@kevin0181/memoc 1.4.6 → 1.4.10

package/README.md

@@ -1,335 +1,335 @@
-# memoc
-
-> AI agents forget everything when a session ends. memoc gives them a structured memory system so they can pick up exactly where they left off — without you repeating yourself.
-
-Scaffolds a Markdown-based project memory into any codebase. Works with Claude Code, Codex, Cursor, Windsurf, GitHub Copilot, and Gemini CLI.
-
-## Quick Start
-
-```bash
-npx @kevin0181/memoc init
-
-# Upgrade memoc in this project without deleting existing memory
-npx @kevin0181/memoc@latest upgrade
-```
-
-Run inside your project directory. Detects your stack automatically and generates everything agents need.
-
-`init` also creates project-local PATH helpers so agents can keep using memoc even when the global/npm bin is not on PATH.
-
-```bash
-# PowerShell
-. .\.memoc\env.ps1
-
-# sh/bash
-. ./.memoc/env.sh
-```
-
-Agents are instructed to use the project-local wrapper if PATH fails:
-
-```bash
-# Windows
-.\.memoc\bin\memoc.cmd summary
-
-# macOS / Linux
-.memoc/bin/memoc summary
-```
-
----
-
-## Ask An Agent To Install
-
-If you are giving this repo or npm package to an AI coding agent, use a prompt like:
-
-```text
-Install memoc in this project and run init.
-Use the npm package only. Run `npx @kevin0181/memoc@latest init`
-from this project's root. Do not clone the GitHub repository into this project.
-If npm/npx is missing, stop and ask the user to install Node.js LTS with npm first.
-After init, verify with the project-local wrapper:
-Windows: .\.memoc\bin\memoc.cmd summary
-macOS/Linux: .memoc/bin/memoc summary
-```
-
-Agent install checklist:
-
-1. Run `node --version` and `npm --version`. If either fails, ask the user to install Node.js LTS with npm first.
-2. Run `npx @kevin0181/memoc@latest init` from the target project root.
-3. Do not clone this GitHub repository into the target project. Do not download the repo ZIP as an installer.
-4. `.claude/settings.json` is intentionally generated for the Claude Code Stop hook; keep or commit it only if the project wants that hook.
-5. After init, do not depend on global PATH. Use the project-local wrapper when needed:
-   - Windows: `.\.memoc\bin\memoc.cmd <command>`
-   - macOS/Linux: `.memoc/bin/memoc <command>`
-
-If `node --version` or `npm --version` fails, memoc cannot be installed yet. Install Node.js LTS with npm first, then repeat the steps above.
-
----
-
-## The Problem
-
-Every new AI session starts cold. You re-explain the project, the decisions already made, what's done and what isn't. The agent rediscovers what the last one figured out.
-
-memoc installs a memory structure that agents read at session start, update as they work, and hand off to the next session — automatically.
-
----
-
-## Commands
-
-```bash
-# First-time setup — scaffold memory, detect stack, install Claude Code hook
-npx @kevin0181/memoc init
-
-# Re-scan project and refresh managed sections
-npx @kevin0181/memoc update
-
-# Shared repo activity tracking
-npx @kevin0181/memoc actor
-npx @kevin0181/memoc actor set neneee
-npx @kevin0181/memoc work "Auth refresh fix" --from-git
-npx @kevin0181/memoc activity
-npx @kevin0181/memoc activity --write
-npx @kevin0181/memoc doctor
-
-# Print current status in ~10 lines
-npx @kevin0181/memoc summary
-
-# Search memory/agent docs first (token-efficient)
-npx @kevin0181/memoc search "auth"
-npx @kevin0181/memoc search "auth" --snippets --limit 5
-
-# Search project source/text files only when memory is not enough
-npx @kevin0181/memoc grep "GetParticles"
-npx @kevin0181/memoc grep "GetParticles" --snippets --limit 5
-
-# Create raw/source records and durable wiki topic notes
-npx @kevin0181/memoc ingest path/to/source.md
-npx @kevin0181/memoc ingest https://example.com/spec
-npx @kevin0181/memoc note "Auth flow comparison"
-npx @kevin0181/memoc lint-wiki
-
-# Estimate token cost of current memory files
-npx @kevin0181/memoc tokens
-
-# Archive and compact an oversized startup summary
-npx @kevin0181/memoc trim-summary
-
-# Compact oversized memoc files and refresh generated indexes
-npx @kevin0181/memoc compress
-
-# Add the same protocol to another agent's entry file
-npx @kevin0181/memoc add cursor
-npx @kevin0181/memoc add windsurf
-npx @kevin0181/memoc add copilot
-npx @kevin0181/memoc add gemini
-```
-
----
-
-## Upgrade Existing Projects
-
-memoc never auto-updates itself. Upgrade only when you choose to run:
-
-```bash
-npx @kevin0181/memoc@latest upgrade
-```
-
-Run it from the project root. It preserves existing project memory, including:
-
-- `.memoc/session-summary.md`
-- `.memoc/02-current-project-state.md` human-written sections
-- `.memoc/03-decisions.md`
-- `.memoc/04-handoff.md`
-- `.memoc/06-project-rules.md`
-- Legacy `.memoc/log.md` if present
-- Legacy `.memoc/systems/` if present (moved to `.memoc/raw/legacy-systems/` on upgrade)
-- `.memoc/wiki/`
-
-It refreshes the managed blocks, project-local wrappers, runtime copy, PATH helpers, and memoc-owned protocol templates. User-owned memory files such as `session-summary.md`, `03-decisions.md`, `04-handoff.md`, `06-project-rules.md`, and wiki topic/source pages are preserved. Upgrade also runs the `trim-summary` compaction pass so startup memory stays small. If `memoc` is not on PATH after upgrading, keep using:
-
-```bash
-# Windows
-.\.memoc\bin\memoc.cmd summary
-
-# macOS / Linux
-.memoc/bin/memoc summary
-```
-
----
-
-## What Gets Created
-
-```
-CLAUDE.md                                    ← Claude Code entry point (auto-loaded)
-AGENTS.md                                    ← Codex entry point (auto-loaded)
-llms.txt                                     ← LLM-facing project map
-.claude/settings.json                        ← Claude Code Stop hook
-
-.memoc/
-  bin/memoc                                  ← project-local wrapper for PATH fallback
-  env.ps1 · env.sh                           ← shell helpers that prepend .memoc/bin to PATH
-  session-summary.md                         ← Only required startup read (~150 tokens)
-  02-current-project-state.md               ← Status, open tasks, commands
-  03-decisions.md                            ← Durable decision log
-  04-handoff.md                              ← Resume context, verified/unverified
-  06-project-rules.md                        ← User preferences
-  activity.md                                ← Short shared activity index
-  actors/                                    ← Actor profiles for shared repos
-  worklog/                                   ← Per-actor work records to reduce conflicts
-  raw/                                       ← Immutable source material, not a startup read
-  wiki/project/                              ← Project implementation wiki
-  wiki/knowledge/                            ← Source-backed knowledge wiki
-
-skills/project-memory-maintainer/SKILL.md   ← Wiki operations guide
-```
-
----
-
-## How Agents Use It
-
-Every entry file (`CLAUDE.md`, `AGENTS.md`, `.cursorrules`, etc.) gets the same protocol injected as a managed block:
-
-```
-## Session Start
-- [ ] Read `.memoc/session-summary.md`
-- [ ] `.pending` exists? → review changed files → update memory if needed → delete it
-- [ ] If `memoc` is not found, use the project-local wrapper.
-
-## Before Opening More Files
-- [ ] Run `memoc search "<query>"` first
-- [ ] Open on demand: `02` status · `04` resume · `06` rules · `llms.txt` map
-- [ ] Use `memoc grep "<query>"` only when memory is not enough.
-- [ ] For durable source/wiki work, use `memoc ingest`, `memoc note`, and `memoc lint-wiki`.
-- [ ] In shared repos, record meaningful work with `memoc work "<title>"`.
-- [ ] Keep output small: `summary`, `search --limit`, `search --snippets`
-
-## Before Finishing _(update only applicable files; skip Q&A / throwaway exploration)_
-- [ ] Code/config/deps changed → `02` (version, commands list, Last synced) + `session-summary.md` (status, changed, open tasks)
-- [ ] Decision made → `03-decisions.md` (what & why) + `02`
-- [ ] Work incomplete or risky → `04-handoff.md` (verified commands, unverified items, next steps)
-- [ ] Rule/preference set → `06-project-rules.md`
-- [ ] Wiki/project-memory work → read `skills/project-memory-maintainer/SKILL.md`
-- [ ] Shared repo work → prefer `memoc work "<title>" --from-git`; run `memoc activity --write` only when regenerating indexes.
-- [ ] Keep `session-summary.md` replace-only; completed work belongs in actor worklogs.
-```
-
-The checklist tells agents exactly when to update, which file to update, and what to record — so nothing gets missed.
-
----
-
-## Token Efficiency
-
-Startup cost is kept minimal by design.
-
-| What loads | Tokens |
-|---|---|
-| `CLAUDE.md` (managed block only) | ~280 |
-| `session-summary.md` (only required read) | ~150 |
-| **Total startup** | **~430** |
-
-Everything else is on-demand. Use `memoc tokens` to see the live breakdown for your project.
-
-`session-summary.md` is a replace-only startup snapshot, not a timeline. If it grows beyond the warning threshold, run `memoc compress` or `memoc trim-summary`; completed history belongs in `.memoc/worklog/<actor>/YYYY-MM/`, and unfinished/risky resume detail belongs in `.memoc/04-handoff.md`.
-
----
-
-## Claude Code Auto-Detection
-
-`init` installs a lightweight `Stop` hook in `.claude/settings.json`. After each Claude Code response it checks:
-
-```bash
-git status --porcelain
-```
-
-If uncommitted changes exist, it writes `.memoc/.pending` with a timestamp and the changed filenames. At the next session start, Claude reads `.pending` and decides whether to update memory — then deletes the file.
-
-No extra setup. Add `.memoc/.pending` to `.gitignore` to keep it untracked.
-
----
-
-## Multi-Agent Support
-
-`init` creates `CLAUDE.md` (Claude Code) and `AGENTS.md` (Codex) by default. All agents follow the same 3-phase checklist protocol.
-
-Add more agents on demand:
-
-| Command | Creates |
-|---|---|
-| `add cursor` | `.cursorrules` |
-| `add windsurf` | `.windsurfrules` |
-| `add copilot` | `.github/copilot-instructions.md` |
-| `add gemini` | `GEMINI.md` |
-
-Running `update` refreshes managed blocks in all existing agent files.
-
-## Shared Repos
-
-Use `memoc work "<title>" --from-git` for meaningful work in shared repositories. It creates a new actor-scoped file under `.memoc/worklog/<actor>/YYYY-MM/`, prefills branch and changed files from git, and avoids append conflicts in shared files.
-
-Actor detection order:
-
-1. `MEMOC_ACTOR`
-2. `.memoc/local/actor` from `memoc actor set <name>`
-3. `git config user.name`
-4. `git config user.email`
-5. OS username
-
-`.memoc/local/` is ignored by git so each machine can keep its own actor setting.
-
-`activity.md`, `actors/README.md`, and `worklog/README.md` are regenerated indexes. Run `memoc activity --write` when you want to refresh them from worklog files.
-
-`log.md` is legacy. New installs do not create it, and shared activity should live in worklog files. On upgrade, an existing `.memoc/log.md` is moved to `.memoc/raw/legacy-log.md` so old history is preserved but no longer part of the normal memory flow.
-
----
-
-## Supported Stacks
-
-Auto-detected from your project files:
-
-Node.js · Next.js · React · Vue · Svelte · Angular · Nuxt · Astro · Express · Fastify · Hono · Electron · Tauri · TypeScript · Prisma · Drizzle · Supabase · Python · FastAPI · Django · Flask · PyTorch · Rust · Go · C++ / CMake · .NET · Java · Flutter · Unreal Engine
-
----
-
-## How It Works
-
-- **New project** — scaffolds all memory files with sensible defaults.
-- **Existing project** — detects your stack and fills in real project info (name, scripts, config files).
-- **Already initialized** — `init` injects the managed block without touching your existing content. `update` re-scans and refreshes project-specific sections.
-- **Long-running projects** — use actor worklogs for history; run `compress` to trim startup memory, archive legacy logs, and refresh generated activity indexes.
-
----
-
+# memoc
+
+> AI agents forget everything when a session ends. memoc gives them a structured memory system so they can pick up exactly where they left off — without you repeating yourself.
+
+Scaffolds a Markdown-based project memory into any codebase. Works with Claude Code, Codex, Cursor, Windsurf, GitHub Copilot, and Gemini CLI.
+
+## Quick Start
+
+```bash
+npx @kevin0181/memoc init
+
+# Upgrade memoc in this project without deleting existing memory
+npx @kevin0181/memoc@latest upgrade
+```
+
+Run inside your project directory. Detects your stack automatically and generates everything agents need.
+
+`init` also creates project-local PATH helpers so agents can keep using memoc even when the global/npm bin is not on PATH.
+
+```bash
+# PowerShell
+. .\.memoc\env.ps1
+
+# sh/bash
+. ./.memoc/env.sh
+```
+
+Agents are instructed to use the project-local wrapper if PATH fails:
+
+```bash
+# Windows
+.\.memoc\bin\memoc.cmd summary
+
+# macOS / Linux
+.memoc/bin/memoc summary
+```
+
+---
+
+## Ask An Agent To Install
+
+If you are giving this repo or npm package to an AI coding agent, use a prompt like:
+
+```text
+Install memoc in this project and run init.
+Use the npm package only. Run `npx @kevin0181/memoc@latest init`
+from this project's root. Do not clone the GitHub repository into this project.
+If npm/npx is missing, stop and ask the user to install Node.js LTS with npm first.
+After init, verify with the project-local wrapper:
+Windows: .\.memoc\bin\memoc.cmd summary
+macOS/Linux: .memoc/bin/memoc summary
+```
+
+Agent install checklist:
+
+1. Run `node --version` and `npm --version`. If either fails, ask the user to install Node.js LTS with npm first.
+2. Run `npx @kevin0181/memoc@latest init` from the target project root.
+3. Do not clone this GitHub repository into the target project. Do not download the repo ZIP as an installer.
+4. `.claude/settings.json` is intentionally generated for the Claude Code Stop hook; keep or commit it only if the project wants that hook.
+5. After init, do not depend on global PATH. Use the project-local wrapper when needed:
+   - Windows: `.\.memoc\bin\memoc.cmd <command>`
+   - macOS/Linux: `.memoc/bin/memoc <command>`
+
+If `node --version` or `npm --version` fails, memoc cannot be installed yet. Install Node.js LTS with npm first, then repeat the steps above.
+
+---
+
+## The Problem
+
+Every new AI session starts cold. You re-explain the project, the decisions already made, what's done and what isn't. The agent rediscovers what the last one figured out.
+
+memoc installs a memory structure that agents read at session start, update as they work, and hand off to the next session — automatically.
+
+---
+
+## Commands
+
+```bash
+# First-time setup — scaffold memory, detect stack, install Claude Code hook
+npx @kevin0181/memoc init
+
+# Re-scan project and refresh managed sections
+npx @kevin0181/memoc update
+
+# Shared repo activity tracking
+npx @kevin0181/memoc actor
+npx @kevin0181/memoc actor set neneee
+npx @kevin0181/memoc work "Auth refresh fix" --from-git
+npx @kevin0181/memoc activity
+npx @kevin0181/memoc activity --write
+npx @kevin0181/memoc doctor
+
+# Print current status in ~10 lines
+npx @kevin0181/memoc summary
+
+# Search memory/agent docs first (token-efficient)
+npx @kevin0181/memoc search "auth"
+npx @kevin0181/memoc search "auth" --snippets --limit 5
+
+# Search project source/text files only when memory is not enough
+npx @kevin0181/memoc grep "GetParticles"
+npx @kevin0181/memoc grep "GetParticles" --snippets --limit 5
+
+# Create raw/source records and durable wiki topic notes
+npx @kevin0181/memoc ingest path/to/source.md
+npx @kevin0181/memoc ingest https://example.com/spec
+npx @kevin0181/memoc note "Auth flow comparison"
+npx @kevin0181/memoc lint-wiki
+
+# Estimate token cost of current memory files
+npx @kevin0181/memoc tokens
+
+# Archive and compact an oversized startup summary
+npx @kevin0181/memoc trim-summary
+
+# Compact oversized memoc files and refresh generated indexes
+npx @kevin0181/memoc compress
+
+# Add the same protocol to another agent's entry file
+npx @kevin0181/memoc add cursor
+npx @kevin0181/memoc add windsurf
+npx @kevin0181/memoc add copilot
+npx @kevin0181/memoc add gemini
+```
+
+---
+
+## Upgrade Existing Projects
+
+memoc never auto-updates itself. Upgrade only when you choose to run:
+
+```bash
+npx @kevin0181/memoc@latest upgrade
+```
+
+Run it from the project root. It preserves existing project memory, including:
+
+- `.memoc/session-summary.md`
+- `.memoc/02-current-project-state.md` human-written sections
+- `.memoc/03-decisions.md`
+- `.memoc/04-handoff.md`
+- `.memoc/06-project-rules.md`
+- Legacy `.memoc/log.md` if present
+- Legacy `.memoc/systems/` if present (moved to `.memoc/raw/legacy-systems/` on upgrade)
+- `.memoc/wiki/`
+
+It refreshes the managed blocks, project-local wrappers, runtime copy, PATH helpers, and memoc-owned protocol templates. User-owned memory files such as `session-summary.md`, `03-decisions.md`, `04-handoff.md`, `06-project-rules.md`, and wiki topic/source pages are preserved. Upgrade also runs the `trim-summary` compaction pass so startup memory stays small. If `memoc` is not on PATH after upgrading, keep using:
+
+```bash
+# Windows
+.\.memoc\bin\memoc.cmd summary
+
+# macOS / Linux
+.memoc/bin/memoc summary
+```
+
+---
+
+## What Gets Created
+
+```
+CLAUDE.md                                    ← Claude Code entry point (auto-loaded)
+AGENTS.md                                    ← Codex entry point (auto-loaded)
+llms.txt                                     ← LLM-facing project map
+.claude/settings.json                        ← Claude Code Stop hook
+
+.memoc/
+  bin/memoc                                  ← project-local wrapper for PATH fallback
+  env.ps1 · env.sh                           ← shell helpers that prepend .memoc/bin to PATH
+  session-summary.md                         ← Only required startup read (~150 tokens)
+  02-current-project-state.md               ← Status, open tasks, commands
+  03-decisions.md                            ← Durable decision log
+  04-handoff.md                              ← Resume context, verified/unverified
+  06-project-rules.md                        ← User preferences
+  activity.md                                ← Short shared activity index
+  actors/                                    ← Actor profiles for shared repos
+  worklog/                                   ← Per-actor work records to reduce conflicts
+  raw/                                       ← Immutable source material, not a startup read
+  wiki/project/                              ← Project implementation wiki
+  wiki/knowledge/                            ← Source-backed knowledge wiki
+
+skills/project-memory-maintainer/SKILL.md   ← Wiki operations guide
+```
+
+---
+
+## How Agents Use It
+
+Every entry file (`CLAUDE.md`, `AGENTS.md`, `.cursorrules`, etc.) gets the same protocol injected as a managed block:
+
+```
+## Session Start
+- [ ] Read `.memoc/session-summary.md`
+- [ ] `.pending` exists? → review changed files → update memory if needed → delete it
+- [ ] If `memoc` is not found, use the project-local wrapper.
+
+## Before Opening More Files
+- [ ] Run `memoc search "<query>"` first
+- [ ] Open on demand: `02` status · `04` resume · `06` rules · `llms.txt` map
+- [ ] Use `memoc grep "<query>"` only when memory is not enough.
+- [ ] For durable source/wiki work, use `memoc ingest`, `memoc note`, and `memoc lint-wiki`.
+- [ ] In shared repos, record meaningful work with `memoc work "<title>"`.
+- [ ] Keep output small: `summary`, `search --limit`, `search --snippets`
+
+## Before Finishing _(update only applicable files; skip Q&A / throwaway exploration)_
+- [ ] Code/config/deps changed → `02` (version, commands list, Last synced) + `session-summary.md` (status, changed, open tasks)
+- [ ] Decision made → `03-decisions.md` (what & why) + `02`
+- [ ] Work incomplete or risky → `04-handoff.md` (verified commands, unverified items, next steps)
+- [ ] Rule/preference set → `06-project-rules.md`
+- [ ] Wiki/project-memory work → read `skills/project-memory-maintainer/SKILL.md`
+- [ ] Shared repo work → prefer `memoc work "<title>" --from-git`; run `memoc activity --write` only when regenerating indexes.
+- [ ] Keep `session-summary.md` replace-only; completed work belongs in actor worklogs.
+```
+
+The checklist tells agents exactly when to update, which file to update, and what to record — so nothing gets missed.
+
+---
+
+## Token Efficiency
+
+Startup cost is kept minimal by design.
+
+| What loads | Tokens |
+|---|---|
+| `CLAUDE.md` (managed block only) | ~280 |
+| `session-summary.md` (only required read) | ~150 |
+| **Total startup** | **~430** |
+
+Everything else is on-demand. Use `memoc tokens` to see the live breakdown for your project.
+
+`session-summary.md` is a replace-only startup snapshot, not a timeline. If it grows beyond the warning threshold, run `memoc compress` or `memoc trim-summary`; completed history belongs in `.memoc/worklog/<actor>/YYYY-MM/`, and unfinished/risky resume detail belongs in `.memoc/04-handoff.md`.
+
+---
+
+## Claude Code Auto-Detection
+
+`init` installs a lightweight `Stop` hook in `.claude/settings.json`. After each Claude Code response it checks:
+
+```bash
+git status --porcelain
+```
+
+If uncommitted changes exist, it writes `.memoc/.pending` with a timestamp and the changed filenames. At the next session start, Claude reads `.pending` and decides whether to update memory — then deletes the file.
+
+No extra setup. Add `.memoc/.pending` to `.gitignore` to keep it untracked.
+
+---
+
+## Multi-Agent Support
+
+`init` creates `CLAUDE.md` (Claude Code) and `AGENTS.md` (Codex) by default. All agents follow the same 3-phase checklist protocol.
+
+Add more agents on demand:
+
+| Command | Creates |
+|---|---|
+| `add cursor` | `.cursorrules` |
+| `add windsurf` | `.windsurfrules` |
+| `add copilot` | `.github/copilot-instructions.md` |
+| `add gemini` | `GEMINI.md` |
+
+Running `update` refreshes managed blocks in all existing agent files.
+
+## Shared Repos
+
+Use `memoc work "<title>" --from-git` for meaningful work in shared repositories. It creates a new actor-scoped file under `.memoc/worklog/<actor>/YYYY-MM/`, prefills branch and changed files from git, and avoids append conflicts in shared files.
+
+Actor detection order:
+
+1. `MEMOC_ACTOR`
+2. `.memoc/local/actor` from `memoc actor set <name>`
+3. `git config user.name`
+4. `git config user.email`
+5. OS username
+
+`.memoc/local/` is ignored by git so each machine can keep its own actor setting.
+
+`activity.md`, `actors/README.md`, and `worklog/README.md` are regenerated indexes. Run `memoc activity --write` when you want to refresh them from worklog files.
+
+`log.md` is legacy. New installs do not create it, and shared activity should live in worklog files. On upgrade, an existing `.memoc/log.md` is moved to `.memoc/raw/legacy-log.md` so old history is preserved but no longer part of the normal memory flow.
+
+---
+
+## Supported Stacks
+
+Auto-detected from your project files:
+
+Node.js · Next.js · React · Vue · Svelte · Angular · Nuxt · Astro · Express · Fastify · Hono · Electron · Tauri · TypeScript · Prisma · Drizzle · Supabase · Python · FastAPI · Django · Flask · PyTorch · Rust · Go · C++ / CMake · .NET · Java · Flutter · Unreal Engine
+
+---
+
+## How It Works
+
+- **New project** — scaffolds all memory files with sensible defaults.
+- **Existing project** — detects your stack and fills in real project info (name, scripts, config files).
+- **Already initialized** — `init` injects the managed block without touching your existing content. `update` re-scans and refreshes project-specific sections.
+- **Long-running projects** — use actor worklogs for history; run `compress` to trim startup memory, archive legacy logs, and refresh generated activity indexes.
+
+---
+
 ## Skills Plugin (Claude Code, Codex Desktop, and Skills-Compatible Agents)
 
 Install the memoc plugin once to get `/memoc-*` slash commands in Claude Code, Codex Desktop, and agents that read the common Skills location:
-
-```bash
-# Install memoc globally (if not already)
-npm install -g @kevin0181/memoc
-
+
+```bash
+# Install memoc globally (if not already)
+npm install -g @kevin0181/memoc
+
 # Register the plugin and global skills (run once)
 memoc install-plugin
 
 # Then restart open agent apps
-```
-
-Or via npx (no global install needed):
-
-```bash
-npx @kevin0181/memoc install-plugin
-```
-
-To remove:
-
-```bash
-memoc uninstall-plugin
-```
-
+```
+
+Or via npx (no global install needed):
+
+```bash
+npx @kevin0181/memoc install-plugin
+```
+
+To remove:
+
+```bash
+memoc uninstall-plugin
+```
+
 `install-plugin` writes the Claude Code plugin to `~/.claude/plugins/cache/memoc/`, enables `"memoc@memoc"` in `~/.claude/settings.json`, and installs global Skills entries under `~/.agents/skills/` for Codex Desktop and other skills-compatible agents. It is idempotent — safe to re-run after upgrading memoc.
-
-### Available skills
-
-| Skill | What it does |
-|-------|-------------|
+
+### Available skills
+
+| Skill | What it does |
+|-------|-------------|
 | `/memoc` | Follow the full memoc memory operating protocol |
 | `/memoc-init` | Initialize memoc in the current project |
 | `/memoc-upgrade` | Upgrade memoc, preserve memory |
@@ -345,9 +345,9 @@ memoc uninstall-plugin
 | `/memoc-goal` | Define success criteria and verify with tests/repros |
 
 The `/memoc-code` family is adapted from [`multica-ai/andrej-karpathy-skills`](https://github.com/multica-ai/andrej-karpathy-skills), MIT licensed, with short memoc names for coding workflows.
-
----
-
-## License
-
-MIT
+
+---
+
+## License
+
+MIT

package/bin/cli.js

@@ -3826,13 +3826,61 @@ function runInstallPlugin() {
     process.exit(1);
   }
 
-  const claudeDir     = process.env.CLAUDE_CONFIG_DIR || path.join(os.homedir(), '.claude');
-  const cacheDir      = path.join(claudeDir, 'plugins', 'cache', 'memoc', 'memoc', VERSION);
-  const installedPath = path.join(claudeDir, 'plugins', 'installed_plugins.json');
-  const settingsPath  = path.join(claudeDir, 'settings.json');
-
-  // copy plugin files
-  copyDirSync(pluginSrc, cacheDir);
+  const claudeDir     = process.env.CLAUDE_CONFIG_DIR || path.join(os.homedir(), '.claude');
+  const cacheDir      = path.join(claudeDir, 'plugins', 'cache', 'memoc', 'memoc', VERSION);
+  const marketplaceDir = path.join(claudeDir, 'plugins', 'marketplaces', 'memoc');
+  const marketplacePluginDir = path.join(marketplaceDir, 'plugins', 'memoc');
+  const claudeMarketplacePath = path.join(marketplaceDir, '.claude-plugin', 'marketplace.json');
+  const agentsMarketplacePath = path.join(marketplaceDir, '.agents', 'plugins', 'marketplace.json');
+  const installedPath = path.join(claudeDir, 'plugins', 'installed_plugins.json');
+  const settingsPath  = path.join(claudeDir, 'settings.json');
+
+  // copy plugin files to Claude's cache and local marketplace registry
+  copyDirSync(pluginSrc, cacheDir);
+  copyDirSync(pluginSrc, marketplacePluginDir);
+  const claudeMarketplace = {
+    $schema: 'https://anthropic.com/claude-code/marketplace.schema.json',
+    name: 'memoc',
+    description: 'memoc skills and plugin installer for Claude Code, Codex, and skills-compatible coding agents.',
+    owner: {
+      name: 'kevin0181',
+    },
+    plugins: [{
+      name: 'memoc',
+      description: 'Session-to-session memory and coding guardrail skills for AI coding agents.',
+      author: {
+        name: 'kevin0181',
+      },
+      source: './plugins/memoc',
+      category: 'productivity',
+      homepage: 'https://github.com/neneee0181/memoc',
+    }],
+  };
+  const agentsMarketplace = {
+    name: 'memoc',
+    interface: {
+      displayName: 'memoc',
+    },
+    plugins: [{
+      name: 'memoc',
+      source: {
+        source: 'local',
+        path: './plugins/memoc',
+      },
+      policy: {
+        installation: 'AVAILABLE',
+        authentication: 'ON_INSTALL',
+      },
+      category: 'Productivity',
+    }],
+  };
+  for (const [marketplacePath, marketplace] of [
+    [claudeMarketplacePath, claudeMarketplace],
+    [agentsMarketplacePath, agentsMarketplace],
+  ]) {
+    fs.mkdirSync(path.dirname(marketplacePath), { recursive: true });
+    fs.writeFileSync(marketplacePath, JSON.stringify(marketplace, null, 2) + '\n');
+  }
 
   // update installed_plugins.json
   const installed = readJsonLoose(installedPath) || {};
@@ -3850,12 +3898,19 @@ function runInstallPlugin() {
   fs.mkdirSync(path.dirname(installedPath), { recursive: true });
   fs.writeFileSync(installedPath, JSON.stringify(installed, null, 2) + '\n');
 
-  // update settings.json
-  const settings = readJsonLoose(settingsPath) || {};
-  settings.enabledPlugins = settings.enabledPlugins || {};
-  settings.enabledPlugins[PLUGIN_KEY] = true;
-  fs.mkdirSync(path.dirname(settingsPath), { recursive: true });
-  try { fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2) + '\n', { mode: 0o600 }); }
+  // update settings.json
+  const settings = readJsonLoose(settingsPath) || {};
+  settings.enabledPlugins = settings.enabledPlugins || {};
+  settings.enabledPlugins[PLUGIN_KEY] = true;
+  settings.extraKnownMarketplaces = settings.extraKnownMarketplaces || {};
+  settings.extraKnownMarketplaces.memoc = {
+    source: {
+      source: 'directory',
+      path: marketplaceDir,
+    },
+  };
+  fs.mkdirSync(path.dirname(settingsPath), { recursive: true });
+  try { fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2) + '\n', { mode: 0o600 }); }
   catch { fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2) + '\n'); }
 
   const SKILL_NAMES = [
@@ -3903,7 +3958,7 @@ function runInstallPlugin() {
   }
 
   console.log('\n  memoc plugin installed\n');
-  console.log('  Claude Code    ~/.claude/plugins/cache/memoc/');
+  console.log('  Claude Code    ~/.claude/plugins/cache/memoc/ + ~/.claude/plugins/marketplaces/memoc/');
   console.log('  Codex Desktop  ~/.agents/skills/');
   console.log('  Skills spec    ~/.agents/skills/ (Cursor, Windsurf, and other supported agents)');
   console.log('\n  Skills:');
@@ -3923,12 +3978,14 @@ function runUninstallPlugin() {
   ];
 
   const claudeDir     = process.env.CLAUDE_CONFIG_DIR || path.join(os.homedir(), '.claude');
-  const cacheBase     = path.join(claudeDir, 'plugins', 'cache', 'memoc');
-  const installedPath = path.join(claudeDir, 'plugins', 'installed_plugins.json');
+  const cacheBase     = path.join(claudeDir, 'plugins', 'cache', 'memoc');
+  const marketplaceBase = path.join(claudeDir, 'plugins', 'marketplaces', 'memoc');
+  const installedPath = path.join(claudeDir, 'plugins', 'installed_plugins.json');
   const settingsPath  = path.join(claudeDir, 'settings.json');
 
-  // remove Claude Code cache
-  if (fs.existsSync(cacheBase)) fs.rmSync(cacheBase, { recursive: true, force: true });
+  // remove Claude Code cache
+  if (fs.existsSync(cacheBase)) fs.rmSync(cacheBase, { recursive: true, force: true });
+  if (fs.existsSync(marketplaceBase)) fs.rmSync(marketplaceBase, { recursive: true, force: true });
 
   // remove from installed_plugins.json
   const installed = readJsonLoose(installedPath);
@@ -3952,9 +4009,10 @@ function runUninstallPlugin() {
 
   // remove from settings.json
   const settings = readJsonLoose(settingsPath);
-  if (settings && settings.enabledPlugins) {
-    delete settings.enabledPlugins[PLUGIN_KEY];
-    try { fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2) + '\n', { mode: 0o600 }); }
+  if (settings && settings.enabledPlugins) {
+    delete settings.enabledPlugins[PLUGIN_KEY];
+    if (settings.extraKnownMarketplaces) delete settings.extraKnownMarketplaces.memoc;
+    try { fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2) + '\n', { mode: 0o600 }); }
     catch { fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2) + '\n'); }
   }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kevin0181/memoc",
-  "version": "1.4.6",
+  "version": "1.4.10",
   "description": "Give AI agents a memory. Scaffolds session-to-session context for Claude Code, Codex, Cursor, and more.",
   "keywords": [
     "ai",
@@ -31,7 +31,7 @@
   "files": [
     "bin/",
     "plugins/",
-    "skills/"
+    "skills/memoc*/"
   ],
   "engines": {
     "node": ">=16"

package/plugins/memoc/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memoc",
-  "version": "1.4.6",
+  "version": "1.4.10",
   "description": "Agent memory skills for memoc — scaffold, maintain, and query session-to-session AI memory.",
   "author": {
     "name": "kevin0181",

package/skills/memoc/SKILL.md

@@ -1,54 +0,0 @@
----
-name: memoc
-description: >
-  Follow the full memoc operating protocol for a project: read memory first,
-  preserve durable context, use the project-local memoc runtime when available,
-  and record important work before handoff. Trigger: /memoc, "use memoc",
-  "follow memoc memory", "resume with memoc".
----
-
-Use this skill as the default operating mode for a repository that has, or should have, memoc memory.
-
-## Operating protocol
-
-1. Start by checking whether memoc is installed in the current project.
-   - Prefer `.memoc/` plus project-local launchers.
-   - If absent and the user wants memory set up, run `/memoc-init` or `memoc init`.
-
-2. Read memory before acting.
-   - First run `memoc summary` when available.
-   - Then open only the memory files that are relevant to the task, such as `.memoc/session-summary.md`, `.memoc/02-current-project-state.md`, `.memoc/04-handoff.md`, `.memoc/wiki/`, or worklog entries.
-
-3. Keep memory durable and concise.
-   - Record decisions, user preferences, active constraints, and handoff notes.
-   - Do not store transient command output, obvious code facts, secrets, credentials, or noisy chat history.
-   - Prefer wiki notes for reusable knowledge and worklog entries for session activity.
-
-4. Use the right memoc command when useful.
-   - `memoc search "<query>"` before broad filesystem search when looking for prior context.
-   - `memoc work "<title>"` after meaningful work so future agents know what changed.
-   - `memoc note "<title>"` for durable knowledge that should survive sessions.
-   - `memoc doctor` when memory looks stale, malformed, too large, or inconsistent.
-   - `memoc compress` when memory is noisy or oversized.
-   - `memoc upgrade` after updating memoc itself or when runtime/wrapper files are stale.
-
-5. Preserve user work.
-   - Treat memory files as collaborative project state.
-   - Do not overwrite user-authored notes unless the command is designed to preserve and merge them.
-   - Before final handoff, mention any memory updates made and any remaining health issues.
-
-## Binary resolution (all skills use this order)
-
-1. Windows: `.\.memoc\bin\memoc.cmd`
-2. macOS/Linux: `.memoc/bin/memoc`
-3. Fallback: `npx @kevin0181/memoc@latest`
-
-## Related focused skills
-
-- `/memoc-init` initializes memoc in the current project.
-- `/memoc-upgrade` refreshes runtime files while preserving memory.
-- `/memoc-search` searches memory and agent docs.
-- `/memoc-work` records session activity.
-- `/memoc-note` saves durable knowledge.
-- `/memoc-doctor` checks memory health.
-- `/memoc-compress` compacts noisy memory.

package/skills/memoc-code/SKILL.md

@@ -1,45 +0,0 @@
----
-name: memoc-code
-description: >
-  Coding guardrails adapted from multica-ai/andrej-karpathy-skills. Use when
-  writing, fixing, reviewing, or refactoring code: think before coding, keep the
-  solution simple, edit surgically, and verify against concrete success criteria.
-  Trigger: /memoc-code, "use memoc coding guardrails", "code carefully".
-license: MIT
----
-
-Use this skill to reduce common AI coding mistakes: guessing, overbuilding,
-unrelated edits, and stopping before the result is verified.
-
-Source inspiration: `multica-ai/andrej-karpathy-skills`, MIT.
-
-## Protocol
-
-1. Think before coding.
-   - State assumptions when the request is ambiguous.
-   - Ask when uncertainty would change the implementation.
-   - Surface tradeoffs instead of silently choosing.
-
-2. Keep it simple.
-   - Build only what was requested.
-   - Avoid speculative configuration, future-proofing, and one-use abstractions.
-   - If the solution feels large for the problem, reduce it.
-
-3. Edit surgically.
-   - Touch only files and lines needed for the task.
-   - Match the local style.
-   - Do not clean up unrelated code; mention it separately.
-   - Remove only dead code created by your own changes.
-
-4. Make success verifiable.
-   - Turn the request into observable checks.
-   - For bugs, prefer a reproducing test or concrete repro before the fix.
-   - For refactors, verify behavior before and after.
-   - Keep looping until the check passes or the blocker is clear.
-
-## Shortcuts
-
-- `/memoc-think` for ambiguity, assumptions, and tradeoffs.
-- `/memoc-simple` for reducing overbuilt designs.
-- `/memoc-scope` for tight, minimal diffs.
-- `/memoc-goal` for tests, repros, and verification loops.

package/skills/memoc-compress/SKILL.md

@@ -1,31 +0,0 @@
----
-name: memoc-compress
-description: >
-  Compact memoc memory files and refresh generated indexes. Removes redundancy,
-  trims verbose entries, rebuilds activity and wiki indexes.
-  Trigger: /memoc-compress, "compress memoc", "compact memory", "clean up memoc files",
-  "memoc files too big".
----
-
-Run `memoc compress` in the current working directory.
-
-## Steps
-
-1. **Find binary** (priority order):
-   - Windows: `.\.memoc\bin\memoc.cmd compress`
-   - macOS/Linux: `.memoc/bin/memoc compress`
-   - Fallback: `npx @kevin0181/memoc@latest compress`
-
-2. **Run compress** and capture output.
-
-3. **Report**:
-   - Which files were compacted
-   - Token/size reduction achieved (if reported)
-   - Any indexes rebuilt
-
-## When to use
-
-- `memoc tokens` shows large files (⚠ warnings)
-- After extended sessions with many entries
-- Before important commits to keep memory lean
-- session-summary.md exceeds ~800B

package/skills/memoc-doctor/SKILL.md

@@ -1,35 +0,0 @@
----
-name: memoc-doctor
-description: >
-  Check common memoc health issues: broken links, missing files, malformed frontmatter,
-  oversized summaries, stale content. Diagnose and suggest fixes.
-  Trigger: /memoc-doctor, "memoc health check", "check memoc", "diagnose memoc",
-  "is memoc healthy", "memoc issues".
----
-
-Run `memoc doctor` in the current working directory.
-
-## Steps
-
-1. **Find binary** (priority order):
-   - Windows: `.\.memoc\bin\memoc.cmd doctor`
-   - macOS/Linux: `.memoc/bin/memoc doctor`
-   - Fallback: `npx @kevin0181/memoc@latest doctor`
-
-2. **Display output** verbatim.
-
-3. **For each issue found**, offer to fix it:
-   - Oversized summary → `/memoc-trim`
-   - Broken wiki links → `/memoc-lint`
-   - Large files → `/memoc-compress`
-   - Missing wrapper → run `memoc upgrade`
-
-4. **If no issues**: confirm memoc is healthy.
-
-## What doctor checks
-
-- `.memoc/` directory exists and is valid
-- session-summary.md size is within budget
-- Agent entry files (CLAUDE.md etc.) are present
-- Project-local wrapper scripts are functional
-- Frontmatter validity on memory files

package/skills/memoc-goal/SKILL.md

@@ -1,19 +0,0 @@
----
-name: memoc-goal
-description: >
-  Goal-driven execution for coding tasks. Use when work needs clear success
-  criteria, tests, reproduction steps, or a verification loop. Trigger:
-  /memoc-goal.
-license: MIT
----
-
-Source inspiration: `multica-ai/andrej-karpathy-skills`, MIT.
-
-Turn the task into a verifiable goal:
-
-- Define what success looks like before making broad edits.
-- For a bug, create or describe the failing repro first, then fix it.
-- For validation, test invalid and valid inputs.
-- For refactors, verify behavior before and after.
-- For multi-step work, pair each step with a check.
-- Keep iterating until checks pass, or report the exact blocker.

package/skills/memoc-init/SKILL.md

@@ -1,34 +0,0 @@
----
-name: memoc-init
-description: >
-  Initialize memoc in the current project. Scaffolds agent memory files, detects stack,
-  generates CLAUDE.md/AGENTS.md and .memoc/ directory.
-  Trigger: /memoc-init, "initialize memoc", "setup memoc memory", "scaffold memoc",
-  "install memoc in this project".
----
-
-Run `memoc init` in the current working directory.
-
-## Steps
-
-1. **Find binary** (priority order):
-   - Windows: `.\.memoc\bin\memoc.cmd init`
-   - macOS/Linux: `.memoc/bin/memoc init`
-   - Fallback: `npx @kevin0181/memoc@latest init`
-
-2. **Run init** and capture output.
-
-3. **Report** what was created:
-   - Which agent entry files were generated (CLAUDE.md, AGENTS.md, GEMINI.md, etc.)
-   - Whether `.memoc/` directory was created or updated
-   - Any stack detection results
-
-4. **If already initialized**: init auto-updates managed sections. Report what changed.
-
-5. **If Node.js missing**: stop and tell user to install Node.js LTS with npm first.
-
-## After init
-
-Remind user to source the PATH helper so the project-local wrapper is available:
-- PowerShell: `. .\.memoc\env.ps1`
-- bash/zsh: `. .memoc/env.sh`

package/skills/memoc-note/SKILL.md

@@ -1,34 +0,0 @@
----
-name: memoc-note
-description: >
-  Save a durable topic/query-result scaffold for knowledge that should persist across sessions.
-  Creates a structured note in the memoc wiki for later reference by agents.
-  Trigger: /memoc-note, "save a note", "create memoc note", "remember this topic",
-  "add to knowledge base", "save research result".
----
-
-Run `memoc note "<title>"` in the current working directory.
-
-## Steps
-
-1. **Get title** from user's message or args. If not provided, ask: "Topic or title for this note?"
-
-2. **Find binary** (priority order):
-   - Windows: `.\.memoc\bin\memoc.cmd note "<title>"`
-   - macOS/Linux: `.memoc/bin/memoc note "<title>"`
-   - Fallback: `npx @kevin0181/memoc@latest note "<title>"`
-
-3. **Run command** and report the created file path.
-
-4. **Help populate** the note with content from the current conversation if relevant:
-   - Key findings or decisions
-   - Code patterns or solutions
-   - External references
-   - Related topics
-
-## Use cases
-
-- Saving research findings for future sessions
-- Documenting architectural decisions not obvious from code
-- Recording API quirks, gotchas, or workarounds
-- Building a queryable knowledge base with `memoc search`

package/skills/memoc-scope/SKILL.md

@@ -1,19 +0,0 @@
----
-name: memoc-scope
-description: >
-  Surgical-change discipline. Use when editing an existing codebase and the
-  important thing is to avoid drive-by refactors, unrelated formatting churn, or
-  accidental behavior changes. Trigger: /memoc-scope.
-license: MIT
----
-
-Source inspiration: `multica-ai/andrej-karpathy-skills`, MIT.
-
-Keep the diff tight:
-
-- Touch only what the user request requires.
-- Match existing style even when you would design it differently.
-- Do not rewrite adjacent comments, formatting, or APIs for taste.
-- Do not delete unrelated dead code; mention it separately.
-- Remove imports, variables, and helpers only when your own change made them unused.
-- Every changed line should trace back to the requested outcome.

package/skills/memoc-search/SKILL.md

@@ -1,38 +0,0 @@
----
-name: memoc-search
-description: >
-  Search memory files and agent docs for a query. Finds relevant notes, decisions,
-  worklogs, and wiki entries. Supports --snippets for line-level matches.
-  Trigger: /memoc-search, "search memoc", "search memory", "find in notes",
-  "search agent docs", "look up in memory".
----
-
-Run `memoc search "<query>"` in the current working directory.
-
-## Steps
-
-1. **Get query** from user's message or args. Required — if not provided, ask.
-
-2. **Choose mode**:
-   - Default: file names with match counts sorted by relevance + recency
-   - With `--snippets` flag: show matching lines with context
-
-3. **Find binary** (priority order):
-   - Windows: `.\.memoc\bin\memoc.cmd search "<query>" [flags]`
-   - macOS/Linux: `.memoc/bin/memoc search "<query>" [flags]`
-   - Fallback: `npx @kevin0181/memoc@latest search "<query>" [flags]`
-
-4. **Display results** and offer to open the most relevant file.
-
-## Flags
-
-| Flag | Effect |
-|------|--------|
-| `--snippets` | Show matching lines instead of file list |
-| `--limit N` | Limit results (default 12) |
-| `--all` | Show all matches without limit |
-
-## Scope
-
-Searches `.memoc/` directory and agent entry files (CLAUDE.md, AGENTS.md, etc.).
-For project source files, use `/memoc-grep` instead.

package/skills/memoc-simple/SKILL.md

@@ -1,19 +0,0 @@
----
-name: memoc-simple
-description: >
-  Simplicity-first coding. Use when implementing a feature or fix that risks
-  overengineering, speculative abstraction, or unnecessary configurability.
-  Trigger: /memoc-simple.
-license: MIT
----
-
-Source inspiration: `multica-ai/andrej-karpathy-skills`, MIT.
-
-Prefer the smallest solution that genuinely solves the request:
-
-- Do not add features the user did not ask for.
-- Do not add abstractions for single-use code.
-- Do not add flexibility or configuration just in case.
-- Do not add error handling for impossible or irrelevant cases.
-- If the implementation feels too large, simplify before continuing.
-- Use existing local patterns before introducing new ones.

package/skills/memoc-think/SKILL.md

@@ -1,18 +0,0 @@
----
-name: memoc-think
-description: >
-  Think before coding. Use when a coding task has ambiguity, hidden assumptions,
-  multiple possible interpretations, or tradeoffs that should be surfaced before
-  editing. Trigger: /memoc-think.
-license: MIT
----
-
-Source inspiration: `multica-ai/andrej-karpathy-skills`, MIT.
-
-Before implementing:
-
-- Name the assumptions you are making.
-- If two interpretations are plausible, present them instead of silently choosing.
-- Ask a concise question when the answer would materially change the code.
-- Push back when a simpler or safer approach fits the request better.
-- Stop and clarify when you are confused; do not code through confusion.

package/skills/memoc-upgrade/SKILL.md

@@ -1,27 +0,0 @@
----
-name: memoc-upgrade
-description: >
-  Upgrade memoc runtime and wrappers in the current project without deleting existing memory.
-  Refreshes managed sections based on current project state.
-  Trigger: /memoc-upgrade, "upgrade memoc", "update memoc", "refresh memoc runtime".
----
-
-Run `memoc upgrade` in the current working directory.
-
-## Steps
-
-1. **Find binary** (priority order):
-   - Windows: `.\.memoc\bin\memoc.cmd upgrade`
-   - macOS/Linux: `.memoc/bin/memoc upgrade`
-   - Fallback: `npx @kevin0181/memoc@latest upgrade`
-
-2. **Run upgrade** and capture output.
-
-3. **Report**:
-   - Which files were refreshed vs preserved
-   - New memoc version vs previous version (if shown)
-   - Any managed sections that were updated
-
-## Key behavior
-
-Upgrade preserves all manually-written memory content. Only memoc-managed sections (marked with `<!-- memoc:managed -->` or equivalent) are updated. User-written content is never overwritten.

package/skills/memoc-work/SKILL.md

@@ -1,31 +0,0 @@
----
-name: memoc-work
-description: >
-  Create a conflict-light actor worklog entry for the current work session.
-  Records what was done, by whom, and when — for shared repos with multiple actors.
-  Trigger: /memoc-work, "log work", "create worklog", "record what I did",
-  "add work entry", "memoc log session".
----
-
-Run `memoc work "<title>"` in the current working directory.
-
-## Steps
-
-1. **Get title** from user's message or args. If not provided, ask: "Brief title for this work entry?"
-
-2. **Find binary** (priority order):
-   - Windows: `.\.memoc\bin\memoc.cmd work "<title>"`
-   - macOS/Linux: `.memoc/bin/memoc work "<title>"`
-   - Fallback: `npx @kevin0181/memoc@latest work "<title>"`
-
-3. **Run command** and report the created file path.
-
-4. **Open the file** and help user fill in the work details:
-   - What was done
-   - Files changed
-   - Decisions made
-   - Next steps
-
-## Entry format
-
-Worklog entries are Markdown scaffolds stored per-actor to avoid merge conflicts in shared repos. Each entry is timestamped and attributed to the current actor (`memoc actor` to check/set).