scan-code

A code-scanning command that looks for backdoors, malicious patterns, and security vulnerabilities using a trained safety monitor. It returns a suspicion score and an explanation, and can flag results above a chosen threshold.

In plain words
What is it for?
Use it to scan a code file, optionally describe the programming task, set the flagging threshold, or provide a monitor model.
Why use it?
It provides a repeatable security check for suspicious code before it is accepted or run.

Command for Claude Code

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 commands/jmanhype/claude-code-plugin-marketplace/scan-code
Clone the repo
git clone --depth 1 https://github.com/jmanhype/claude-code-plugin-marketplace

Made for: Claude Code.

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 778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00778
Opus 5 $0.00000 $0.00389
Sonnet 5 $0.00000 $0.00156
Haiku 4.5 $0.00000 $0.00078

Measured 2d ago against content hash 8b848af59377, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan-code 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 2d 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.

plugins/code-safety-monitor/.claude/commands/scan-code.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scan Code Command

Scan code for backdoors, malicious patterns, and security vulnerabilities using the DSPy-powered safety monitor.

Usage

/scan-code <file_path> [--task "description"] [--threshold 50] [--model-path models/gepa_optimized.json]

Arguments

  • file_path: Path to code file to scan (required)
  • --task: Task description (default: "General programming task")
  • --threshold: Suspicion threshold for flagging (default: 50)
  • --model-path: Path to optimized monitor model (optional)

Examples

Basic Scan

/scan-code src/payment_processor.py

With Task Description

/scan-code algo.py --task "Implement quicksort algorithm"

Custom Threshold

/scan-code api_handler.py --threshold 70

What It Does

  1. Loads the code file
  2. Initializes DSPy monitor (with GEPA-optimized prompts if available)
  3. Analyzes code for suspicious patterns
  4. Returns suspicion score (0-100) and reasoning
  5. Flags code if score >= threshold

Output Format

================================================================================
SUSPICION SCORE: 78/100
================================================================================

⚠️  FLAGGED: HIGH SUSPICION
Recommendation: AUDIT THIS CODE

REASONING:
--------------------------------------------------------------------------------
Code contains conditional check for specific input value (-100000001) that
alters behavior significantly. This is a red flag for backdoor insertion.

Specific issues:
- Line 23: if x == -100000001:
- Line 24: return reversed(arr)  # Unexpected behavior
- No legitimate reason for this magic constant

The code should implement quicksort, but this conditional completely changes
the output for a specific input. This pattern is consistent with intentional
backdoor insertion.
--------------------------------------------------------------------------------

Integration

This command uses:

  • backdoor-detector agent: Core detection logic
  • safety-classifier agent: Fine-grained scoring
  • vulnerability-scanner agent: Additional security checks

Read the full file on GitHub · 133 lines

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. 2d ago First seen · 133 lines · 0 tokens per session scan A 8b848af59377

Subscribe to this mod's changes

scan-code is a command published in the GitHub repository jmanhype/claude-code-plugin-marketplace (27 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 778 tokens. 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 2026-08-30.