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.
git clone --depth 1 https://github.com/pr3m/claude-code-bash-smart-approveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/pr3m/claude-code-bash-smart-approve/bash-smart-approve)<a href="https://agentmods.dev/plugins/pr3m/claude-code-bash-smart-approve/bash-smart-approve"><img src="https://agentmods.dev/badge/plugins/pr3m/claude-code-bash-smart-approve/bash-smart-approve/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/pr3m/claude-code-bash-smart-approve/bash-smart-approve"><img src="https://agentmods.dev/badge/plugins/pr3m/claude-code-bash-smart-approve/bash-smart-approve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bash-smart-approve scanned grade A with 0 findings 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 1mo ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "bash-smart-approve",
"version": "0.2.0",
"description": "Auto-approves Claude Code Bash commands via AST-based allowlist. Handles pipes, subshells, compound commands, and env-var prefixes that literal Bash(...) prefix rules can't match.",
"author": {
"name": "Christjan Schumann",
"url": "https://github.com/pr3m"
},
"homepage": "https://github.com/pr3m/claude-code-bash-smart-approve",
"repository": "https://github.com/pr3m/claude-code-bash-smart-approve",
"license": "MIT",
"keywords": ["claude-code", "plugin", "hook", "bash", "permissions", "allowlist", "pretooluse"]
}
What it installs
The manifest is a name and a version. 8 skills, 1 hook travel with it, and installing the plugin installs all of them — 428 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill bash-smart-approve:list A 49 tokens
- Skill bash-smart-approve:review-log A 46 tokens
- Skill bash-smart-approve:allow A 53 tokens
- Skill bash-smart-approve:remove A 54 tokens
- Skill bash-smart-approve:status B 65 tokens
- Skill bash-smart-approve:install C 54 tokens
- Skill bash-smart-approve:import D 57 tokens
- Skill bash-smart-approve:uninstall D 50 tokens
- Hook PreToolUse A not measured
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.
- 1mo ago First seen · 14 lines scan A f4e70ec5b653
bash-smart-approve is a plugin published in the GitHub repository pr3m/claude-code-bash-smart-approve (1 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
caushell-claude
Session-aware shell guardrails for Claude Code backed by the Caushell runtime.
smart-approval
AI permission tier for Claude Code Bash commands: deny-list gate plus smart AI evaluation for unknown commands. Requires Claude Code >= 2.0.45, shfmt, jq (brew install shfmt jq).
claude-timestamp
Time awareness for coding agents, in Claude Code and Codex: in Claude Code, stamps every message with the local time and how long the turn took; in both, tells the agent when a turn runs long, a tool call is slow or work resumes after a gap, remembers how long each command usually takes in a project, and reports where.
simple-statusline-marketplace
A minimal statusline for Claude Code.
simple-statusline
A simple, hackable two-line statusline for Claude Code showing model, git status, context usage, and rate limits.
cprof
Select which Claude account a session uses, by default profile, per-repo pin, or directory rule.