scan-tool-call

scan-tool-call is a command for Claude Code from MaxwellCalkin/sentinel-ai. It costs 0 tokens per session (184 once invoked), scanned C, original, Apache-2.0.

A command for checking whether a proposed tool call contains dangerous actions or attempts to access sensitive data.

In plain words
What is it for?
It helps inspect shell commands and tool arguments and report their risk level and whether they should be blocked.
Why use it?
It provides a safety review before the tool call runs, helping catch destructive commands, data theft, or privilege escalation.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the sentinel-ai plugin — 1 skill, 5 commands, 1 MCP server shipped together

Good fit It helps inspect shell commands and tool arguments and report their risk level and whether they should be blocked.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/maxwellcalkin/sentinel-ai/scan-tool-call
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.

Clone the repo
git clone --depth 1 https://github.com/MaxwellCalkin/sentinel-ai

Made for: Claude Code.

Or install sentinel-ai, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 1 MCP server.

Wrote 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.

agentmods badge for scan-tool-call

README.md
[![agentmods](https://agentmods.dev/badge/commands/maxwellcalkin/sentinel-ai/scan-tool-call/github.svg)](https://agentmods.dev/commands/maxwellcalkin/sentinel-ai/scan-tool-call)
Your own site
<a href="https://agentmods.dev/commands/maxwellcalkin/sentinel-ai/scan-tool-call"><img src="https://agentmods.dev/badge/commands/maxwellcalkin/sentinel-ai/scan-tool-call/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.

agentmods 80×15 button for scan-tool-call

Your own site · 80×15
<a href="https://agentmods.dev/commands/maxwellcalkin/sentinel-ai/scan-tool-call"><img src="https://agentmods.dev/badge/commands/maxwellcalkin/sentinel-ai/scan-tool-call.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 184 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00184
Opus 5 $0.00000 $0.00092
Sonnet 5 $0.00000 $0.00037
Haiku 4.5 $0.00000 $0.00018

Measured 9d ago against content hash 9698d78da93d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

scan-tool-call scanned grade C with 2 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

2. Check for dangerous shell commands (rm -rf, credential access, etc.)

Makes network callslowCapability

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

3. Check for data exfiltration patterns (curl to external servers, etc.)
commands/scan-tool-call.md · 27 lines

What it actually says

/scan-tool-call — Check if a tool call is safe

Scan a tool call for dangerous operations before execution.

Usage

/scan-tool-call <tool_name>

Behavior

Use the Sentinel AI scan_tool_call MCP tool to:

  1. Parse the tool name and JSON arguments
  2. Check for dangerous shell commands (rm -rf, credential access, etc.)
  3. Check for data exfiltration patterns (curl to external servers, etc.)
  4. Check for privilege escalation attempts
  5. Report risk level and whether the call should be blocked

Present findings with:

  • Risk level (NONE, LOW, MEDIUM, HIGH, CRITICAL)
  • Threat type (dangerous_command, exfiltration, sensitive_file, privilege_escalation)
  • Description of the threat
  • Whether the tool call would be blocked

Input

$ARGUMENTS

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.

  1. 9d ago First seen · 27 lines · 0 tokens per session scan C 9698d78da93d

Subscribe to this mod's changes

scan-tool-call is a command published in the GitHub repository MaxwellCalkin/sentinel-ai (24 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 184 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.