# Vibe

> Authoritative reference for Mistral Vibe — the CLI agent you (the model) are running inside. LOAD when the user: - asks anything about Vibe itself, even by indirect name ("this CLI", "this tool", "you"); - wants to change, inspect, or reset their setup; - asks why the agent did or did not act; - asks how to make the CLI do X, where X lives, or what a flag/command/setting does; - asks any meta question about your own behavior; - is unsure whether a command, flag, env var, or file is in scope — this skill is the source of truth. SCOPE: config under `~/.vibe/` and project-local `.vibe/`; `VIBE_*` and `LOG_*` env vars; models and providers; agents and subagents; skills; tools and their permission model; every slash command and CLI flag; hooks; MCP servers; connectors; plugins; trusted folders; `@`-file mentions; logs; themes; voice.

- Skill: `mistralai/vibe` (Agent Skill)
- Install (CLI): `npx skillmds@latest add mistralai/vibe`
- Raw SKILL.md: https://api.skillmd.com/api/skills/mistralai/vibe/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: mistralai (https://skillmd.com/u/mistralai)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/mistralai/vibe

---


# Vibe CLI Self-Awareness

You are running inside **Mistral Vibe**, a CLI coding agent built by Mistral AI.
This skill gives you full knowledge of the application internals so you can help
the user understand, configure, and troubleshoot their Vibe installation.

## Going Deeper

For facts not covered here, fetch the README:
https://github.com/mistralai/mistral-vibe/blob/main/README.md
It tracks the latest release, so check `vibe --version` before relying on it for
anything version-specific. Point the user at
https://docs.mistral.ai/vibe/code/overview for human-readable docs.

## VIBE_HOME

The user's Vibe home directory defaults to `~/.vibe` but can be overridden via
the `VIBE_HOME` environment variable. All user-level configuration, skills, tools,
agents, prompts, logs, and session data live here.

### Directory Structure

```
~/.vibe/
  config.toml          # Optional user configuration, created on first saved setting
  hooks.toml           # User-level hook definitions
  .env                 # API keys and credentials (dotenv format)
  vibehistory          # Command history
  trusted_folders.toml # Trust database for project folders
  connector_bootstrap_cache.json # Short-lived connector discovery cache
  agents/              # Custom agent profiles (*.toml)
  prompts/             # Custom prompts (*.md)
  skills/              # User-level skills (each skill is a subdirectory with SKILL.md)
  tools/               # Custom tools (<name>.py); descriptions & overrides in tools/prompts/<name>.md
  logs/
    vibe.log           # Main log file
    session/           # Session log files
  plans/               # Session plans

~/.agents/
  skills/              # Additional user-level skills directory
```

### Project-Local Configuration

When in a trusted folder, Vibe also looks for project-local configuration:
- `.vibe/config.toml` - Project-specific config (overrides user config)
- `.vibe/hooks.toml` - Project-specific hooks (requires trusted folder)
- `.vibe/skills/` - Project-specific skills
- `.vibe/tools/` - Project-specific tools (`<name>.py`); a `prompts/<name>.md` beside them sets or overrides the description of the tool named `<name>` — builtin, MCP, or custom (e.g. `.vibe/tools/prompts/bash.md` re-describes `bash`). Same `tools/*.py` + `tools/prompts/*.md` layout as the builtins.
- `.vibe/agents/` - Project-specific agents
- `.vibe/prompts/` - Project-specific prompts
- `.agents/skills/` - Standard agent skills directory

Custom Python tools will be deprecated in a future release. Recommend skills
for new extensions. When a user asks for migration help, inspect the custom
tool's behavior and replace it with an equivalent skill.

### AGENTS.md Discovery

`AGENTS.md` files provide directory-scoped instructions to the model. At startup,
Vibe loads `~/.vibe/AGENTS.md` and every `AGENTS.md` from the project root up
through the trust chain. `AGENTS.md` files in subdirectories are discovered
lazily: when `read_file` reads a file below the project root, any `AGENTS.md`
between the file's parent and the project root is injected into
context.

## Lifecycle: Exit, Update, Version, Resume

### Exit

Chat input (case-insensitive): `/exit`, `exit`, `quit`, `:q`, `:quit`.
Keyboard: `Ctrl+C` / `Ctrl+D` — press twice within ~1s to quit. For `Ctrl+C`,
the first press instead interrupts the running job or clears the input if either
is present. Set `ask_confirmation_on_exit = false` to make `Ctrl+D` quit on the
first press (also toggleable in `/config`); `Ctrl+C` always requires a second
press. `Ctrl+Z` suspends on POSIX (resume with `fg`).

### Update

Vibe never updates silently. With `enable_update_checks = true` (default), it
polls PyPI for `mistral-vibe` daily and prompts on the next launch when a
newer release exists; accepting runs `uv tool upgrade mistral-vibe`, then
`brew upgrade mistral-vibe` as a fallback. Disable via `enable_update_checks
= false`. Run `vibe update` (equivalent to `vibe --check-upgrade`) to check
immediately, prompt to install a newer version if one exists, and exit. Initial
install: `uv tool install mistral-vibe`.

### Version

`vibe --version` (or `-v`) prints it and exits. Not shown anywhere in-session.

### Resume

- `vibe -c` / `--continue`: most recent session in this terminal (TTY-scoped;
  falls back to latest in cwd).
- `vibe --resume [SESSION_ID]`: specific session; without an id, opens a picker.
- In-session: `/resume` (alias `/continue`).

#### Session titles

Each session has a `title` stored in `meta.json` (with `title_source`: `auto` or
`manual`). A session stays untitled until a background LLM call generates a
concise descriptive title (the `--resume` list shows a message preview until
then). Automatic generation runs only for the interactive CLI; other clients
(ACP, app server, programmatic) keep their own session management and fall back
to the message preview. Title generation runs on the session's active
model/provider — it substitutes a small fast Mistral model only when the active
provider is already Mistral and the allowlist permits it, so titles never reach a
new destination. The first title waits for the opening turn to finish (or a few
model steps) so it isn't generated off a thin tool-call preamble. On that cheap
fast model it also refreshes periodically and
after each compaction; when it falls back to the (possibly expensive) active
model it stays bounded — one title at the start plus one after a compaction, a
couple at most — so a large model isn't re-invoked every few turns. The refresh
keeps the opening intent and the latest exchange in view and feeds the previous
title back so it refines rather than restarts. `/rename <title>` sets a `manual`
title that auto-generation never overwrites. Set `session_logging.generate_titles
= false` to turn automatic titles off (the `--resume` list and tab then use the
message preview). The current title also drives the terminal tab/window title
(OSC), updated on rename, auto-title changes, and resume; it never blocks a turn.

#### Session storage & folder scoping

Local sessions are written under `~/.vibe/logs/session/` (override with
`session_logging.save_dir`). Each session records the `cwd` it ran in. The
`/resume` picker, `--continue`, and bare `--resume` (no id) are **scoped to the
current folder**: only sessions whose `cwd` matches where Vibe is launched are
listed, so the same directory shows its own history and nothing else. Switch
folders to see a different set. The explicit `--resume <SESSION_ID>` form is
**not** folder-scoped: it resolves the session by id regardless of which folder
it ran in.

The first user message pins the resolved model alias to the session. Resuming
keeps that model even if the configured default changes. `/model` uses the same
config persistence target as other settings and also updates an existing
session override immediately; the session file is synchronized when the next
user message is sent. An explicit persistent target selected through `/config`
changes only that layer. `/clear` starts an unpinned conversation that follows
the current config again. If a selected model is no longer configured, Vibe
falls back to the current default model.

## Configuration (config.toml)

The configuration file uses TOML format. When it does not exist, Vibe uses its
built-in defaults and creates a sparse file on the first persisted setting.
Settings can also be overridden via environment variables with the `VIBE_`
prefix (e.g., `VIBE_ACTIVE_MODEL=local`).

Custom prompt IDs are resolved from project-local `.vibe/prompts/` first, then
from `~/.vibe/prompts/`, and finally from the built-in bundled prompts.

### Key Settings

```toml
# Model selection
active_model = "mistral-medium-3.5"  # Model alias to pin; omit or set "" to follow the server-routed default

# UI preferences
theme = "auto"  # Follow terminal background, then OS light/dark preference
disable_welcome_banner_animation = false
autocopy_to_clipboard = true  # Enable automatic copying of selected text to clipboard
file_watcher_for_autocomplete = false
ask_confirmation_on_exit = true  # Require a second Ctrl+D to quit (Ctrl+C always confirms)
show_greeting = true  # Show "Hello {name}" greeting below the banner at startup (Mistral providers, once per 24h)
log_level = "WARNING"  # Optional. DEBUG | INFO | WARNING | ERROR | CRITICAL — log level for ~/.vibe/logs/vibe.log
```

### Copy and Text Selection

- **Copy shortcuts**: `Ctrl+Y` and `Ctrl+Shift+C` both copy the current selection to the clipboard. When autocopy is enabled (default), releasing the mouse over a selection also copies automatically. Each successful copy flashes a brief inline "Copied to clipboard" notice.
- **Multi-click selection**: Double-click selects a word, triple-click selects the current paragraph; dragging extends the selection at the same granularity.

```toml
# Behavior
bypass_tool_permissions = false    # Skip tool approval prompts
system_prompt_id = "cli"          # System prompt: "cli", "lean", or custom .md filename
compaction_prompt_id = "compact"  # Compaction prompt: built-in "compact" or custom .md filename
enable_telemetry = true
enable_update_checks = true       # Daily PyPI check; prompts on next launch when a newer release exists
enable_notifications = true
enable_system_trust_store = false  # Use OS trust store for outbound HTTPS
api_timeout = 720.0               # API request timeout in seconds
api_retry_max_elapsed_time = 300.0  # Retry budget for retryable API failures in seconds
auto_compact_threshold = 200000   # Fallback for models without their own threshold

# Git commit behavior
include_commit_signature = true   # Add "Co-Authored-By" to commits

# System prompt composition
include_model_info = true         # Include model name in system prompt
include_project_context = true    # Include project context (git info, cwd) in system prompt
include_prompt_detail = true      # Include OS info, tool prompts, skills, and agents in system prompt

# Voice features
voice_mode_enabled = false
narrator_enabled = false
active_transcribe_model = "voxtral-realtime"
active_tts_model = "voxtral-tts"
```

### OpenTelemetry Tracing

Set `enable_otel = true` to export traces for agent, model, and tool operations
over OTLP/HTTP. `enable_telemetry` must also be enabled. With no explicit
endpoint, Vibe derives the telemetry endpoint and API key from the configured
Mistral provider, except public regional API hosts that do not serve telemetry.

To use another collector, set `otel_endpoint` to its base URL; Vibe appends
`/v1/traces`. Configure custom-collector authentication through the standard
`OTEL_EXPORTER_OTLP_*` environment variables.

`otel_redaction` controls client-side span attribute redaction: `default`
redacts sensitive values, `strict` redacts sensitive attributes entirely, and
`none` disables redaction. Use `none` only for a collector trusted to receive
potentially sensitive prompt, response, and tool data.

```toml
enable_otel = true
otel_endpoint = "https://collector.example.com:4318"
otel_redaction = "default"
```

### Providers

```toml
[[providers]]
name = "mistral"
api_base = "https://api.mistral.ai/v1"
api_key_env_var = "MISTRAL_API_KEY"
backend = "mistral"

[[providers]]
name = "llamacpp"
api_base = "http://127.0.0.1:8080/v1"
api_key_env_var = ""
extra_headers = { "X-Custom-Header" = "value" }  # optional per-provider HTTP headers
emits_finish_reason = false  # set false for OpenAI-compatible endpoints that end
                             # streams without a finish reason; avoids spurious
                             # "incomplete stream" errors and retries (default true)
```

### Models

```toml
[[models]]
name = "mistral-vibe-cli-latest"
provider = "mistral"
alias = "mistral-medium-3.5"
temperature = 1.0
input_price = 1.5
output_price = 7.5
cached_input_price = 0.15         # per million cached input tokens; omit to bill at input_price
thinking = "high"                 # "off", "low", "medium", "high", "max"
auto_compact_threshold = 200000
supports_images = true            # vision-capable; allows @-mentioned images

[[models]]
name = "devstral"
provider = "llamacpp"
alias = "local"
```

### Tool Configuration

```toml
# Additional tool search paths
tool_paths = ["/path/to/custom/tools"]

# Enable only specific tools (glob and regex supported)
enabled_tools = ["bash", "read_file", "grep"]

# Disable specific tools after enabled_tools filtering
disabled_tools = ["web_fetch"]

# Per-tool configuration
[tools.bash]
allowlist = ["git", "npm", "python"]

[tools.git_bash]
permission = "ask"
shell = "C:\Program Files\Git\bin\bash.exe"

[tools.powershell]
permission = "ask"
shell = "powershell.exe"
```

The built-in shell surface is controlled by the `managed_shell_tools_enabled` config
field and the `vibe_cli_managed_shell_tools` GrowthBook experiment. The default variant
keeps the legacy one-shot `bash` tool, including its existing Windows behavior.
The managed variant exposes OS-native shell tools:
POSIX systems, including WSL where Vibe runs as Linux, get managed `bash`,
`bash_output`, `bash_stdin`, `bash_sessions`, and `bash_log_file`; native Windows
gets `git_bash`, `git_bash_output`, `git_bash_stdin`, `git_bash_sessions`, and
`git_bash_log_file` when Git Bash is available. If Git Bash is unavailable,
native Windows falls back to `powershell`, `powershell_output`,
`powershell_stdin`, `powershell_sessions`, and `powershell_log_file`.

Managed shell sessions return a `session_id`, inline output, a cursor for polling
more output, and a log path under `~/.vibe/shell-tool/sessions/`. Long-running
commands can be left alive with `background = true`, and interactive commands can
be driven with the matching stdin tool.

POSIX `bash` reads permissions, allowlists, and denylists from `[tools.bash]`.
Native Windows `git_bash` reads them from `[tools.git_bash]`; native Windows
`powershell` reads them from `[tools.powershell]`. Neither Windows tool reads
`[tools.bash]`. Git Bash is preferred when Vibe can resolve a usable `bash.exe`
from PATH, Git for Windows, or standard Git install locations. If Git Bash is
unavailable, the PowerShell resolution order is `pwsh.exe`, then
`powershell.exe`. `cmd.exe` is not used by the managed Windows shell tools.
Output polling uses byte offset cursors
(`cursor` / `next_cursor`), `max_bytes` caps per-call inline output, and
`max_inline_bytes` configures the default cap.

**Special case — `find` command:** Even if `find` is in the bash allowlist,
Vibe detects `-exec`, `-execdir`, `-ok`, and `-okdir` predicates and will
prompt for user permission before running the command.

#### File Tool Permission Resolution

File-based tools (`read`, `grep`, `write_file`, `edit`) resolve
permissions in this order (first match wins):

1. **Scratchpad** path → always allowed
2. **denylist** glob match → always denied
3. **allowlist** glob match → always allowed
4. **sensitive_patterns** match → requires approval
5. **Outside workdir** → requires approval (or denied if `permission = "never"`)
6. **Default** → uses the tool's `permission` setting

The **denylist** is checked before the allowlist — a path matching both lists
is denied. Both are checked before the outside-workdir boundary, so the
allowlist can still auto-approve access to directories outside the project.

### Skill Configuration

```toml
# Additional skill search paths
skill_paths = ["/path/to/custom/skills"]

# Enable only specific skills
enabled_skills = ["vibe", "custom-*"]

# Disable specific skills
disabled_skills = ["experimental-*"]
```

### Agent Configuration

```toml
# Additional agent search paths
agent_paths = ["/path/to/custom/agents"]

# Enable/disable agents
enabled_agents = ["ask", "plan"]
disabled_agents = ["auto-approve"]

# Opt-in builtin agents (only affects agents with install_required=True, e.g. lean)
installed_agents = ["lean"]

# Agent profile to use when --agent is not passed
# (default: "accept-edits"). Valid values: "ask", "plan", "accept-edits",
# "auto-approve", "lean" (only when listed in installed_agents), or any
# custom agent name from ~/.vibe/agents/ or .vibe/agents/. Subagents
# (e.g. "explore") are rejected. Applies in both interactive and programmatic
# (-p/--prompt) mode.
default_agent = "plan"
```

### MCP Servers

Remote MCP servers can be added non-interactively from the shell:

```bash
vibe mcp add mistralai \
  --url https://api.mistral.ai/mcp \
  --transport streamable-http \
  --api-key-env MISTRAL_API_KEY

vibe mcp add linear \
  --url https://mcp.linear.app/mcp

vibe mcp remove mistralai
```

Static auth is selected when `--api-key-env` or `--header` is provided.
Otherwise the server uses OAuth and starts browser login by default. Pass
`--no-login` to only persist the OAuth configuration. Run
`vibe mcp add --help` for all supported authentication and timeout options.
Use `vibe mcp remove <name>` to remove a server from the user configuration;
stored OAuth credentials are deleted when available.

Hosted OAuth MCP servers can also be added from inside Vibe:

```text
/mcp add https://mcp.linear.app/mcp
/mcp add https://mcp.example.com/mcp --name docs --scope read --transport http --no-login
```

`/mcp add` is OAuth-only. It writes `auth.type = "oauth"` with optional
scopes and starts login by default. It uses `transport = "streamable-http"`
unless you pass `--transport http`. Pass `--no-login` to add the server without
starting OAuth login. The shortcut supports `streamable-http` and `http`
transports.

```toml
[[mcp_servers]]
name = "my-server"
transport = "stdio"
command = "npx"
args = ["-y", "@my/mcp-server"]

[[mcp_servers]]
name = "remote-server"
transport = "http"
url = "https://mcp.example.com"

[mcp_servers.auth]
type = "static"
api_key_env = "MCP_API_KEY"
api_key_header = "Authorization"
api_key_format = "Bearer {token}"

[[mcp_servers]]
name = "linear"
transport = "streamable-http"
url = "https://mcp.linear.app/mcp"

[mcp_servers.auth]
type = "oauth"
scopes = ["read", "write"]
# Optional: client_id = "pre-registered-public-client"
# Optional: client_metadata_url = "https://example.com/client-metadata.json"
# Optional: redirect_port = 47823
```

HTTP MCP servers can use either static auth or OAuth:

- Static auth: legacy `api_key_env` / `headers` keys still work and are
  promoted to `auth.type = "static"` internally.
- OAuth auth: use `auth.type = "oauth"` with `scopes`. Vibe stores tokens
  in the OS keyring under `mcp-oauth:<alias>:tokens`, dynamic client info
  under `mcp-oauth:<alias>:client_info`, and config drift fingerprints under
  `mcp-oauth:<alias>:fingerprint`.
- Headless environments without an OS keyring cannot store OAuth tokens; use
  static auth via `api_key_env` instead.
- For SSH/remote browser callbacks, forward the loopback port:
  `ssh -L 47823:127.0.0.1:47823 <host>`.

### Connectors

Mistral connectors are auto-discovered when the active provider is Mistral
and the API key env var is set. Toggle the master switch or hide individual
connectors / tools:

The legacy backend keeps a discovered connector disabled until it has an
explicit `[[connectors]]` entry. The Unified backend selected with
`--experimental-harness` enables ready connectors by default in memory. It
does not write that default to TOML, and the master switch plus explicit
connector, tool, allowlist, and denylist settings always take precedence.

```toml
enable_connectors = true          # Master switch (default: true)

[[connectors]]
name = "github"
disabled = true                   # Hide all tools from this connector

[[connectors]]
name = "linear"
disabled_tools = ["delete_issue"] # Hide selected tools only
```

### Session Logging

```toml
[session_logging]
enabled = true
save_dir = ""                     # Defaults to ~/.vibe/logs/session
session_prefix = "session"
generate_titles = true            # Background LLM session titles; false uses the message preview
```

### Browser Sign-In

Browser sign-in lets users authenticate through the browser during onboarding.
Mistral providers use default browser sign-in URLs (`console.mistral.ai` /
`api.mistral.ai`). Custom or renamed providers must configure both URLs:

```toml
[[providers]]
browser_auth_base_url = "https://console.mistral.ai"
browser_auth_api_base_url = "https://console.mistral.ai/api"
```

Split-horizon deployments (e.g. behind an SAP Cloud Connector) expose the
console under a virtual host the CLI reaches but the server does not know about,
so it returns sign-in/poll URLs on its own public host. Set
`browser_auth_allow_origin_rewrite = true` on the provider to re-home the
returned URLs onto the configured `browser_auth_base_url` /
`browser_auth_api_base_url` origins instead of rejecting them for an origin
mismatch (path traversal is still rejected). Only the origin (scheme, host,
port) is rewritten; the returned URL's path must already sit under the
configured base path, so the connector must preserve the server's path prefix.
Point `browser_auth_base_url` at the browser-reachable console and
`browser_auth_api_base_url` at the CLI-reachable API host. The interactive
onboarding wizard's custom-domain screen also accepts an optional browser-auth
API base URL and auto-enables this rewrite when its origin differs from the
console origin:

```toml
[[providers]]
browser_auth_base_url = "https://console.internal.example"
browser_auth_api_base_url = "https://connector.internal.example:443/api"
browser_auth_allow_origin_rewrite = true
```

Self-hosted deployments can point Vibe CLI upgrade and API-key links to their
Le Chat web deployment, where the Vibe API key is managed:

```toml
vibe_base_url = "https://chat.mistral.ai"
```

Interactive setup can target a Mistral-compatible deployment instead of the
default `console.mistral.ai` / `api.mistral.ai`. The final credential is always a
Mistral API key. On the auth-method screen pick **Launch browser**, then
**Other** on the sign-in-target screen, and enter a login domain to complete
browser sign-in. This sets `browser_auth_base_url` (the entered domain) and
derives `browser_auth_api_base_url` (`DOMAIN/api`). The overridden `mistral`
provider is persisted to user config so subsequent runs reuse it.

The wizard reads any custom `browser_auth_base_url` already in `config.toml`:
choosing **Other** pre-fills that configured domain so it can be confirmed or
edited. Choosing **Mistral AI** while a custom domain is configured warns first
and requires pressing **Enter** again to confirm the reset to the default
domain, which is then persisted.

### Hooks

Hooks let users run shell commands automatically at lifecycle events. They
are always available — no flag is required; dropping a `hooks.toml` in place
is enough.

#### Config and hook types

Hooks live in `hooks.toml` files (separate from `config.toml`), discovered in
this order:

1. `<project>/.vibe/hooks.toml` — loaded first, only when the folder is
   trusted.
2. `~/.vibe/hooks.toml` — loaded second.

A duplicate `name` across the two files is reported as a config issue and the
project entry wins. Config-load errors (invalid TOML, missing required
fields) surface in the TUI as warnings and the offending hook is skipped.

```toml
[[hooks]]
name = "lint"                       # Required: unique within the file.
type = "post_agent"                 # Required: post_agent | pre_tool | post_tool.
command = "eslint --quiet ."        # Required: shell command run in cwd.
timeout = 60.0                      # Default: 60s for all hooks.
description = "Run ESLint"          # Optional.

[[hooks]]
name = "deny-rm-rf"
type = "pre_tool"
match = "bash"                      # Tool-name matcher (tool hooks only, default "*").
strict = true                       # Tool hooks only: escalate any failure to deny/clear.
command = "uv run python /path/to/guard-bash"
```

| Type | When it runs |
|---|---|
| `post_agent` | Once per turn, after the agent finishes responding (no pending tool calls). |
| `pre_tool` | Per tool call, before the user permission prompt. |
| `post_tool` | Per tool call, **iff the tool body actually ran**. `tool_status` is `success`, `failure`, or `cancelled`. Does not fire when the tool never executed (`pre_tool` denial, user denial at the approval prompt, permission `NEVER`, or cancellation before the body started). |

**Matcher syntax** (same as `enabled_tools`): fnmatch glob by default
(`"bash"`, `"read_*"`, case-insensitive), or a regex full-match when the
pattern starts with `re:` (`"re:(read_file|grep)"`). `match` is forbidden on
`post_agent`.

**Tool name conventions** for matchers:
- Built-in tools use their bare name (`bash`, `read_file`, …); see the Tools
  section above for the full list.
- MCP tools: `{server-name}_{raw-tool-name}` (e.g. `linear_create-issue`).
- Connector tools: `connector_{normalized-name}_{remote-tool-name}` (e.g.
  `connector_Google_Drive_search_files`).
- Subagents all route through `task`. Match with `match = "task"` and read
  `tool_input.agent` to discriminate by subagent.

Subagent invocations inherit the parent's hook config. Their hook events are
logged to the subagent's session log and don't propagate to the parent's UI.

#### Wire protocol

Every hook is spawned in `cwd` and receives a JSON object on **stdin**
discriminated by `hook_event_name`:

```json
// post_agent
{"hook_event_name": "post_agent", "session_id": "...",
 "parent_session_id": null, "transcript_path": "...", "cwd": "..."}

// pre_tool
{"hook_event_name": "pre_tool", "session_id": "...", "parent_session_id": null,
 "transcript_path": "...", "cwd": "...",
 "tool_name": "bash", "tool_call_id": "call_42",
 "tool_input": {"command": "ls"}}

// post_tool
{"hook_event_name": "post_tool", "session_id": "...", "parent_session_id": null,
 "transcript_path": "...", "cwd": "...",
 "tool_name": "bash", "tool_call_id": "call_42",
 "tool_input": {"command": "ls"},
 "tool_status": "success",         // success | failure | cancelled
 "tool_output": {"output": "..."},  // the tool's serialized result (success/cancelled); null otherwise
 "tool_output_text": "...",         // current text the LLM will see; mutable by prior hooks
 "tool_error": null,                // populated on failure/skipped
 "duration_ms": 42.5}
```

`parent_session_id` is set when running inside a subagent. Exceeding
`timeout` kills the whole process tree.

A hook signals back via its **exit code** and **stdout** (stderr is reserved
for diagnostics — Vibe never parses it for control):

| Exit | Stdout | Behavior |
|---|---|---|
| `0` | empty | Pass through (no action). |
| `0` | valid structured-response JSON object (schema below) | Act per the JSON fields. |
| `0` | anything else (free-form text, broken JSON, scalar/array, schema mismatch) | Failure path (see below). The parse error is in the message. |
| non-zero / timeout / spawn failure | — | Failure path. Reason taken from stderr, then stdout, then the exit code. |

Structured-response schema:

```json
{
  "decision": "allow" | "deny",          // optional; default "allow"
  "reason": "string",                     // required when decision == "deny"
  "system_message": "string",             // optional UI note
  "hook_specific_output": {
    "tool_input": { ... },                // pre_tool only
    "additional_context": "string"        // post_tool only
  }
}
```

Unknown fields are tolerated at every level. Fields that aren't meaningful
for the current hook type are silently ignored.

**Don't self-name in `system_message` or `reason`** — the UI prefixes
hook-end-event content with `[hook-name]` automatically, and `pre_tool`
denials are wrapped as ``Tool 'X' was denied by hook 'Y': {reason}`` before
the LLM sees them. A hook that writes ``"reason": "guard: refused..."``
will produce ``hook 'guard': guard: refused...`` downstream.

`decision: "deny"` per hook type:

| Hook | Effect of `decision: "deny"` |
|---|---|
| `pre_tool` | Deny the tool call; `reason` is the tool error returned to the LLM. First deny short-circuits the remaining `pre_tool` hooks for this call. |
| `post_tool` | Replace `tool_output_text` with `reason`. Pipeline continues; subsequent hooks see the replacement. |
| `post_agent` | Inject `reason` as a retry user message. Capped at 3 retries per hook per user turn. |

Event-specific payloads:

- `hook_specific_output.tool_input` (`pre_tool`): full replacement of the
  model's arguments. Vibe re-validates against the tool's schema **after each
  rewriting hook** — the first invalid rewrite aborts the chain and
  synthesizes a denial attributing the failure to that hook. Rewrites
  compose: hook N receives `tool_input` as rewritten by hooks 1..N-1.
- `hook_specific_output.additional_context` (`post_tool`): text appended
  (with `
`) to the current `tool_output_text`. Composes with a same-hook
  `decision: "deny"`: deny replaces first, then `additional_context` is
  appended to the replacement.

**Failure path.** Any failure (non-zero exit, timeout, spawn failure,
non-conforming stdout) emits a UI warning and lets the gated action proceed
(fail open). With `strict = true` on a tool hook:

| Hook | Strict failure escalates to |
|---|---|
| `pre_tool` | Deny the tool call with the failure reason. |
| `post_tool` | Clear `tool_output_text` (replace with empty). |

`strict` is forbidden on `post_agent`.

#### Execution semantics

- Hooks of the same type fire sequentially in load order (project file first,
  then user file; declaration order within each file).
- Tool calls within a single LLM turn run **concurrently**; each call's hook
  chain runs serially but the chains run in parallel across calls. Hooks
  that touch shared state (filesystem, env) must coordinate themselves.
- `pre_tool` rewrites take effect everywhere downstream: the user
  permission prompt sees the rewritten arguments, the tool runs with them,
  and the assistant message is patched so subsequent LLM turns reflect what
  actually ran.

### Pattern Matching

Tool, skill, and agent names support three matching modes:
- **Exact**: `"bash"`, `"read_file"`
- **Glob**: `"bash*"`, `"mcp_*"`
- **Regex**: `"re:^serena_.*$"` (full match, case-insensitive)

## CLI Parameters

```
vibe [PROMPT]                       # Start interactive session with optional prompt
vibe -p TEXT / --prompt TEXT         # Programmatic mode using `default_agent`, one-shot, exit
vibe -p TEXT --auto-approve          # Programmatic mode with all tool calls approved
vibe -p TEXT --agent lean --yolo      # Lean mode with all tool calls approved
vibe --agent NAME                   # Select agent profile (falls back to `default_agent` config)
vibe --auto-approve / --yolo         # Approve all tool calls for the selected agent
vibe --workdir DIR                  # Change working directory
vibe --worktree NAME                # Create/reuse a git worktree under $VIBE_HOME/worktrees on branch NAME and run inside it. Auto-cleanup only for worktrees Vibe created this run and only after a session started; reused worktrees and attached (pre-existing) branches are kept unless confirmed. -p sessions keep worktrees. Ignored with --setup/--check-upgrade.
vibe --worktree                     # Same, but Vibe picks an unused name from the prompt (a random slug when there is no prompt) on a vibe/<name> branch, and never reuses an existing worktree. The prompt must precede the flag or follow a `--`, since --worktree otherwise reads it as NAME.
vibe --add-dir DIR                  # Extra working dir loaded for context (repeatable). Implicitly trusted.
vibe --trust                        # Trust cwd for this invocation only (not persisted). Skips the trust prompt.
vibe -c / --continue                # Continue most recent session in this terminal (TTY-scoped, falls back to latest in cwd)
vibe --resume [SESSION_ID]          # Resume a specific session
vibe -v / --version                 # Show version
vibe --setup                        # Run onboarding/setup
vibe update / vibe --check-upgrade  # Check for a Vibe update now, prompt to install it, and exit
vibe --max-turns N                  # Max assistant turns (programmatic mode)
vibe --max-price DOLLARS            # Max cost limit (programmatic mode)
vibe --max-tokens N                 # Max total session tokens (programmatic mode)
vibe --enabled-tools TOOL           # Enable specific tools (repeatable)
vibe --disabled-tools TOOL          # Disable specific tools (repeatable)
vibe --output text|json|streaming   # Output format (programmatic mode)
```

## Built-in Agents

There are two kinds of agents:
- **Agents** are user-facing profiles selectable via `--agent` or `Shift+Tab`.
  They configure the model's behavior, tools, and system prompt.
- **Subagents** are model-facing: the model can spawn them autonomously to delegate
  subtasks (e.g. exploring the codebase). Users cannot select subagents directly.

### Agents

- **ask**: Requests approval for tool executions
- **plan**: Planning-focused agent
- **accept-edits**: Default agent; auto-approves file edits but asks for other tools
- **auto-approve**: Auto-approves all tool calls
- **lean**: Specialized Lean 4 proof assistant. Not available by default — must be
  installed with `/leanstall` (removed with `/unleanstall`). Use `--agent lean
  --auto-approve` or `--agent lean --yolo` to run Lean mode without tool prompts.

### Subagents

- **explore**: Read-only codebase exploration subagent with grep, file reading,
  and skill loading. Spawned by the model, not selectable by the user.

Custom agents are TOML files in `~/.vibe/agents/NAME.toml`.

## Built-in Slash Commands

- `/help` - Show help message
- `/config` - Full-screen settings browser. Fields show their value and origin layer (default / TOML / env / override). Type to filter, arrows to move, Enter to edit; booleans toggle, closed-set fields (theme, models) pick from a list, scalars edit inline, complex fields open a JSON editor. The edit modal shows an inspector of the layers setting the field; edits persist to the user config (`~/.vibe/config.toml`) by default, `Tab` cycles the save target through the project config (`.vibe/config.toml`, when the project layer is active) and the ephemeral session override (until restart), and `Ctrl+R` clears the field one writable layer at a time toward the default. The `tools` field opens a grouped tool list with a per-tool config editor (permission, allow/deny lists, `Ctrl+E` for raw JSON). Enabling/disabling whole MCP servers or connectors stays in `/mcp`.
- `/model` - Select active model
- `/skills` - Browse and manage the skills available to this session. Lists the
  installed ones alongside the shared skills you can add, and can import a
  skill, pin it to a version or alias, convert it to a local copy, or remove it.
  Registered only when `experimental_enable_registry_skills` is set.
- `/thinking` - Select thinking level
- `/theme` - Select Textual UI theme; `auto` follows terminal/OS appearance (persisted in config)
- `/reload` - Reload configuration, agent instructions, and skills from disk
- `/clear`, `/new` - Start a new conversation. Optionally pass a prompt to seed it
- `/log` - Show path to current interaction log file
- `/log-level` - Show or set the log level. `/log-level` prints the full chain
  (session, env, config, effective); `/log-level set <LEVEL>` sets a
  process-lifetime override; `/log-level set-global <LEVEL>` also persists to
  config.toml; `/log-level unset` clears the session override. LEVEL is one of
  DEBUG, INFO, WARNING, ERROR, CRITICAL.
- `/debug` - Toggle debug console
- `/compact` - Compact model context by summarizing. The session ID and visible
  conversation stay intact; the auto title is refreshed to reflect the
  compacted conversation (unless renamed manually).
- `/rename <title>` - Set a manual session title. Persists to `meta.json`
  (`title_source=manual`), updates the terminal tab title, and is never
  overwritten by automatic title generation.
- `/retry [additional instructions]` - Continue a model response interrupted by
  a backend error without repeating text already shown. Optional instructions
  are passed to the model for the continuation. Relevant error messages also
  hint at this command.
- `/status` - Display agent statistics
- `/whoami` - Display the Mistral signed-in user, workspace, and plan
- `/copy` - Copy the last agent message to the clipboard
- `/paste-image` - Paste an image from the OS clipboard into the prompt.
  **macOS only** — the command is not registered on Linux or Windows.
- `/voice` - Configure voice settings
- `/mcp` (or `/connectors`) - Display MCP servers and connector status. The
  browser opens on the first item; press Up or Left to move into the fuzzy-search
  bar, and Up again to wrap to the last item. Pass a server or connector name to
  list its tools or open its auth panel when authentication is required
- `/mcp add <url>` - Add a hosted OAuth MCP server. Supports `--name <alias>`,
  repeatable `--scope <scope>`, `--transport <http|streamable-http>`, and
  `--no-login`. Starts OAuth login by default. OAuth-only; use
  `vibe mcp add <name> --url <url> --api-key-env <var>` for API-key/static auth.
- `vibe mcp remove <name>` - Remove an MCP server from the user configuration
  and delete its stored OAuth credentials when available.
- `/mcp status` - Display MCP auth state (`ok`, `needs_auth`, `static`, `stdio`)
- `/mcp login <alias>` - Start OAuth login for an MCP server
- `/mcp logout <alias>` - Log out from an MCP server and delete stored OAuth
  secrets
- `/resume` (or `/continue`) - Browse and resume past sessions for the current
  folder. The picker header shows the folder being listed. Press `d` twice to
  delete a saved session; the active session cannot be deleted here.
- `/rewind` - Rewind to a previous message. Also triggered by pressing `Esc`
  twice on an empty input; if the input has content, the first double-`Esc`
  clears it instead. In the rewind panel: `↑/↓` pick option, `Shift+↑/↓`
  scroll, `←`/`Esc` edit previous message, `→` edit next message, `Enter`
  accept, `q` quit.
- `/loop <interval> <prompt>` - Schedule a recurring prompt (e.g. `/loop 30s ping`).
  Intervals: `Ns/Nm/Nh/Nd`, minimum 30s, max 50 loops/session.
  - `/loop` (or `/loop list` / `/loop ls`) - List current scheduled loops.
  - `/loop cancel <id|all>` (aliases `rm`, `stop`, `delete`) - Cancel a loop.
  - Loops fire only when the agent is idle and the input bar is focused. At
    most one loop fires per poll. Overdue loops fire once on the next poll
    (no catch-up); `next_fire_at` advances to `now + interval`.
  - Loops are persisted in the session metadata (`loops` field of `meta.json`)
    and restored on `--resume`/`--continue`.
- `/proxy-setup` - Configure proxy and SSL certificate settings
- `/leanstall` - Install the Lean 4 agent (leanstral)
- `/unleanstall` - Uninstall the Lean 4 agent
- `/plugins` - Display the plugins this session is running (experimental harness
  mode only). Shows each plugin's name, scope, source format, content digest, and
  components (skills, MCP servers, agents, hooks, knowledge, connectors, tools).
  Press `r` inside the view to reload.
- `/reload-plugins` - Re-pin this session's plugins and report what changed
  (experimental harness mode only). Re-discovers plugins from disk, re-pins the
  snapshot, and prints a diff of added, removed, and updated plugins.
- `/data-retention` - Show data retention information
- `/teleport` - Teleport session to Vibe Code Web (only available when Vibe Code is enabled)
- `/remote-project` - Select the Vibe Code Web project for this repository (only
  available when Vibe Code is enabled)
- `/exit` - Exit the application

## File Mentions (`@`)

Type `@` in the chat input to autocomplete files and folders from the
project tree. Pressing Tab/Enter inserts the chosen path. Your message text
is sent as-is (the `@path` stays in the prompt); behavior then depends on
the mention kind:

- **Text files** trigger a synthetic `read_file` tool ca

…(truncated)