agent-toggle 0.12.1__tar.gz → 0.13.1__tar.gz

{agent_toggle-0.12.1 → agent_toggle-0.13.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-toggle
-Version: 0.12.1
+Version: 0.13.1
 Summary: Temporarily disable / re-enable AI-agent skills, agents, commands, rules, plugins and MCP servers across harnesses (Claude Code, Codex, Grok, OpenCode, OpenClaw, Copilot, Vibe, Devin, Antigravity)
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/weskao/agent-toggle
@@ -59,16 +59,17 @@ language, update check and Telegram notifications. It also runs tools such as `d
 
 ![agent-toggle config: the settings menu](https://raw.githubusercontent.com/weskao/agent-toggle/main/docs/images/config-menu.jpeg)
 
-**`/agent-toggle` inside Claude Code**: the same picker as a pane, for turning skills, MCP
-servers, plugins and mods on or off without leaving the session ([Claude Code pane mod](#claude-code-pane-mod)).
+**`/agent-toggle` inside Claude Code**: the same picker as a pane. Search, then turn skills, MCP
+servers, plugins and mods on or off without leaving the session; each toggle applies at once and
+queues the matching reload ([Claude Code pane mod](#claude-code-pane-mod)).
 
-![/agent-toggle: the picker as a Claude Code pane](https://raw.githubusercontent.com/weskao/agent-toggle/main/docs/images/claude-pane-mod.jpeg)
+![/agent-toggle: searching and toggling resources in the Claude Code pane](https://raw.githubusercontent.com/weskao/agent-toggle/main/docs/images/claude-mods-demo.gif)
 
 ## Why
 
 | target | native mechanism | the gap |
 |---|---|---|
-| plugin | `claude plugin disable/enable` | fine — this tool just batches it |
+| plugin | `claude plugin disable/enable` | without `-s` the scope follows the current dir, so a project plugin enabled from elsewhere stays off; this tool pins the install's scope and project |
 | skill | none | moving files by hand hits the rename trap below |
 | agent | none | same |
 | command | none | same, plus nested `group/name.md` paths get flattened |
@@ -146,17 +147,12 @@ tool itself stays in one place.
 **Optional: Telegram alerts for CI** (for maintainers of a fork or clone). The
 Telegram support comes from [telegram-kit](https://pypi.org/project/telegram-kit/)
 (itself stdlib-only), which every install includes, so a reinstall or upgrade keeps
-your settings. Run the setup once; see [CI notifications](#ci-notifications):
-
-```sh
-agent-toggle config                          # settings menu: bot token + chat id live under Notifications
-agent-toggle config sync-ci                  # set the two GitHub repository secrets
-```
+your settings. The settings menu hides its Telegram rows for now; set up the alerts as in
+[CI notifications](#ci-notifications).
 
 The old `agent-toggle[telegram]` extra still resolves and is now a no-op. If
 telegram-kit is missing from a broken install, `config test` and `config sync-ci`
-exit `4`, bare `config` still opens, and the Telegram rows read
-`telegram-kit missing: reinstall agent-toggle`.
+exit `4`.
 
 **Optional: the Claude Code pane mod** (the picker as a pane inside Claude Code, claude harness
 only). It is not part of the PyPI package; with `agent-toggle` already on `PATH` from one of the
@@ -172,16 +168,27 @@ See [Claude Code pane mod](#claude-code-pane-mod).
 
 ## Shell completion
 
-Each release publishes static completion files for bash, zsh and fish as the
-`completions` artifact of its Release workflow run. They are generated from the
-CLI parser; to build them from a checkout:
+`agent-toggle completion <shell>` prints a static completion script, built from the CLI
+parser, for bash, zsh, fish or PowerShell. Save it once where your shell loads it, and
+run the same line again after an upgrade so new commands complete:
 
 ```sh
-python3 tools/gen_completions.py completions   # agent-toggle.bash, _agent-toggle (zsh), agent-toggle.fish
+# zsh: needs fpath=(~/.zfunc $fpath) before compinit in ~/.zshrc
+mkdir -p ~/.zfunc && agent-toggle completion zsh > ~/.zfunc/_agent-toggle
+# bash: loaded on demand by the bash-completion package
+mkdir -p ~/.local/share/bash-completion/completions && agent-toggle completion bash > ~/.local/share/bash-completion/completions/agent-toggle
+# fish
+agent-toggle completion fish > ~/.config/fish/completions/agent-toggle.fish
 ```
 
-Source `agent-toggle.bash` from `~/.bashrc`, put `_agent-toggle` on your zsh
-`fpath`, or copy `agent-toggle.fish` to `~/.config/fish/completions/`.
+```powershell
+# PowerShell: save the script, then load it from your profile
+agent-toggle completion powershell > "$HOME\agent-toggle.ps1"; Add-Content $PROFILE '. "$HOME\agent-toggle.ps1"'
+```
+
+Without the bash-completion package, add `source <file>` to `~/.bashrc` instead.
+`python3 tools/gen_completions.py completions` writes all four files from a checkout; the
+Release workflow uploads them as its `completions` artifact.
 
 ## Usage
 
@@ -258,7 +265,9 @@ unshared).
 `--dry-run` (`disable` / `enable` / `enable --all` / `undo` / `profile apply` /
 `install-shims` / `ui`) computes the plan --
 moves, companions, backups, MCP edits, warnings -- and writes nothing: no state,
-log, lock or backup, and no chmod; it never shells out to `claude`. `disable` /
+log, lock or backup, and no chmod; it never shells out to `claude`, except one
+read-only `claude plugin list --json` (up to 30 s) when a killed run left a plugin
+op pending and has to be settled. `disable` /
 `enable` result rows have action `would-disable` / `would-enable`; every plan
 row has status `planned`. Read-only commands (`list`, `status`, `cost`) also
 change nothing on disk -- `status` warns about a `state.json` or
@@ -391,8 +400,6 @@ a band above the prompt, buttons) and change Claude Code's behaviour. A plugin w
 `hooks.json`, or with only ordinary hooks (shell commands such as `PreToolUse`), is a plain
 plugin: it ships skills, commands, agents, MCP servers or hooks and draws nothing.
 
-![Claude Mods: toggling mods from the picker](https://raw.githubusercontent.com/weskao/agent-toggle/main/docs/images/claude-mods-demo.gif)
-
 - The check reads the install path `claude plugin list` reports and every cached version
   under `~/.claude/plugins/cache/<marketplace>/<name>/`, so a parked mod is still a mod.
   To list the installed mods by hand:
@@ -428,8 +435,7 @@ end of input, `q` or an empty line exits `0`
 | General | Check for updates, Color, Logo, Language, Default harness |
 | Harnesses | one On/Off per harness, with `found ~/.x` or `not on this machine` |
 | Picker | default sort, harness filter, type filter |
-| Notifications | Telegram bot token (masked, last 4 characters shown), Telegram chat ID |
-| Tools | Health check (`doctor`; then asks y/n per fix it can run), Install shims, Undo last change (asks y/n), Send test message, Sync CI secrets (asks y/n); their output shows in an overlay |
+| Tools | Health check (`doctor`; then asks y/n per fix it can run), Install shims, Undo last change (asks y/n); their output shows in an overlay |
 
 Keys: `↑` `↓` move (wraps, skips headings), `←` `→` cycle a value, `Enter` / `Space` change or run
 the row, `r` reset the row, `R` reset everything (asks y/n), `q` / `Esc` / `Ctrl-C` quit. In an
@@ -528,7 +534,9 @@ logo, centred, when the window is tall enough to fit the whole menu beside it; t
 | agy | `~/.gemini/config` | ✓ | — | — | — | — | ✓ `mcp_config.json` |
 
 Per-harness locations, mechanisms and the harness versions this was checked
-against are in [docs/harnesses.md](docs/harnesses.md).
+against are in [docs/harnesses.md](docs/harnesses.md). What `disable` and `enable`
+change on disk for each type, with example live, parked and backup paths, is in
+[docs/toggle-paths.md](docs/toggle-paths.md).
 
 **Homes per OS.** Every `~` above is Python's `Path.home()`: `$HOME` on macOS and
 Linux, `%USERPROFILE%` on Windows (so `~/.claude` is `C:\Users\<you>\.claude`).
@@ -545,8 +553,13 @@ Plugin ids are passed to `claude plugin ...`, which on Windows runs through
 
 Copilot's `config.json` is machine-managed and never edited by this tool; Copilot
 plugins are not yet supported. `claude` plugins are toggled through `claude
-plugin enable/disable`; `openclaw` plugins through a config flag (see [Assumed
-formats](#assumed-formats)). Codex has no plugin CLI this tool can drive: `disable
+plugin enable/disable -s <scope>`. The scope comes from the plugin's one install in
+`~/.claude/plugins/installed_plugins.json`, and a project or local install runs in its
+project dir, so a disable and an enable from different directories still hit the same
+setting. With several installs of one id, the CLI picks the scope from the current dir;
+`enable` then runs in the dir the disable ran in. Details are in
+[docs/toggle-paths.md](docs/toggle-paths.md#plugins). `openclaw` plugins are toggled
+through a config flag (see [Assumed formats](#assumed-formats)). Codex has no plugin CLI this tool can drive: `disable
 plugin x --harness codex` exits `4`, which is why the matrix leaves it unchecked.
 
 Flag items (openclaw plugins and flagged skills, opencode mcp) are toggled with
@@ -568,7 +581,7 @@ rather than guessing.
 
 OpenCode may read skills from another harness's directory through
 `opencode.json` → `skills.paths` (absolute, `~`, `$HOME/...`
-and `${HOME}/...` entries; read from `opencode.json`, else `opencode.jsonc`;
+and `${HOME}/...` entries; read from `opencode.json` and `opencode.jsonc` (OpenCode loads both and merges them);
 relative entries are skipped, since OpenCode resolves them against the session
 directory). OpenCode also always scans `~/.claude/skills` and `~/.agents/skills`,
 so claude's skills count as shared with it. Such a directory is **one** item, filed under
@@ -576,6 +589,11 @@ its owner (the harness whose home really holds it): it is
 parked once, tracked once, and every row reports `shared_with`, the other
 harnesses it also affects. `status` prints `shared dir with: ...`.
 
+Disabling an OpenCode skill while a same-named copy sits in another scanned dir warns
+that OpenCode still loads that copy (stderr, and `warnings` in `--json`). Two copies of
+one name under one owner share one record, so a second `disable` is refused with
+`another copy is already parked at <path> -- enable it first`.
+
 If the live directory carries `.synced-from-*` markers, a sync job may
 re-create what you parked; `status` and `disable` warn about it. Park in the
 source harness instead. The warning is printed once per real directory, naming
@@ -612,6 +630,11 @@ visible rather than silent.
 MCP changes need a **new session** to take effect, except in a Claude Code session running the
 agent-toggle mod, which runs `/mcp disable|enable <name>` for you (see the mod section).
 
+`/mcp disable <name>` also lists the server in that project's `disabledMcpServers` in
+`~/.claude.json`. Left there, a restored server would stay off in that project, so `enable`
+removes the name again: from every project for a user- or local-scope server, and only from
+that repo and the dirs inside it for a `--project` `.mcp.json` server.
+
 ### Claude MCP scopes
 
 Both scopes stored in `~/.claude.json` are togglable, and the scope round-trips:
@@ -875,10 +898,11 @@ a warning and a `recovered` log row (which `undo` does not reverse). `status` an
 `doctor` report it, with `agent-toggle enable ...` when the item ends up
 disabled. The one case left to you is a cross-filesystem move killed between its
 two renames: both copies are complete, and the report names the `diff -r` to
-check and the `rm -rf` that keeps either one. MCP and plugin items are saved
-per item (when the next one starts), without a `pending` record (a project `.mcp.json`
-edit has one): a kill inside that window
-leaves the change unrecorded (an MCP server's backup stays in `mcp-backups/`).
+check and the `rm -rf` that keeps either one. MCP servers (user-scope json,
+claude-json, toml, project `.mcp.json`) and claude plugins have a `pending` record
+too (a plugin is settled from a live `claude plugin list --json`); only a
+`claude.ai` connector toggle is saved per item (when the next one starts), and a
+kill inside that window leaves its change unrecorded.
 A killed run also leaves its `lock`; the next run's error says so.
 
 Each `log.jsonl` row is `{ts, harness, type, name, action, result, batch,
@@ -989,6 +1013,9 @@ claude --plugin-dir ./mod    # then run /agent-toggle inside Claude
   `/reload-plugins`, an MCP server `/mcp disable|enable <name>`. The toast names it, e.g.
   `⛔ [DISABLED] skill: foo (/reload-skills)`. Agents and rules have no reload and still say
   `takes effect in a new session`. If Claude refuses a queued command, a toast says so.
+  `/reload-skills` and `/reload-plugins` only re-read what is on disk. `/mcp disable` also
+  leaves the per-project mark that `enable` clears (see
+  [MCP backups are verbatim](#mcp-backups-are-verbatim)).
 - `agent-toggle ui` in another terminal applies on Enter and writes the Claude rows it changed to
   `~/.agent-toggle/reload.json`. Every open session running the mod checks that file's mtime every
   5 s (one `stat`) and queues the same reloads, toasting `agent-toggle ui: /reload-skills`. A file
@@ -1029,21 +1056,24 @@ it on macOS, Linux and Windows.
 
 ## CI notifications
 
-`.github/workflows/ci.yml` can send a Telegram message when the test matrix fails on a
-push (a lint-only failure does not page). Alerts never fire for pull requests or green
-runs. The message names the repository, branch, 7-character commit and a link to the run.
+CI and the Release workflow can send a Telegram message when they fail: `ci.yml` when the
+test matrix fails on a push (a lint-only failure does not page), `release.yml` when the
+build, PyPI publish or post-publish smoke test fails. Alerts never fire for pull requests or
+green runs. Both call `.github/workflows/notify-telegram.yml`, and the message names the
+failure, repository, tag or branch, 7-character commit and a link to the run.
 
-Set it up once, with the `telegram` extra installed (see [Install](#install)):
+The [settings menu](#settings--config-menu) hides its Telegram rows (bot token, chat ID,
+Send test message, Sync CI secrets) for now; `SHOW_TELEGRAM` in `agent_toggle/ui/config_menu.py`
+brings them back. `config test` and `config sync-ci` still work: they read a bot token and
+chat ID saved earlier, else `TG_BOT_TOKEN` / `TG_CHAT_ID` from the environment. Without
+either, set the secrets by hand (below).
 
 ```sh
-agent-toggle config            # settings menu: Notifications has the bot token (hidden) and chat id
 agent-toggle config test       # send one test message
 agent-toggle config sync-ci    # set TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID on the repo
 ```
 
-In the [settings menu](#settings--config-menu) an inline field commits on `Enter`, cancels on
-`Esc`, and clears on `-` then `Enter`; the Tools group also has Send test message and Sync CI
-secrets (the same as `config test` / `config sync-ci`). The bot token
+When the rows are shown, the bot token
 is kept only in the OS credential store (macOS Keychain, Linux Secret Service, Windows DPAPI)
 through telegram-kit, never in a file or on a command line, and is shown masked. With no
 credential store it refuses to store the token; set `TG_BOT_TOKEN` in the environment instead
@@ -1059,6 +1089,12 @@ gh secret set TELEGRAM_BOT_TOKEN
 gh secret set TELEGRAM_CHAT_ID
 ```
 
+To check the repository secrets themselves, send a test message through the same workflow:
+
+```sh
+gh workflow run notify-telegram.yml    # optional: -f title="..."
+```
+
 With either secret unset (a fork, or a clone you have not configured) the notify job
 prints a `::notice::` and exits 0, so it never adds a second red X.
 

{agent_toggle-0.12.1 → agent_toggle-0.13.1}/README.md

@@ -26,16 +26,17 @@ language, update check and Telegram notifications. It also runs tools such as `d
 
 ![agent-toggle config: the settings menu](https://raw.githubusercontent.com/weskao/agent-toggle/main/docs/images/config-menu.jpeg)
 
-**`/agent-toggle` inside Claude Code**: the same picker as a pane, for turning skills, MCP
-servers, plugins and mods on or off without leaving the session ([Claude Code pane mod](#claude-code-pane-mod)).
+**`/agent-toggle` inside Claude Code**: the same picker as a pane. Search, then turn skills, MCP
+servers, plugins and mods on or off without leaving the session; each toggle applies at once and
+queues the matching reload ([Claude Code pane mod](#claude-code-pane-mod)).
 
-![/agent-toggle: the picker as a Claude Code pane](https://raw.githubusercontent.com/weskao/agent-toggle/main/docs/images/claude-pane-mod.jpeg)
+![/agent-toggle: searching and toggling resources in the Claude Code pane](https://raw.githubusercontent.com/weskao/agent-toggle/main/docs/images/claude-mods-demo.gif)
 
 ## Why
 
 | target | native mechanism | the gap |
 |---|---|---|
-| plugin | `claude plugin disable/enable` | fine — this tool just batches it |
+| plugin | `claude plugin disable/enable` | without `-s` the scope follows the current dir, so a project plugin enabled from elsewhere stays off; this tool pins the install's scope and project |
 | skill | none | moving files by hand hits the rename trap below |
 | agent | none | same |
 | command | none | same, plus nested `group/name.md` paths get flattened |
@@ -113,17 +114,12 @@ tool itself stays in one place.
 **Optional: Telegram alerts for CI** (for maintainers of a fork or clone). The
 Telegram support comes from [telegram-kit](https://pypi.org/project/telegram-kit/)
 (itself stdlib-only), which every install includes, so a reinstall or upgrade keeps
-your settings. Run the setup once; see [CI notifications](#ci-notifications):
-
-```sh
-agent-toggle config                          # settings menu: bot token + chat id live under Notifications
-agent-toggle config sync-ci                  # set the two GitHub repository secrets
-```
+your settings. The settings menu hides its Telegram rows for now; set up the alerts as in
+[CI notifications](#ci-notifications).
 
 The old `agent-toggle[telegram]` extra still resolves and is now a no-op. If
 telegram-kit is missing from a broken install, `config test` and `config sync-ci`
-exit `4`, bare `config` still opens, and the Telegram rows read
-`telegram-kit missing: reinstall agent-toggle`.
+exit `4`.
 
 **Optional: the Claude Code pane mod** (the picker as a pane inside Claude Code, claude harness
 only). It is not part of the PyPI package; with `agent-toggle` already on `PATH` from one of the
@@ -139,16 +135,27 @@ See [Claude Code pane mod](#claude-code-pane-mod).
 
 ## Shell completion
 
-Each release publishes static completion files for bash, zsh and fish as the
-`completions` artifact of its Release workflow run. They are generated from the
-CLI parser; to build them from a checkout:
+`agent-toggle completion <shell>` prints a static completion script, built from the CLI
+parser, for bash, zsh, fish or PowerShell. Save it once where your shell loads it, and
+run the same line again after an upgrade so new commands complete:
 
 ```sh
-python3 tools/gen_completions.py completions   # agent-toggle.bash, _agent-toggle (zsh), agent-toggle.fish
+# zsh: needs fpath=(~/.zfunc $fpath) before compinit in ~/.zshrc
+mkdir -p ~/.zfunc && agent-toggle completion zsh > ~/.zfunc/_agent-toggle
+# bash: loaded on demand by the bash-completion package
+mkdir -p ~/.local/share/bash-completion/completions && agent-toggle completion bash > ~/.local/share/bash-completion/completions/agent-toggle
+# fish
+agent-toggle completion fish > ~/.config/fish/completions/agent-toggle.fish
 ```
 
-Source `agent-toggle.bash` from `~/.bashrc`, put `_agent-toggle` on your zsh
-`fpath`, or copy `agent-toggle.fish` to `~/.config/fish/completions/`.
+```powershell
+# PowerShell: save the script, then load it from your profile
+agent-toggle completion powershell > "$HOME\agent-toggle.ps1"; Add-Content $PROFILE '. "$HOME\agent-toggle.ps1"'
+```
+
+Without the bash-completion package, add `source <file>` to `~/.bashrc` instead.
+`python3 tools/gen_completions.py completions` writes all four files from a checkout; the
+Release workflow uploads them as its `completions` artifact.
 
 ## Usage
 
@@ -225,7 +232,9 @@ unshared).
 `--dry-run` (`disable` / `enable` / `enable --all` / `undo` / `profile apply` /
 `install-shims` / `ui`) computes the plan --
 moves, companions, backups, MCP edits, warnings -- and writes nothing: no state,
-log, lock or backup, and no chmod; it never shells out to `claude`. `disable` /
+log, lock or backup, and no chmod; it never shells out to `claude`, except one
+read-only `claude plugin list --json` (up to 30 s) when a killed run left a plugin
+op pending and has to be settled. `disable` /
 `enable` result rows have action `would-disable` / `would-enable`; every plan
 row has status `planned`. Read-only commands (`list`, `status`, `cost`) also
 change nothing on disk -- `status` warns about a `state.json` or
@@ -358,8 +367,6 @@ a band above the prompt, buttons) and change Claude Code's behaviour. A plugin w
 `hooks.json`, or with only ordinary hooks (shell commands such as `PreToolUse`), is a plain
 plugin: it ships skills, commands, agents, MCP servers or hooks and draws nothing.
 
-![Claude Mods: toggling mods from the picker](https://raw.githubusercontent.com/weskao/agent-toggle/main/docs/images/claude-mods-demo.gif)
-
 - The check reads the install path `claude plugin list` reports and every cached version
   under `~/.claude/plugins/cache/<marketplace>/<name>/`, so a parked mod is still a mod.
   To list the installed mods by hand:
@@ -395,8 +402,7 @@ end of input, `q` or an empty line exits `0`
 | General | Check for updates, Color, Logo, Language, Default harness |
 | Harnesses | one On/Off per harness, with `found ~/.x` or `not on this machine` |
 | Picker | default sort, harness filter, type filter |
-| Notifications | Telegram bot token (masked, last 4 characters shown), Telegram chat ID |
-| Tools | Health check (`doctor`; then asks y/n per fix it can run), Install shims, Undo last change (asks y/n), Send test message, Sync CI secrets (asks y/n); their output shows in an overlay |
+| Tools | Health check (`doctor`; then asks y/n per fix it can run), Install shims, Undo last change (asks y/n); their output shows in an overlay |
 
 Keys: `↑` `↓` move (wraps, skips headings), `←` `→` cycle a value, `Enter` / `Space` change or run
 the row, `r` reset the row, `R` reset everything (asks y/n), `q` / `Esc` / `Ctrl-C` quit. In an
@@ -495,7 +501,9 @@ logo, centred, when the window is tall enough to fit the whole menu beside it; t
 | agy | `~/.gemini/config` | ✓ | — | — | — | — | ✓ `mcp_config.json` |
 
 Per-harness locations, mechanisms and the harness versions this was checked
-against are in [docs/harnesses.md](docs/harnesses.md).
+against are in [docs/harnesses.md](docs/harnesses.md). What `disable` and `enable`
+change on disk for each type, with example live, parked and backup paths, is in
+[docs/toggle-paths.md](docs/toggle-paths.md).
 
 **Homes per OS.** Every `~` above is Python's `Path.home()`: `$HOME` on macOS and
 Linux, `%USERPROFILE%` on Windows (so `~/.claude` is `C:\Users\<you>\.claude`).
@@ -512,8 +520,13 @@ Plugin ids are passed to `claude plugin ...`, which on Windows runs through
 
 Copilot's `config.json` is machine-managed and never edited by this tool; Copilot
 plugins are not yet supported. `claude` plugins are toggled through `claude
-plugin enable/disable`; `openclaw` plugins through a config flag (see [Assumed
-formats](#assumed-formats)). Codex has no plugin CLI this tool can drive: `disable
+plugin enable/disable -s <scope>`. The scope comes from the plugin's one install in
+`~/.claude/plugins/installed_plugins.json`, and a project or local install runs in its
+project dir, so a disable and an enable from different directories still hit the same
+setting. With several installs of one id, the CLI picks the scope from the current dir;
+`enable` then runs in the dir the disable ran in. Details are in
+[docs/toggle-paths.md](docs/toggle-paths.md#plugins). `openclaw` plugins are toggled
+through a config flag (see [Assumed formats](#assumed-formats)). Codex has no plugin CLI this tool can drive: `disable
 plugin x --harness codex` exits `4`, which is why the matrix leaves it unchecked.
 
 Flag items (openclaw plugins and flagged skills, opencode mcp) are toggled with
@@ -535,7 +548,7 @@ rather than guessing.
 
 OpenCode may read skills from another harness's directory through
 `opencode.json` → `skills.paths` (absolute, `~`, `$HOME/...`
-and `${HOME}/...` entries; read from `opencode.json`, else `opencode.jsonc`;
+and `${HOME}/...` entries; read from `opencode.json` and `opencode.jsonc` (OpenCode loads both and merges them);
 relative entries are skipped, since OpenCode resolves them against the session
 directory). OpenCode also always scans `~/.claude/skills` and `~/.agents/skills`,
 so claude's skills count as shared with it. Such a directory is **one** item, filed under
@@ -543,6 +556,11 @@ its owner (the harness whose home really holds it): it is
 parked once, tracked once, and every row reports `shared_with`, the other
 harnesses it also affects. `status` prints `shared dir with: ...`.
 
+Disabling an OpenCode skill while a same-named copy sits in another scanned dir warns
+that OpenCode still loads that copy (stderr, and `warnings` in `--json`). Two copies of
+one name under one owner share one record, so a second `disable` is refused with
+`another copy is already parked at <path> -- enable it first`.
+
 If the live directory carries `.synced-from-*` markers, a sync job may
 re-create what you parked; `status` and `disable` warn about it. Park in the
 source harness instead. The warning is printed once per real directory, naming
@@ -579,6 +597,11 @@ visible rather than silent.
 MCP changes need a **new session** to take effect, except in a Claude Code session running the
 agent-toggle mod, which runs `/mcp disable|enable <name>` for you (see the mod section).
 
+`/mcp disable <name>` also lists the server in that project's `disabledMcpServers` in
+`~/.claude.json`. Left there, a restored server would stay off in that project, so `enable`
+removes the name again: from every project for a user- or local-scope server, and only from
+that repo and the dirs inside it for a `--project` `.mcp.json` server.
+
 ### Claude MCP scopes
 
 Both scopes stored in `~/.claude.json` are togglable, and the scope round-trips:
@@ -842,10 +865,11 @@ a warning and a `recovered` log row (which `undo` does not reverse). `status` an
 `doctor` report it, with `agent-toggle enable ...` when the item ends up
 disabled. The one case left to you is a cross-filesystem move killed between its
 two renames: both copies are complete, and the report names the `diff -r` to
-check and the `rm -rf` that keeps either one. MCP and plugin items are saved
-per item (when the next one starts), without a `pending` record (a project `.mcp.json`
-edit has one): a kill inside that window
-leaves the change unrecorded (an MCP server's backup stays in `mcp-backups/`).
+check and the `rm -rf` that keeps either one. MCP servers (user-scope json,
+claude-json, toml, project `.mcp.json`) and claude plugins have a `pending` record
+too (a plugin is settled from a live `claude plugin list --json`); only a
+`claude.ai` connector toggle is saved per item (when the next one starts), and a
+kill inside that window leaves its change unrecorded.
 A killed run also leaves its `lock`; the next run's error says so.
 
 Each `log.jsonl` row is `{ts, harness, type, name, action, result, batch,
@@ -956,6 +980,9 @@ claude --plugin-dir ./mod    # then run /agent-toggle inside Claude
   `/reload-plugins`, an MCP server `/mcp disable|enable <name>`. The toast names it, e.g.
   `⛔ [DISABLED] skill: foo (/reload-skills)`. Agents and rules have no reload and still say
   `takes effect in a new session`. If Claude refuses a queued command, a toast says so.
+  `/reload-skills` and `/reload-plugins` only re-read what is on disk. `/mcp disable` also
+  leaves the per-project mark that `enable` clears (see
+  [MCP backups are verbatim](#mcp-backups-are-verbatim)).
 - `agent-toggle ui` in another terminal applies on Enter and writes the Claude rows it changed to
   `~/.agent-toggle/reload.json`. Every open session running the mod checks that file's mtime every
   5 s (one `stat`) and queues the same reloads, toasting `agent-toggle ui: /reload-skills`. A file
@@ -996,21 +1023,24 @@ it on macOS, Linux and Windows.
 
 ## CI notifications
 
-`.github/workflows/ci.yml` can send a Telegram message when the test matrix fails on a
-push (a lint-only failure does not page). Alerts never fire for pull requests or green
-runs. The message names the repository, branch, 7-character commit and a link to the run.
+CI and the Release workflow can send a Telegram message when they fail: `ci.yml` when the
+test matrix fails on a push (a lint-only failure does not page), `release.yml` when the
+build, PyPI publish or post-publish smoke test fails. Alerts never fire for pull requests or
+green runs. Both call `.github/workflows/notify-telegram.yml`, and the message names the
+failure, repository, tag or branch, 7-character commit and a link to the run.
 
-Set it up once, with the `telegram` extra installed (see [Install](#install)):
+The [settings menu](#settings--config-menu) hides its Telegram rows (bot token, chat ID,
+Send test message, Sync CI secrets) for now; `SHOW_TELEGRAM` in `agent_toggle/ui/config_menu.py`
+brings them back. `config test` and `config sync-ci` still work: they read a bot token and
+chat ID saved earlier, else `TG_BOT_TOKEN` / `TG_CHAT_ID` from the environment. Without
+either, set the secrets by hand (below).
 
 ```sh
-agent-toggle config            # settings menu: Notifications has the bot token (hidden) and chat id
 agent-toggle config test       # send one test message
 agent-toggle config sync-ci    # set TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID on the repo
 ```
 
-In the [settings menu](#settings--config-menu) an inline field commits on `Enter`, cancels on
-`Esc`, and clears on `-` then `Enter`; the Tools group also has Send test message and Sync CI
-secrets (the same as `config test` / `config sync-ci`). The bot token
+When the rows are shown, the bot token
 is kept only in the OS credential store (macOS Keychain, Linux Secret Service, Windows DPAPI)
 through telegram-kit, never in a file or on a command line, and is shown masked. With no
 credential store it refuses to store the token; set `TG_BOT_TOKEN` in the environment instead
@@ -1026,6 +1056,12 @@ gh secret set TELEGRAM_BOT_TOKEN
 gh secret set TELEGRAM_CHAT_ID
 ```
 
+To check the repository secrets themselves, send a test message through the same workflow:
+
+```sh
+gh workflow run notify-telegram.yml    # optional: -f title="..."
+```
+
 With either secret unset (a fork, or a clone you have not configured) the notify job
 prints a `::notice::` and exits 0, so it never adds a second red X.
 

{agent_toggle-0.12.1 → agent_toggle-0.13.1}/agent_toggle/__init__.py

@@ -1,3 +1,3 @@
 """agent-toggle: temporarily disable / re-enable AI-agent resources."""
 
-__version__ = "0.12.1"
+__version__ = "0.13.1"

{agent_toggle-0.12.1 → agent_toggle-0.13.1}/agent_toggle/backends/mcp_json.py

@@ -58,11 +58,12 @@ def claudeai_connector_names() -> set[str]:
     return set(cfg.get("claudeAiMcpEverConnected", []) or [])
 
 
-def toggle_claudeai_connector(action: str, name: str,
-                              dry_run: bool = False) -> tuple[bool, list | str]:
+def toggle_claudeai_connector(action: str, name: str, dry_run: bool = False,
+                              under: Path | None = None) -> tuple[bool, list | str]:
     """Fan a claude.ai connector on/off across every EXISTING project entry
     in ~/.claude.json's disabledMcpServers list -- the only place /mcp writes
-    that state; no `claude mcp` CLI verb reaches it.
+    that state; no `claude mcp` CLI verb reaches it. `under`: only the project
+    entries that are that dir or inside it.
 
     ponytail: covers projects that exist now; a project dir opened for the
     first time later starts without the entry until this is re-run for it.
@@ -75,7 +76,8 @@ def toggle_claudeai_connector(action: str, name: str,
 
     touched = []
     for proj, pdata in cfg.get("projects", {}).items():
-        if not isinstance(pdata, dict):
+        if not isinstance(pdata, dict) or (
+                under is not None and under != Path(proj) and under not in Path(proj).parents):
             continue
         cur = pdata.get("disabledMcpServers") or []
         has = name in cur

{agent_toggle-0.12.1 → agent_toggle-0.13.1}/agent_toggle/backends/plugin_cli.py

@@ -10,6 +10,7 @@ import os
 import shutil
 import subprocess
 import sys
+from pathlib import Path
 from typing import Callable
 
 from .. import fs
@@ -17,6 +18,8 @@ from .. import fs
 which = shutil.which
 runner = subprocess.run
 
+PLUGIN_SCOPES = ("user", "project", "local")      # `claude plugin enable|disable -s`
+
 TIMEOUT_ENV = "AGENT_TOGGLE_CLI_TIMEOUT"
 MUTATE_TIMEOUT = 120      # enable / disable / install / mcp add|remove: may fetch from a marketplace
 READ_TIMEOUT = 30         # read-only `plugin list`
@@ -59,8 +62,8 @@ def run_cli(binary: str | None, args: list[str], cwd: str | None = None,
         return False, "CLI not found on PATH"
     limit = _timeout(timeout)
     try:
-        p = runner([binary, *args], capture_output=True, text=True,
-                   timeout=limit, cwd=cwd)
+        p = runner([binary, *args], capture_output=True, text=True, encoding="utf-8",
+                   errors="replace", timeout=limit, cwd=cwd)     # Windows: not cp1252
     except subprocess.TimeoutExpired:
         return False, f"CLI timed out after {limit:g}s (raise it with {TIMEOUT_ENV}=<seconds>)"
     except OSError as e:                     # cwd gone, binary unexecutable
@@ -68,18 +71,46 @@ def run_cli(binary: str | None, args: list[str], cwd: str | None = None,
     return p.returncode == 0, (p.stdout + p.stderr).strip()
 
 
-def list_plugins(warn: Callable[[str], None]) -> list[dict]:
-    """`claude plugin list --json` through the injectable runner; [] when unavailable."""
+def plugin_where(name: str, claude_home: Path) -> tuple[str | None, str | None]:
+    """(scope, cwd) of plugin `name`'s one install, from Claude Code's install registry
+    (`<claude_home>/plugins/installed_plugins.json`; a bare name: its one `name@mkt` id).
+
+    Without `-s` the CLI picks the scope from its cwd, so a project-scope plugin toggled
+    from another dir lands in user scope. (None, None) when the registry cannot say --
+    absent, another shape, several installs, a project dir that is gone: the caller
+    then lets the CLI auto-detect, as before. A file read, not `claude plugin list`
+    (~0.8 s per call, paid on every pane toggle)."""
+    try:
+        reg = json.loads((claude_home / "plugins" / "installed_plugins.json")
+                         .read_text(encoding="utf-8"))
+        rows = [r for k, v in reg["plugins"].items()
+                if k == name or ("@" not in name and k.partition("@")[0] == name) for r in v]
+    except (OSError, ValueError, KeyError, TypeError, AttributeError):
+        return None, None
+    if len(rows) != 1 or not isinstance(rows[0], dict) or rows[0].get("scope") not in PLUGIN_SCOPES:
+        return None, None
+    scope, proj = rows[0]["scope"], rows[0].get("projectPath")
+    if scope == "user":
+        return scope, None
+    if isinstance(proj, str) and os.path.isabs(proj) and os.path.isdir(proj):
+        return scope, proj
+    return None, None
+
+
+def list_plugins(warn: Callable[[str], None], cwd: str | None = None) -> list[dict]:
+    """`claude plugin list --json` through the injectable runner; [] when unavailable.
+    `cwd`: its `enabled` is the plugin's state as seen from there."""
     exe = claude_bin()
     if not exe:
         return []
-    ok, text = run_cli(exe, ["plugin", "list", "--json"], timeout=READ_TIMEOUT)
+    ok, text = run_cli(exe, ["plugin", "list", "--json"], cwd=cwd, timeout=READ_TIMEOUT)
     try:       # run_cli merges stderr into the text: skip any notice before the array
         data = json.JSONDecoder().raw_decode(text, max(text.find("["), 0))[0] if ok else None
     except ValueError:
         data = None
     if not isinstance(data, list):
-        warn("could not read `claude plugin list --json`; plugin rows come from state only")
+        why = f" ({text.splitlines()[-1][:120]})" if not ok and text else ""   # e.g. a timeout
+        warn(f"could not read `claude plugin list --json`{why}; plugin rows come from state only")
         return []
     return [p for p in data if isinstance(p, dict) and isinstance(p.get("id"), str)]