refactor(plugin-source): per-platform routing + auto-generate bob commands

Three changes that compose:

1. Bob commands are now derived 1:1 from the skills walk in build_plugins.py
   instead of static plugin-source/commands/*.md files. Each command file
   uses `description` from the skill's SKILL.md frontmatter (bob's command
   schema only honors `description` / `argument-hints` — the slash-command
   identifier comes from the file name). The body references the on-disk
   folder name (`evolve-lite-<skill>`, dash form) since that's what bob
   resolves skills by; folders stay colon-free for Windows compatibility.

2. Per-platform routing: any source file under `plugin-source/_<platform>/`
   ships only to that platform, with the `_<platform>/` prefix stripped
   from the output target. This is how single-platform artifacts now live
   alongside the universal sources:
     - _bob/custom_modes.yaml         (bob's mandatory workflow definition)
     - _bob/README.md
     - _claude/hooks/hooks.json       (Stop / UserPromptSubmit / SessionStart)
     - _claude/README.md
     - _claw-code/hooks/retrieve_entities.sh
     - _claw-code/README.md
     - _codex/README.md

3. render_to() now wipes each platform's plugin_root before writing, so
   files removed from plugin-source/ (renamed skills, deleted scripts,
   obsolete commands) cannot linger as orphans. Together with (2), this
   makes platform-integrations/ fully derivable from plugin-source/.

Also drops the now-dead `^commands/` target_excludes from claude / claw-code
/ codex, since the static commands directory is gone.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: illeatmyhat

platform-integrations/bob/evolve-lite/commands/evolve-lite-learn.md

@@ -1,5 +1,4 @@
 ---
-name: evolve-lite:learn
-description: Run the evolve-lite:learn skill on the current conversation
+description: Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.
 ---
-Use the evolve-lite:learn skill on the current conversation. Follow the skill's instructions exactly.
+Use the `evolve-lite-learn` skill on the current conversation. Follow the skill's instructions exactly.

platform-integrations/bob/evolve-lite/commands/evolve-lite-publish.md

@@ -1,5 +1,4 @@
 ---
-name: evolve-lite:publish
-description: Publish a private guideline to a configured write-scope repo
+description: Publish a private guideline to a configured write-scope repo.
 ---
-Use the evolve-lite:publish skill to share your private guidelines via a configured write-scope repo. Follow the skill's instructions exactly.
+Use the `evolve-lite-publish` skill on the current conversation. Follow the skill's instructions exactly.

platform-integrations/bob/evolve-lite/commands/evolve-lite-recall.md

@@ -1,5 +1,4 @@
 ---
-name: evolve-lite:recall
-description: Run the evolve-lite:recall skill on the current conversation
+description: Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
 ---
-Use the evolve-lite:recall skill on the current conversation. Follow the skill's instructions exactly.
+Use the `evolve-lite-recall` skill on the current conversation. Follow the skill's instructions exactly.

platform-integrations/bob/evolve-lite/commands/evolve-lite-save-trajectory.md

@@ -1,5 +1,4 @@
 ---
-name: evolve-lite:save-trajectory
-description: Save the current conversation trajectory as a JSON file
+description: Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning
 ---
-Use the evolve-lite:save-trajectory skill on the current conversation. Follow the skill's instructions exactly.
+Use the `evolve-lite-save-trajectory` skill on the current conversation. Follow the skill's instructions exactly.

platform-integrations/bob/evolve-lite/commands/evolve-lite-save.md

@@ -1,5 +1,4 @@
 ---
-name: evolve-lite:save
-description: Capture the current session's successful workflow as a reusable skill
+description: Captures the current session's successful workflow and saves it as a reusable skill with SKILL.md and helper scripts
 ---
-Use the evolve-lite:save skill to capture the current session's workflow as a reusable skill in your skills directory. Follow the skill's instructions exactly.
+Use the `evolve-lite-save` skill on the current conversation. Follow the skill's instructions exactly.

platform-integrations/bob/evolve-lite/commands/evolve-lite-subscribe.md

@@ -1,5 +1,4 @@
 ---
-name: evolve-lite:subscribe
-description: Add a shared guidelines repo (read- or write-scope) to the unified repos list
+description: Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.
 ---
-Use the evolve-lite:subscribe skill to add a shared guidelines repo — either a read-scope subscription or a write-scope publish target. Follow the skill's instructions exactly.
+Use the `evolve-lite-subscribe` skill on the current conversation. Follow the skill's instructions exactly.

platform-integrations/bob/evolve-lite/commands/evolve-lite-sync.md

@@ -1,5 +1,4 @@
 ---
-name: evolve-lite:sync
-description: Pull the latest guidelines from every configured repo (read- and write-scope)
+description: Pull the latest guidelines from every configured repo (read- and write-scope).
 ---
-Use the evolve-lite:sync skill to update your configured guidelines repos. Follow the skill's instructions exactly.
+Use the `evolve-lite-sync` skill on the current conversation. Follow the skill's instructions exactly.

platform-integrations/bob/evolve-lite/commands/evolve-lite-unsubscribe.md

@@ -1,5 +1,4 @@
 ---
-name: evolve-lite:unsubscribe
-description: Remove a repo from the unified repos list and delete its local clone
+description: Remove a repo from the unified repos list and delete its local clone.
 ---
-Use the evolve-lite:unsubscribe skill to remove a configured repo and delete its local clone. Follow the skill's instructions exactly.
+Use the `evolve-lite-unsubscribe` skill on the current conversation. Follow the skill's instructions exactly.

plugin-source/_bob/README.md

@@ -0,0 +1,225 @@
+# Evolve Lite for Bob
+
+A Bob integration that helps you learn from conversations by automatically extracting and applying guidelines.
+
+⭐ Star the repo: https://github.com/AgentToolkit/altk-evolve
+
+## Features
+
+- **Manual Learning**: Use `evolve-lite:learn` to extract and save guidelines from conversations
+- **Manual Retrieval**: Use `evolve-lite:recall` to retrieve and apply stored guidelines
+- **Guideline Sharing**: Subscribe to read-scope repos and publish to write-scope repos via Git
+
+## Installation
+
+Run the installation script from the repository root:
+
+```bash
+bash platform-integrations/install.sh install bob lite
+```
+
+This installs:
+- 6 skills in `~/.bob/skills/`
+- Shared library in `~/.bob/evolve-lib/`
+- Custom mode configuration
+
+## How It Works
+
+### Guideline Storage
+
+Guidelines are stored as individual markdown files in `.evolve/entities/`,
+organized by source. Both read-scope subscriptions and write-scope publish
+targets live under `entities/subscribed/{name}/`:
+
+```text
+.evolve/entities/
+  guideline/                            # Private guidelines
+    use-context-managers.md
+  subscribed/
+    memory/                             # write-scope clone (publishes land here)
+      guideline/
+        my-published-guideline.md
+    alice/                              # read-scope clone
+      guideline/
+        her-guideline.md
+```
+
+Each file uses markdown with YAML frontmatter:
+
+```markdown
+---
+type: guideline
+trigger: When processing files or managing resources
+visibility: private
+---
+
+Use context managers for file operations
+
+## Rationale
+
+Context managers ensure proper resource cleanup
+```
+
+## Sharing Guidelines
+
+Evolve Lite treats shared guidelines as multi-reader / multi-writer git
+databases. A single unified `repos:` list in `evolve.config.yaml`
+describes every external guideline repo; each entry has a `scope` of
+`read` (subscribe only) or `write` (publish target that is also pulled
+on sync).
+
+### Setup
+
+Sharing requires `evolve.config.yaml` at the project root. If it doesn't
+exist, the subscribe or publish skills will prompt you to create one.
+Minimal structure:
+
+```yaml
+identity:
+  user: yourname          # used to stamp ownership on published guidelines
+
+repos:
+  - name: memory
+    scope: write
+    remote: git@github.com:yourname/evolve-memory.git
+    branch: main
+    notes: public memory for my open-source projects
+  - name: team
+    scope: read
+    remote: git@github.com:myorg/evolve-guidelines.git
+    branch: main
+
+sync:
+  on_session_start: false
+```
+
+The `.evolve/` directory is kept out of version control — the skills
+automatically add it to `.gitignore`.
+
+### Subscribing to a Repo
+
+Use `evolve-lite:subscribe` to add either a read-scope subscription or a
+write-scope publish target:
+
+```text
+evolve-lite:subscribe
+> Remote URL: git@github.com:alice/evolve-guidelines.git
+> Short name: alice
+> Scope: read
+```
+
+The repo is cloned directly into `.evolve/entities/subscribed/{name}/`
+(this directory serves as both the git clone and the recall mirror).
+
+### Publishing Guidelines
+
+Use `evolve-lite:publish` to share local guidelines via a **write-scope** repo:
+
+1. The skill picks (or asks about) the write-scope target repo
+2. Lists files in `.evolve/entities/guideline/`
+3. You pick which ones to publish
+4. Each selected file is moved into the write-scope clone at
+   `.evolve/entities/subscribed/{repo}/guideline/`, stamped with your
+   username, committed, and pushed to the remote
+
+Because the publish target is also a subscribed repo, your next sync
+pulls in anything other writers have pushed to the same remote.
+
+### Syncing Repos
+
+Use `evolve-lite:sync` to pull the latest changes from every configured
+repo:
+
+```text
+evolve-lite:sync
+> Synced 2 repo(s): memory [write] (+0 added, 1 updated, 0 removed), alice [read] (+2 added, 0 updated, 0 removed)
+```
+
+Read-scope repos use `git fetch` + `git reset --hard`. Write-scope repos
+use `git fetch` + `git rebase` so any unpushed local publish commits are
+preserved.
+
+### Unsubscribing
+
+Use `evolve-lite:unsubscribe` to remove a configured repo and delete
+its locally cloned files:
+
+```text
+evolve-lite:unsubscribe
+> Which repo would you like to remove?
+> 1. memory [write]
+> 2. alice [read]
+```
+
+The skill confirms before deleting `.evolve/entities/subscribed/{name}/`.
+Removing a write-scope repo will also discard any unpushed local
+publish commits, so the skill warns first.
+
+### Sharing Storage Layout
+
+```text
+.evolve/
+  entities/
+    guideline/                      # your private guidelines
+      my-guideline.md
+    subscribed/
+      memory/                       # write-scope clone (publishes land here)
+        guideline/
+          my-published-guideline.md
+      alice/                        # read-scope clone (also serves as recall mirror)
+        guideline/
+          her-guideline.md
+```
+
+## Skills Included
+
+### `evolve-lite:learn`
+
+Manually invoke to extract guidelines from the current conversation:
+- Analyzes task, steps taken, successes and failures
+- Generates proactive guidelines (what to do, not what to avoid)
+- Saves guidelines as markdown files in `.evolve/entities/guideline/`
+
+### `evolve-lite:recall`
+
+Manually invoke to retrieve and display stored guidelines:
+- Loads guidelines from private and subscribed sources
+- Formats and displays them for your review
+- Annotates subscribed guidelines with their source
+
+### `evolve-lite:publish`
+
+Publish private guidelines to a write-scope repo:
+- Lists available private guidelines
+- Moves selected guidelines into the write-scope clone at
+  `.evolve/entities/subscribed/{repo}/guideline/`
+- Stamps with `owner`, `published_at`, and `source` metadata
+- Commits and pushes to the configured remote
+
+### `evolve-lite:subscribe`
+
+Add a configured repo to the unified `repos:` list:
+- Clones the remote into `.evolve/entities/subscribed/{name}/`
+- Adds an entry with `scope: read` or `scope: write` to config
+
+### `evolve-lite:sync`
+
+Sync every configured repo:
+- Read-scope: fetch + reset --hard (clobbers any local edits)
+- Write-scope: fetch + rebase (preserves unpushed local publishes)
+- Reports changes (added, updated, removed)
+
+### `evolve-lite:unsubscribe`
+
+Remove a configured repo:
+- Lists current repos with their scope and notes
+- Deletes the local clone at `.evolve/entities/subscribed/{name}/`
+- Removes the entry from config
+
+## Environment Variables
+
+- `EVOLVE_DIR`: Override the default `.evolve` directory location (guidelines, config, etc. are stored here)
+
+## Verification
+
+After installation, the skills should be available in Bob's skill list.

plugin-source/_bob/custom_modes.yaml

@@ -0,0 +1,71 @@
+customModes:
+  - slug: evolve-lite
+    name: Evolve Lite
+    roleDefinition: |-
+      You are Evolve Lite — a learning mode that improves from every interaction.
+
+      ⚠️ CRITICAL: THE FOLLOWING WORKFLOW IS ABSOLUTELY MANDATORY AND CANNOT BE SKIPPED ⚠️
+
+      WORKFLOW (4 steps, strict order):
+
+      1. ⚠️ FIRST ACTION (MANDATORY): Use the evolve-lite:recall skill to retrieve relevant guidelines.
+         - This MUST be your FIRST action in EVERY conversation
+         - NO exceptions - even for simple tasks like "echo hello world"
+      2. WORK: Complete the user's request. When a retrieved guideline applies, cite it in your reasoning.
+      3. ⚠️ SECOND-TO-LAST ACTION (MANDATORY): Use the evolve-lite:save-trajectory skill to save the conversation.
+         - This MUST happen BEFORE evolve-lite:learn
+         - Note the trajectory file path from its output — you will need it in Step 4
+      4. ⚠️ LAST ACTION (MANDATORY): Use the evolve-lite:learn skill to extract and save learnings.
+         - This MUST happen BEFORE attempt_completion
+         - NO exceptions - even if you think there's nothing to learn
+
+      Before using any skill for the first time in a conversation, read its
+      SKILL.md so you know the exact invocation syntax. Bob installs skills
+      under `.bob/skills/`; the runtime will resolve a skill by name.
+
+      ⚠️ ENFORCEMENT RULES ⚠️
+      - Do not skip steps. Do not reorder steps.
+      - Step 1 must happen before any other tool use (except a one-time
+        SKILL.md read for a skill you have not invoked yet).
+      - Step 3 must happen before Step 4.
+      - Step 4 must happen before attempt_completion.
+      - If you forget Step 1, STOP and call evolve-lite:recall immediately.
+      - If you reach attempt_completion without Steps 3 and 4, STOP and complete them first.
+    customInstructions: |-
+      - ALWAYS read a skill's SKILL.md before using it for the first time in a conversation
+      - If evolve-lite:recall returns no guidelines, that is normal — proceed with the task.
+      - If evolve-lite:learn reports no new entities, that counts as successful completion — do not retry.
+      - The trajectory path from evolve-lite:save-trajectory is available in conversation context — do not re-run it.
+      - If no errors or non-obvious discoveries occurred, saving zero entities is correct — do not force low-quality entities.
+
+      MEMORY SHARING (Optional):
+      Additional evolve-lite skills handle sharing guidelines with others
+      (publish, subscribe, unsubscribe, sync). They are OPTIONAL and do not
+      affect the core workflow. Use them when you want to share your
+      learnings with teammates, learn from others' guidelines, or keep
+      subscribed guidelines up to date. Read the SKILL.md for any of these
+      before first use.
+
+      PRE-COMPLETION GATE:
+      Before calling attempt_completion, ask yourself:
+      ┌─────────────────────────────────────────────────────────────────┐
+      │ Did I run the evolve-lite:recall skill at the start?            │
+      │ Did I run the evolve-lite:save-trajectory skill and note the path?│
+      │ Did I run the evolve-lite:learn skill and see its output?       │
+      │                                                                 │
+      │ ❌ NO  → STOP. Go back and complete the step.                   │
+      │ ✅ YES → Proceed with attempt_completion.                       │
+      └─────────────────────────────────────────────────────────────────┘
+
+      Rules:
+
+      - Before using a skill for the first time, read its SKILL.md file to understand the correct usage syntax.
+      - ALWAYS call the evolve-lite:learn skill before attempt_completion, even if the task seems simple or you think there's nothing to learn.
+      - The workflow is non-negotiable: recall → work → evolve-lite:save-trajectory → learn → complete.
+      - Skipping evolve-lite:learn violates the core purpose of this mode.
+
+    groups:
+      - read
+      - edit
+      - command
+      - browser