What is bash-smart-approve:remove?

A command for removing a binary, website domain, or file path from bash-smart-approve's allowlist, which is the list of actions it permits without asking.

Use it to stop allowing a command, `curl` domain, or `rm` path, with a proposed change shown before the configuration is edited.

It removes rules that are no longer appropriate. It also checks user and project settings so you can change the correct rule.

bash-smart-approve:remove

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/pr3m/claude-code-bash-smart-approve/remove

Any agent

npx skills add pr3m/claude-code-bash-smart-approve --skill remove

Clone the repo

git clone --depth 1 https://github.com/pr3m/claude-code-bash-smart-approve

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 395 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00054	$0.00395
Opus 5	$0.00027	$0.00198
Sonnet 5	$0.00011	$0.00079
Haiku 4.5	$0.00005	$0.00040

Measured yesterday against content hash d9841be03aef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bash-smart-approve:remove scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If `$ARGUMENTS` names an item, use it. Otherwise ask: "What should I remove? (binary name, curl domain, or rm path)"

plugins/bash-smart-approve/skills/remove/SKILL.md · 41 lines

What it actually says

Remove from Allowlist

Step 1 — Identify target

If $ARGUMENTS names an item, use it. Otherwise ask: "What should I remove? (binary name, curl domain, or rm path)"

Classify:

Contains a . but no / → likely a domain (e.g. example.com, *.example.com)
Starts with / or ~ or contains ** → path (for allowedRmPaths)
Otherwise → binary name

If ambiguous, ask the user.

Step 2 — Locate

Check every config layer:

User: $CLAUDE_PLUGIN_DATA/config.json or ~/.claude/bash-smart-approve.json
Project: <cwd>/.claude/bash-smart-approve.json

Find the item in the relevant array (allowedBinaries, allowedCurlDomains, allowedRmPaths, or deniedPatterns).

If the item is only in defaults (shipped with the plugin, not in any user config) → tell the user: "X is a built-in default. To block it, add it to deniedPatterns instead." Suggest the exact regex.

If the item appears in multiple layers → ask which to remove (or both).

Step 3 — Confirm and edit

Show the user the proposed diff. On approval, Edit the config file(s) and remove the array entry.

Step 4 — Summary

Report:

Item removed from <file>
No restart needed — config reloads on next hook invocation
Hint: /bash-smart-approve:list to verify

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 41 lines · 54 tokens per session scan A d9841be03aef

Subscribe to this mod's changes

bash-smart-approve:remove is a skill published in the GitHub repository pr3m/claude-code-bash-smart-approve (1 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 395 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security allowlist bash claude-code claude-code-hook claude-code-plugin

x-nets

Enhanced netstat module with cached data and structured output. View network connections, routing tables, and interface statistics in interactive or TSV/CSV formats. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 69 tokens

x-mankier

Search and browse man pages from ManKier.com. Command line interface for ManKier man page repository. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 62 tokens

x-osv

CLI for Google OSV database. Query vulnerabilities for packages, scan local projects for vulnerable dependencies. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill). Required Tool: Install osv-scanner for project scanning (see https://github.com/google/osv-scanner).

x-cmd/x-cmd · 72 tokens