Permissions

Ante has a permission system that controls whether tool calls are auto-approved, require user confirmation, or are denied entirely.

Policies

Policy	Behavior
default	Each tool call is evaluated against permission rules. If no rule matches, the user is prompted for approval.
yolo	All tool calls are auto-approved — no prompts, no rules evaluation.

Set the policy in ~/.ante/settings.json:

{ "policy": "default" }

Or override per-session:

ante --yolo "run cargo clippy and fix all warnings"

warning

In headless mode, yolo policy is implied — all tools are auto-approved since there is no interactive prompt.

Decisions

Decision	Effect
Allow	Tool executes immediately, no prompt
Ask	User is prompted to approve or deny
Deny	Tool call is blocked

Rules

Permission rules pair a decision with a tool matcher. Rules are evaluated in order — first match wins.

Rules:  [ Ask(Bash), Allow(Write), Deny(Bash(rm *)) ]
                ↓
Tool call: Bash({ "command": "ls" })
                ↓
Match: Ask(Bash)  ← first rule that matches wins
                ↓
Result: Ask (prompt user)

If no rule matches, the default decision is Ask.

Default rules

Tool	Default decision
Bash	Ask
Write	Ask
Edit	Ask
Read	Allow
Glob	Allow
Grep	Allow
BashOutput	Allow
KillShell	Ask
Agent	Allow
TodoWrite	Allow
WebFetch	Ask
WebSearch	Ask

Session-level overrides

When you approve a tool during a session (e.g. "always allow Bash"), Ante inserts an Allow rule at the front of the rule list, effectively overriding the default Ask for that tool for the remainder of the session.

Tool matchers

Simple matcher

Matches any invocation of a tool by name:

Bash
Write
Agent

Specifier matcher

Matches a tool only when its primary argument matches a glob pattern:

Bash(cargo test *)
Bash(npm run *)
Agent(explore)

Tool	Primary argument
Bash	command
Agent	subagent_type

Glob syntax

Pattern	Matches
cargo test *	cargo test --all, cargo test my_mod
npm run *	npm run build, npm run test
safe-cmd:*	safe-cmd:foo, safe-cmd:bar
exp*	explore, experiment

note

The glob safe-cmd:* does not match safe-cmd --flag. Use safe-cmd * (with a space) to match space-separated arguments.

Tool filtering

# Only allow these tools (whitelist)
ante --allowed-tools Read Glob Grep "analyze the code"

# Remove these tools (blacklist)
ante --disallowed-tools Bash Write "read-only analysis"

# Fine-grained: allow Bash only for specific commands
ante --allowed-tools Read "Bash(cargo test *)" "Bash(cargo clippy *)" "analyze and test"

tip

Tool filtering and permissions are independent. Filtering controls what tools exist in the session; permissions control whether existing tools require approval.

Mode-specific behavior

In TUI mode, tools that require approval show an interactive prompt. You can approve or deny each call, or choose to always allow a tool for the session.

In headless mode, yolo policy is implied. Use --allowed-tools or --disallowed-tools to restrict what the agent can do.