LLM enrichment on each rebuild (requires `ANTHROPIC_API_KEY`) |
-
-## Examples
-
-```bash
-# Watch and rebuild on any file change
-npx monomind monograph watch
-
-# Watch with Claude semantic enrichment on each rebuild
-npx monomind monograph watch --llm
-
-# Watch a specific path
-npx monomind monograph watch -p ./docs
-```
-
-## Behavior
-
-- Runs until `Ctrl+C`
-- Detects changes to code files, markdown, text, RST, and PDFs
-- Triggers incremental rebuild (only changed files re-processed)
-- Outputs progress per phase as changes are detected
-
-## When to Use
-
-- During active documentation writing — graph stays current as you write
-- During refactoring — relationships update as imports change
-- CI environments — run in background to keep graph fresh for search queries
-
-## MCP Tools
-
-```javascript
-// Start watch via MCP
-mcp__monomind__monograph_watch({ path: "./" })
-
-// Stop watch via MCP
-mcp__monomind__monograph_watch_stop()
-```
-
-## See Also
-
-- `monograph build` — one-time full build
-- `monograph wiki` — doc-focused build
-- `monograph stats` — check current graph state