mema-kit 1.1.0 → 1.1.1

package/README.md

@@ -91,6 +91,7 @@ claude
 ├── project/               # Stable project knowledge
 │   ├── architecture.md
 │   ├── requirements.md
+│   ├── structure.md
 │   └── decisions/
 ├── agent/                 # Cross-session knowledge
 │   ├── lessons.md

package/docs/guide.md

@@ -188,6 +188,7 @@ Every skill reads what previous skills wrote. The index ties it all together.
 ├── project/               # Stable project knowledge
 │   ├── architecture.md
 │   ├── requirements.md
+│   ├── structure.md       # Annotated directory tree
 │   └── decisions/
 ├── agent/                 # Cross-session knowledge
 │   ├── lessons.md

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mema-kit",
-  "version": "1.1.0",
+  "version": "1.1.1",
   "description": "AI-assisted development lifecycle kit",
   "bin": {
     "mema-kit": "bin/cli.js"

package/skills/_memory-protocol.md

@@ -84,6 +84,12 @@ Update `.mema/index.md` to reflect all changes made in Phase 3. This is **mandat
 - **UPDATE** when the stack or requirements change.
 - Keep current state only — these are reference documents, not history logs.
 
+### project/structure.md — Replace curation
+- **UPDATE** when directories or key files are added, renamed, or removed.
+- Keep current state only — this is a navigation reference, not a history log.
+- **NOOP** if no structural change occurred in this session.
+- Never delete — if the project structure is unknown, leave the file with a minimal tree rather than removing it.
+
 ### agent/lessons.md and agent/patterns.md — Consolidation curation
 - **Merge similar lessons.** "Drizzle needs type casting" and "Drizzle enum handling requires explicit cast" are the same lesson — keep one entry with both examples.
 - **UPDATE** with new examples when the same pattern/lesson recurs.

package/skills/mema.create-skill/SKILL.md

@@ -292,6 +292,10 @@ Follow the curation rules in `_memory-protocol.md`.
 
 **If a skill file was written** (user did not CANCEL):
 - ADD/UPDATE `agent/patterns.md` with a lightweight record: skill name, complexity level, one-sentence purpose, action taken (`created` / `enhanced` / `overwritten`), date (`YYYY-MM-DD`)
+- UPDATE `project/structure.md`:
+  - Add `├── [skill-name]/   — [skill purpose, one clause]` to the `.claude/skills/` subtree in `## Directory Tree`
+  - Add entry to `## Where to Find X`: `**[Skill name] skill:** .claude/skills/[skill-name]/SKILL.md`
+  - If `project/structure.md` does not exist, NOOP (structure.md is created by `/mema.onboard`)
 
 **If no file was written** (user cancelled at any step):
 - NOOP — no memory changes
@@ -301,4 +305,5 @@ Follow the curation rules in `_memory-protocol.md`.
 Update `.mema/index.md`:
 1. Re-read the current index
 2. If `agent/patterns.md` was modified, update its summary entry
-3. Update the `**Updated:**` date
+3. If `project/structure.md` was modified, update its summary entry
+4. Update the `**Updated:**` date

package/skills/mema.implement/SKILL.md

@@ -143,6 +143,7 @@ Follow curation rules in `_memory-protocol.md`:
 
 - **Decisions made** during implementation → ADD to `project/decisions/YYYY-MM-DD-short-name.md`
 - **Architecture changes** → UPDATE `project/architecture.md`
+- **Structural changes** (new files, directories, or moves) → UPDATE `project/structure.md`: add/remove/rename the affected entries in `## Directory Tree` and `## Where to Find X`. If nothing structural changed, NOOP.
 - **Lessons learned** → ADD/UPDATE `agent/lessons.md`
 - **Patterns discovered** → ADD/UPDATE `agent/patterns.md`
 - **Task progress** → UPDATE `features/NNN-name/status.md` (done in 2f)

package/skills/mema.onboard/SKILL.md

@@ -220,6 +220,39 @@ Using scan findings, create files with **real content** (not empty placeholders)
 - [Constraint discovered]
 ```
 
+### `.mema/project/structure.md`
+
+Using the directory scan from Step 5b, write an annotated repo tree and navigation guide:
+
+```
+# Repository Structure
+
+**Status:** active | **Updated:** [today]
+
+## Directory Tree
+
+```
+[project-name]/
+[2–3 level annotated tree derived from Step 5b scan]
+```
+
+## Entry Points
+
+[Key files per subsystem, e.g.:]
+- `[entry file]` — [what it does]
+
+## Source vs. Generated
+
+- **Source:** [source dirs]
+- **Generated:** [build output, node_modules, etc.]
+- **Gitignored:** `.mema/`, [other gitignored items]
+
+## Where to Find X
+
+[Quick-reference for the top subsystems found during scan:]
+- **[Component type]:** `[path/]`
+```
+
 ### `.mema/agent/lessons.md`
 
 ```
@@ -262,6 +295,7 @@ Build the index from files just created:
 ## Project Knowledge
 - `project/architecture.md` — [one-line stack/architecture summary]
 - `project/requirements.md` — [one-line purpose summary]
+- `project/structure.md` — [one-line: e.g. "Annotated repo tree, 3 top-level dirs"]
 
 ## Agent Knowledge
 - `agent/lessons.md` — [N] lessons recorded
@@ -336,6 +370,7 @@ Print a summary of what was done:
 mema-kit initialized!
 
 [check] .mema/ structure created (product/, features/, project/, agent/)
+[check] project/structure.md generated
 [check] CLAUDE.md [generated / updated / already configured]
 [check] .gitignore updated
 

package/skills/mema.recall/SKILL.md

@@ -42,6 +42,7 @@ Read the following (skip any that don't exist):
 
 1. `.mema/project/architecture.md` — tech stack, structure, architecture pattern
 2. `.mema/project/requirements.md` — project purpose and constraints
+3. `.mema/project/structure.md` — annotated directory tree and navigation guide
 
 ## Step 5: Load Additional Files (Full Mode Only)
 
@@ -104,6 +105,13 @@ Stack: [tech stack from architecture.md]
 Stack: [tech stack]
 Architecture: [pattern]
 
+### Repository Structure
+[If project/structure.md exists:]
+[Top-level tree from ## Directory Tree (first level only)]
+Where to find:
+[Entries from ## Where to Find X, condensed to one line each]
+[If project/structure.md does not exist: omit section]
+
 ### Recent Decisions
 [For each decision file, list:]
 - **[Decision title]** — [one-line summary]

package/templates/index.md

@@ -19,6 +19,7 @@
 
 - `project/architecture.md` — Project architecture (not yet documented)
 - `project/requirements.md` — Project requirements (not yet documented)
+- `project/structure.md` — Annotated directory tree (not yet documented)
 
 ## Agent Knowledge
 

package/templates/project/structure.md

@@ -0,0 +1,32 @@
+# Repository Structure
+
+**Status:** active | **Updated:** YYYY-MM-DD
+
+## Directory Tree
+
+<!-- Annotated 2–3 level tree. Update when directories are added or removed. -->
+<!-- Format: path/  — description -->
+
+```
+project-root/
+├── src/           — [description]
+│   └── ...
+└── package.json   — [description]
+```
+
+## Entry Points
+
+<!-- Key files to start reading for each subsystem -->
+- `path/to/entry.file` — [what it does]
+
+## Source vs. Generated
+
+<!-- What is hand-written vs. auto-generated vs. gitignored -->
+- **Source:** `src/`, `tests/`
+- **Generated:** `dist/`, `node_modules/`
+- **Gitignored:** `.mema/`, `node_modules/`, `.env`
+
+## Where to Find X
+
+<!-- Quick-reference for navigating the codebase -->
+- **[Component type]:** `path/to/dir/`