docs(config): describe current sync behavior

docs/configuration.md

@@ -1,6 +1,6 @@
 # Configuration
 
-Codex receives a generated global `AGENTS.md`, agent TOML files, skills, rule files, and a `config.toml` adapter. It keeps workspace sandboxing, automatic approval review, `agents.enabled = true`, `agents.max_concurrent_threads_per_session = 5`, and `agents.max_depth = 1`. Claude Code receives a generated global `CLAUDE.md`, agent Markdown files, skills, and `settings.json` with `auto` permissions, explicit `Agent` permission, and five-operation concurrency. Installation resolves user paths at runtime; the repository contains no machine-specific paths.
+Codex receives a generated global `AGENTS.md`, agent TOML files, skills, rule files, and a `config.toml` adapter. It sets workspace sandboxing, automatic approval review, `agents.enabled = true`, `agents.max_concurrent_threads_per_session = 5`, and `agents.max_depth = 1`. Claude Code receives a generated global `CLAUDE.md`, agent Markdown files, skills, and `settings.json` with `auto` permissions, explicit `Agent` permission, and a five-operation concurrency default. Installation resolves user paths at runtime; the repository contains no machine-specific paths.
 
 Both clients embed `shared/rules/general.md` and the rule-loading conditions from `shared/global-instructions.md`. Rules for languages and frameworks live in their own directories, with an `index.md` entry point and focused Markdown rules under `references/`. Security has its own directory with a baseline entry point and focused rules for authentication, web, APIs, data, files, network, cryptography, and supply chains. Git, Microsoft, and cross-cutting rules remain directly under `shared/rules/`. Codex receives the full directory tree; Claude generates a skill for each rule and copies supporting references alongside the index skill.
 
@@ -12,7 +12,7 @@ Client settings remain thin adapters. Shared semantics remain in `shared/`. User
 
 ## Permission defaults
 
-Codex sets `approval_policy = "on-request"`, `approvals_reviewer = "auto_review"`, and `sandbox_mode = "workspace-write"`. Eligible approval requests go through automatic review; sandboxing remains enabled. Claude sets `permissions.defaultMode = "auto"`. These are generated defaults, not a guarantee that a running session, account policy, or explicit launch override uses the same mode.
+Codex sets `approval_policy = "on-request"`, `approvals_reviewer = "auto_review"`, and `sandbox_mode = "workspace-write"`. Eligible approval requests go through automatic review. Claude sets `permissions.defaultMode = "auto"` and shell-specific deny rules. Its sandbox is enabled on supported macOS, Linux, and WSL2 environments and disabled where unavailable, including native Windows. These are generated defaults, not a guarantee that a running session, account policy, or explicit launch override uses the same mode.
 
 ## Status displays
 
@@ -37,4 +37,4 @@ The agent chooses the smallest sufficient checks based on behavior, affected cal
 
 Delegation and long-running state use the shared orchestration rule, loaded on demand as a Codex rule or Claude skill. The coordinator owns decisions and routes concise evidence-based handoffs. Review and execution verification have separate responsibilities; see [Agents](agents.md).
 
-Rebuild packages after changes to shared definitions or adapters. Generated defaults reach a user's configuration only through installation or update. Updates back up replaced files and preserve Codex's local `model`, `reasoning_effort`, `plugins`, and `marketplaces` settings; other local settings are not generally merged. See [the README](../README.md) for overwrite and backup behavior.
+Rebuild packages after changes to shared definitions or adapters. Generated defaults reach a user's configuration only through installation or update. Updates merge Codex's setup-owned root keys and table fields while retaining other root keys, extra fields in managed tables, plugin and marketplace tables, and unowned array tables. Other standalone tables may be dropped. Claude settings retain unrelated keys and hooks. See [the README](../README.md) for overwrite and backup behavior.

docs/extending-configuration.md

@@ -8,7 +8,7 @@ Create cross-cutting rules such as Git or Microsoft guidance as focused Markdown
 
 ## Add a skill
 
-Create `shared/skills/<category>/<skill>/SKILL.md` with valid YAML frontmatter and a concise workflow. Reference shared rules instead of repeating persistent standards.
+Create `shared/skills/<skill>/SKILL.md` for a standalone skill, or `shared/skills/<category>/<skill>/SKILL.md` for a grouped workflow. Each leaf skill directory must contain a readable `SKILL.md` with valid YAML frontmatter. Keep the initial workflow focused; place longer supporting material under `references/`. Reference shared rules instead of repeating persistent standards.
 
 ## Add an agent
 

docs/plugins.md

@@ -2,7 +2,7 @@
 
 The user-level plugin manifest is `adapters/plugins.tsv`. It maps each logical extension to the client-specific plugin, skill, or MCP installation method.
 
-The current baseline includes Ponytail, i-have-adhd, Superpowers, Context7, Caveman, QMD, Humanizer, Impeccable, and Anthropic Frontend Design. Both scripts operate at user scope and show a plugin selector unless running a dry run. Selections are collected before configuration changes. Both rebuild generated packages first.
+The current baseline includes Ponytail, i-have-adhd, Superpowers, Context7, Caveman, QMD, MCPorter, Humanizer, Impeccable, and Anthropic Frontend Design. Both scripts operate at user scope and show an extension selector unless running a dry run. Selections are collected before configuration changes. Both rebuild generated packages first.
 
 Selecting Context7 with MCPorter registers the server in MCPorter. Selecting Context7 without MCPorter installs its native client plugin; that explicit selection permits the native MCP route under the global instructions.
 
@@ -10,7 +10,7 @@ Selecting Context7 with MCPorter registers the server in MCPorter. Selecting Con
 
 `update.ps1`/`update.sh` lets you revise the saved extension selection. Checking an extension installs it if missing or updates it if owned; existing foreign installations are preserved. Deselection removes only extensions that this setup installed and recorded as owned. Pre-existing or manually installed plugins and skills are retained. Extensions removed from the manifest are also removed when recorded as owned; unrelated installations are retained. Update refuses to run if any selected destination lacks an installation manifest (`Not installed, use the install script.`).
 
-Codex's local `plugins` and `marketplaces` tables survive configuration synchronization. Cached plugin files alone are not treated as proof of installation: selection uses the client CLI's installed list. If an older update removed the registrations, inspect the backed-up `config.toml` under `~/.codex/backups/` and reselect the affected plugins on the next update.
+Codex's local `plugins` and `marketplaces` tables survive configuration synchronization, along with other root keys, extra fields in managed tables, and unowned array tables. Other standalone tables may be dropped; changed files are backed up. Cached plugin files alone are not treated as proof of installation: selection uses the client CLI's installed list. If an older update removed the registrations, inspect the backed-up `config.toml` under `~/.codex/backups/` and reselect the affected plugins on the next update.
 
 Codex receives Caveman through its native plugin adapter. Humanizer, Impeccable, and Anthropic Frontend Design are downloaded as skill payloads from the GitHub sources in the manifest, without running upstream installers. All three appear in the extension selector for Codex. Ownership is recorded in `~/.my-ai-configuration/extensions.json`. Skill files are tracked by hash; modified or foreign files are retained with a warning. Existing installations from before ownership tracking are not automatically adopted.
 
@@ -20,7 +20,7 @@ On Windows, installation and update repair the known Caveman 1.0.0 hook launcher
 
 Normal installation and update ask whether to enable Flashbang, apply the custom status line, and enable the optional Qwen3-Embedding-0.6B semantic retrieval layer. Retrieval uses a per-user virtual environment and index and is invoked through the installed `server.py search` CLI, disabled by default. Quickupdate reuses the saved shell, client, status line, Flashbang, retrieval, and extension choices without opening menus. Disabling the status line removes its custom setting and setup-owned Claude script; disabling retrieval removes its setup-owned runtime and index. Only successful runs save selections; dry runs do not update extensions or retrieval. Install and update do not modify the Codex or Claude CLI installations.
 
-The `server.py search`/`rebuild` CLI transparently reuses a background daemon (spawned automatically on first use per `--data-dir`) that keeps the embedding and reranking models loaded in memory, so only the first query after a cold start or an idle period pays the model-loading cost; every call falls back to loading the models directly in-process if the daemon cannot be reached or started. The daemon exits on its own after 30 minutes of inactivity. Indexing skips files larger than 512 KB and, per repository, stops after 2000 indexable files by default; set `SEMANTIC_RETRIEVAL_MAX_FILES` to raise that cap for larger monorepos. When the cap is reached, the CLI prints an explicit warning to stderr rather than silently omitting files.
+The `server.py search`/`rebuild` CLI transparently reuses a background daemon (spawned automatically on first use per `--data-dir`) that keeps the embedding and reranking models loaded in memory, so only the first query after a cold start or an idle period pays the model-loading cost; every call falls back to loading the models directly in-process if the daemon cannot be reached or started. The daemon exits on its own after 30 minutes of inactivity. Search requires a Git repository and indexes tracked files plus untracked files that Git does not ignore. Indexing skips files larger than 512 KB and, per repository, stops after 2000 indexable files by default; set `SEMANTIC_RETRIEVAL_MAX_FILES` to raise that cap for larger monorepos. When the cap is reached, the CLI prints an explicit warning to stderr rather than silently omitting files.
 
 Plugin installation requires the corresponding client CLI, network access, and any authentication required by the plugin. Context7 may open an OAuth flow. Codex or plugin hooks may require a trust review in `/hooks`. The scripts never install plugins during a build or doctor run and never install them when `--dry-run` or `-DryRun` is used.