command-code 1.0.0 → 1.1.0

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # command-code
 
+## 1.1.0
+
+### Minor Changes
+
+- fix: /reload header
+  feat: improve mods and cmd knowledge internal docs
+
 ## 1.0.0
 
 ### Major Changes

package/dist/bundled/command-code-knowledge/SKILL.md

@@ -36,7 +36,8 @@ the matching reference file.
 - `reference/memory.md` — Memory
 - `reference/headless.md` — Headless Mode
 - `reference/plan-mode.md` — Plan Mode and Auto-Accept Mode
-- `reference/checkpoints.md` — Checkpoints
+- `reference/plan-review.md` — Plan Review
+- `reference/checkpoints.md` — Sessions & Checkpoints
 - `reference/models.md` — Command Code Models
 - `reference/product-help.md` — Product help (slash commands, CLI, taste, FAQ, pricing)
 <!-- generated:reference-index:end -->

package/dist/bundled/command-code-knowledge/reference/custom-agents.md

@@ -58,10 +58,10 @@ After generation, you’ll confirm tools and save. Manual creation follows the s
 
 Each agent is a **Markdown file** with YAML front matter and a body that becomes the **system prompt**.
 
-- **`name`** — Identifier and filename (e.g. `security-review.md` → agent `security-review`).
-- **`description`** — Tells Command Code **when** to use this agent.
-- **`tools`** — Comma-separated tool list, **`"*"`** for all tools, or a restriction such as read-only style lists.
-- **`model`** — Optional model this agent always runs on (any `/model` id, e.g. `deepseek/deepseek-v4-pro` or `claude-sonnet-5`). Omit it or set `model: inherit` to follow the session's current model. Per-agent models let you pin deep-reasoning models to architect/planner agents while implementation or docs agents ride faster, cheaper ones — each keeps its own prompt cache.
+- **`name`** - Identifier and filename (e.g. `security-review.md` → agent `security-review`).
+- **`description`** - Tells Command Code **when** to use this agent.
+- **`tools`** - Comma-separated tool list, **`"*"`** for all tools, or a restriction such as read-only style lists.
+- **`model`** - Optional model this agent always runs on (any `/model` id, e.g. `deepseek/deepseek-v4-pro` or `claude-sonnet-5`). Omit it or set `model: inherit` to follow the session's current model. Per-agent models let you pin deep-reasoning models to architect/planner agents while implementation or docs agents ride faster, cheaper ones - each keeps its own prompt cache.
 
 Do not use reserved names for custom agents: `explore`, `plan`, `review`, and `general`. Those names are reserved for built-in or internal behavior; custom files with those names are ignored.
 
@@ -86,6 +86,6 @@ You can edit files directly in `.commandcode/agents/` or `~/.commandcode/agents/
 
 ## Next steps
 
-- [Interactive mode](https://commandcode.ai/docs/core-concepts/interactive-mode) — slash commands and session controls
-- [Memory](./memory.md) — project and user instructions in `AGENTS.md`
-- [Skills](./skills.md) — reusable skill packages vs. full subagents
+- [Interactive mode](https://commandcode.ai/docs/core-concepts/interactive-mode) - slash commands and session controls
+- [Memory](./memory.md) - project and user instructions in `AGENTS.md`
+- [Skills](./skills.md) - reusable skill packages vs. full subagents

package/dist/bundled/command-code-knowledge/reference/custom-slash-commands.md

@@ -8,7 +8,7 @@ Command Code includes built-in slash commands for interactive workflows, and als
 
 ## Built-in Slash Commands
 
-For the full list of built-in slash commands, see [Interactive Mode — Slash Commands](https://commandcode.ai/docs/reference/cli#cli-slash-commands).
+For the full list of built-in slash commands, see [Interactive Mode - Slash Commands](https://commandcode.ai/docs/reference/cli#cli-slash-commands).
 
 ---
 
@@ -171,15 +171,15 @@ Summarize the current state in ${1:-7} bullet points.
 /summarize 3      # → "Summarize the current state in 3 bullet points."
 ```
 
-Defaults work with `$@`/`$ARGUMENTS` as well — `${@:-the current diff}` uses all
+Defaults work with `$@`/`$ARGUMENTS` as well - `${@:-the current diff}` uses all
 arguments when provided, otherwise the literal text `the current diff`.
 
 ### Argument Slices with `${@:N}` and `${@:N:L}`
 
 Select a range of positional arguments (1-indexed) and join them with spaces:
 
-- `${@:N}` — every argument from the Nth position to the end
-- `${@:N:L}` — `L` arguments starting at the Nth position
+- `${@:N}` - every argument from the Nth position to the end
+- `${@:N:L}` - `L` arguments starting at the Nth position
 
 **Command definition** (`.commandcode/commands/commit.md`):
 
@@ -303,7 +303,7 @@ Include:
 | `$ARGUMENTS` / `$@` | All arguments as string                       | `unit Jest async` | `unit Jest async` |
 | `$1`                | First argument                                | `unit Jest`       | `unit`            |
 | `$2`                | Second argument                               | `unit Jest`       | `Jest`            |
-| `$N`                | Nth argument                                  | —                 | —                 |
+| `$N`                | Nth argument                                  | -                 | -                 |
 | `${N}`              | Braced Nth argument (safe next to other text) | `unit Jest`       | `unit`            |
 | `${N:-default}`     | Nth argument, or `default` when missing/empty | `` (none)         | `default`         |
 | `${@:N}`            | Arguments from the Nth position to the end    | `a b c`           | `b c` (N=2)       |

package/dist/bundled/command-code-knowledge/reference/headless.md

@@ -46,7 +46,7 @@ Command Code auto-detects piped input when no query argument is provided. If std
 
 ## Permissions
 
-By default, headless mode **blocks tools that modify your system** — file writes, file edits, and shell commands are denied. This keeps automated runs safe.
+By default, headless mode **blocks tools that modify your system** - file writes, file edits, and shell commands are denied. This keeps automated runs safe.
 
 To enable all tools, pass `--yolo`:
 
@@ -76,7 +76,7 @@ The conversation loop runs for up to **10 turns**. If the limit is reached, a wa
 
 ## Sessions & Resuming
 
-Each headless run persists its transcript to disk, so you can chain follow-up queries that keep prior context. Headless sessions are tagged separately and stay **hidden** from the interactive `/resume` menu and from interactive `--continue` — automation never pollutes your interactive history.
+Each headless run persists its transcript to disk, so you can chain follow-up queries that keep prior context. Headless sessions are tagged separately and stay **hidden** from the interactive `/resume` menu and from interactive `--continue` - automation never pollutes your interactive history.
 
 ### Continue the most recent run
 
@@ -87,7 +87,7 @@ cmd -p "find the slowest test"
 cmd -p --continue "now suggest a fix"   # carries the previous turn's context
 ```
 
-If no headless session exists yet, `--continue` starts a fresh one — so a `-p --continue` loop works from the first iteration.
+If no headless session exists yet, `--continue` starts a fresh one - so a `-p --continue` loop works from the first iteration.
 
 ### Resume a specific session
 
@@ -103,7 +103,7 @@ Then resume that exact session by id:
 cmd -p --resume 9f4e1c0a-... "continue the review"
 ```
 
-A bare `--resume` with no id errors in headless mode — there is no interactive picker. Use `--continue` to pick up the latest run instead.
+A bare `--resume` with no id errors in headless mode - there is no interactive picker. Use `--continue` to pick up the latest run instead.
 
 ### Open a headless session in interactive mode
 
@@ -187,7 +187,7 @@ Flags useful for headless and automated workflows:
 | `-m, --model <model>` | Run on a specific model this session |
 | `--effort <level>` | Set reasoning effort (`low`, `medium`, `high`, …) |
 | `--theme <theme>` | Set the color theme (`dark` or `light`) |
-| `--config <key=value>` | Set any setting headlessly (repeatable) — see below |
+| `--config <key=value>` | Set any setting headlessly (repeatable) - see below |
 | `--yolo` | Allow file writes and shell commands |
 | `--auto-accept` | Start in auto-accept mode (alias for `--permission-mode auto-accept`) |
 | `--skip-onboarding` | Skip taste onboarding (for CI/automated runs) |
@@ -199,7 +199,7 @@ Flags useful for headless and automated workflows:
 
 ## Configuring settings
 
-Slash commands are interactive-only, but the settings behind them are available as **flags** —
+Slash commands are interactive-only, but the settings behind them are available as **flags** -
 never as a `/slash` string on the command line. The common ones have dedicated flags
 (`--model`, `--effort`, `--theme`), and `--config key=value` reaches any setting the `/config`
 UI can change:
@@ -221,7 +221,7 @@ scriptable automatically. Confirmations print to stderr, keeping `-p` stdout cle
 
 | **Limitation** | **Details** |
 | -------------- | ----------- |
-| **No interactive prompts** | No keyboard shortcuts or interactive UI. Slash commands aren't typed here — use flags instead (see [Configuring settings](#configuring-settings)); session-lifecycle commands like `/clear` and `/reload` have no meaning in one-shot mode |
+| **No interactive prompts** | No keyboard shortcuts or interactive UI. Slash commands aren't typed here - use flags instead (see [Configuring settings](#configuring-settings)); session-lifecycle commands like `/clear` and `/reload` have no meaning in one-shot mode |
 | **No resume picker** | A bare `--resume` errors in print mode; resume by explicit id or use `--continue` |
 | **Stdin timeout** | Piped stdin times out after 30 seconds if no data is received |
 

package/dist/bundled/command-code-knowledge/reference/hooks.md

@@ -92,7 +92,7 @@ The `command` field is what Command Code runs when the hook fires. Here it print
 
 Hooks initialize on startup. Restart Command Code with `cmd`, then run a prompt such as `Use the shell tool to list the files in the current directory`. The message `PreToolUse: hook fired` should appear before the shell command executes.
 
-The quickstart hook emits a static message. Real hooks parse the JSON payload on stdin and return results, halt sessions, or inject context for the next turn — read on for configuration, the full schema, examples, and best practices.
+The quickstart hook emits a static message. Real hooks parse the JSON payload on stdin and return results, halt sessions, or inject context for the next turn - read on for configuration, the full schema, examples, and best practices.
 
 ---
 
@@ -158,7 +158,7 @@ Chooses which tools this group of handlers applies to.
 
 | **Field** | **Required** | **Type** | **Description** |
 | --------- | ------------ | -------- | --------------- |
-| `matcher` | Optional | `string` | Omit to match every tool. Examples: `"shell"`, `"write\|edit"`. Only meaningful for the tool events (`PreToolUse`, `PostToolUse`). `Stop` and `SessionStart` carry no tool, so a `matcher` there never matches and the hook **will not fire** — omit it for those events. |
+| `matcher` | Optional | `string` | Omit to match every tool. Examples: `"shell"`, `"write\|edit"`. Only meaningful for the tool events (`PreToolUse`, `PostToolUse`). `Stop` and `SessionStart` carry no tool, so a `matcher` there never matches and the hook **will not fire** - omit it for those events. |
 | `hooks` | Required | `array` | One or more handlers. Runs in the order listed |
 
 ### HookEntry fields (inner)
@@ -256,7 +256,7 @@ An event may add its own fields on top of the common and tool-call sets. New eve
 
 #### Stop
 
-`Stop` fires when the assistant produces its final response with no remaining tool calls (end of turn). It carries no tool fields — omit `matcher` on `Stop` hooks (a `matcher` here prevents the hook from firing). It provides only the common fields plus:
+`Stop` fires when the assistant produces its final response with no remaining tool calls (end of turn). It carries no tool fields - omit `matcher` on `Stop` hooks (a `matcher` here prevents the hook from firing). It provides only the common fields plus:
 
 | **Field** | **Type** | **Description** |
 | --------- | -------- | --------------- |
@@ -264,7 +264,7 @@ An event may add its own fields on top of the common and tool-call sets. New eve
 
 #### SessionStart
 
-`SessionStart` fires once when a session begins. It carries no tool fields — omit `matcher` on `SessionStart` hooks (a `matcher` here prevents the hook from firing). It provides only the common fields plus:
+`SessionStart` fires once when a session begins. It carries no tool fields - omit `matcher` on `SessionStart` hooks (a `matcher` here prevents the hook from firing). It provides only the common fields plus:
 
 | **Field** | **Type** | **Description** |
 | --------- | -------- | --------------- |
@@ -438,11 +438,11 @@ Use this to pick the right field for the audience you want to reach.
 
 | **Field** | **User (TUI)** | **Model** |
 | --------- | :------------: | :-------: |
-| `stopReason` | ✓ | — |
-| `systemMessage` | ✓ | — |
+| `stopReason` | ✓ | - |
+| `systemMessage` | ✓ | - |
 | `permissionDecisionReason` (Pre) | ✓ | ✓ (when denying) |
 | `reason` (Post / Stop) | ✓ | ✓ (Post & Stop when `decision: "block"`; an `exit 2` retry feeds stderr instead) |
-| `additionalContext` | — | ✓ (appended before next turn) |
+| `additionalContext` | - | ✓ (appended before next turn) |
 | `stderr` (exit 2) | ✓ first line | ✓ (full text fed to model on retry, all events) |
 
 Rule of thumb: for machine-style detail the model should act on verbatim, use `exit 2` + stderr. For natural-language revision guidance, use Stop's `reason`. For a user-only notice, use `systemMessage` or `stopReason`.

package/dist/bundled/command-code-knowledge/reference/mcp.md

@@ -2,13 +2,13 @@
 
 # MCP Servers
 
-Connect Command Code to external tools and data sources through MCP servers. MCP is an open protocol that lets Command Code interact with external services — databases, APIs, issue trackers, and more.
+Connect Command Code to external tools and data sources through MCP servers. MCP is an open protocol that lets Command Code interact with external services - databases, APIs, issue trackers, and more.
 
 ---
 
 ## What is MCP?
 
-MCP (Model Context Protocol) is an open protocol that lets AI agents connect to external tools and services. With MCP, Command Code can interact with databases, APIs, dev tools, and more — all through a standardized interface.
+MCP (Model Context Protocol) is an open protocol that lets AI agents connect to external tools and services. With MCP, Command Code can interact with databases, APIs, dev tools, and more - all through a standardized interface.
 
 Instead of building custom integrations, you connect MCP servers and Command Code automatically discovers and uses their tools.
 
@@ -196,8 +196,8 @@ All flags (`--transport`, `--scope`, `--env`, `--header`) must come **before** t
 | --------------------------- | -------------------------------------------- | ----------- |
 | `-t, --transport <type>`    | Transport type: `stdio` or `http`            | `stdio`     |
 | `-s, --scope <scope>`       | Where to store: `local`, `project`, or `user`| `local`     |
-| `-e, --env <KEY=value>`     | Environment variable (repeatable)            | —           |
-| `-H, --header <Header: value>` | HTTP header (repeatable, http only)       | —           |
+| `-e, --env <KEY=value>`     | Environment variable (repeatable)            | -           |
+| `-H, --header <Header: value>` | HTTP header (repeatable, http only)       | -           |
 
 ---
 
@@ -260,7 +260,7 @@ cmd mcp add --transport http stripe --scope local https://mcp.stripe.com
 
 ### Project scope
 
-Stored in `.mcp.json` at your project root. Checked into version control — shared with your team.
+Stored in `.mcp.json` at your project root. Checked into version control - shared with your team.
 
 ```bash
 cmd mcp add --transport http stripe --scope project https://mcp.stripe.com
@@ -484,9 +484,9 @@ After adding, authenticate via the `/mcp` menu inside a Command Code session.
 
 ### GitHub
 
-Manage GitHub beyond what git supports — issues, PRs, code search, and more. It requires your GitHub Personal Access Token (PAT).
+Manage GitHub beyond what git supports - issues, PRs, code search, and more. It requires your GitHub Personal Access Token (PAT).
 
-**Fine-grained token (recommended)** — scoped to specific repos, minimal permissions:
+**Fine-grained token (recommended)** - scoped to specific repos, minimal permissions:
 
 1. Go to [GitHub > Settings > Developer settings > Personal access tokens > Fine-grained tokens](https://github.com/settings/personal-access-tokens)
 2. Click **Generate new token**
@@ -499,7 +499,7 @@ Manage GitHub beyond what git supports — issues, PRs, code search, and more. I
    - **Metadata**: Read-only (automatically included)
 6. Generate token and copy it
 
-**Classic token** — broader access, simpler setup:
+**Classic token** - broader access, simpler setup:
 
 1. Go to [GitHub > Settings > Developer settings > Personal access tokens > Tokens (classic)](https://github.com/settings/tokens/new)
 2. Name it `commandcode-mcp`, set expiration as needed