scan

scan is a command for coding agents from fusengine/agents. It costs 30 tokens per session (485 once invoked), scanned A, original, MIT.

A command that audits a software project for security problems, including vulnerable dependencies, common web risks, exposed secrets, and weak authentication patterns. It produces a structured report of its findings.

In plain words
What is it for?
Use it to review dependencies, check for OWASP Top 10 issues, inspect security headers and authentication, or scan for hardcoded credentials.
Why use it?
It brings several security checks into one project scan, helping uncover known vulnerabilities and risky code before they reach users.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the fuse-security plugin — 5 skills, 1 command, 1 agent shipped together

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/fusengine/agents/scan
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Or install fuse-security, the plugin that ships this one along with the rest of its 5 skills, 1 command, 1 agent.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/fusengine/agents/scan.svg)](https://agentmods.dev/commands/fusengine/agents/scan)
Your own site
<a href="https://agentmods.dev/commands/fusengine/agents/scan"><img src="https://agentmods.dev/badge/commands/fusengine/agents/scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 485 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 $0.00030 $0.00485
Opus 5 $0.00015 $0.00243
Sonnet 5 $0.00006 $0.00097
Haiku 4.5 $0.00003 $0.00049

Measured yesterday against content hash b31fe0f940ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan 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 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.

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/security-expert/commands/scan.md · 62 lines

What it actually says

Security Scan

Execute a comprehensive security audit following the 5-phase workflow.

Usage

  • /scan - Full security audit of current project
  • /scan --deps-only - Dependency audit only
  • /scan --headers - Security headers check only
  • /scan --auth - Authentication patterns audit only
  • /scan path/to/dir - Scan specific directory

Workflow

Phase 1: DETECT

Identify project language and framework automatically:

  • Scan for marker files (package.json, composer.json, etc.)
  • Detect framework versions and dependencies
  • Map to appropriate scan patterns

Phase 2: RESEARCH

Query recent CVEs for the detected stack:

  • Use Exa to search NVD, OSV.dev, GitHub Advisory
  • Focus on dependencies found in project
  • Check for known exploits

Phase 3: SCAN

Run vulnerability patterns and dependency audit:

  • Execute language-specific grep patterns (OWASP Top 10)
  • Run bun ${CLAUDE_PLUGIN_ROOT}/../node_modules/@fusengine/harness/dist/cli/bin.mjs scan <dir> for automated pattern matching
  • Execute dependency audit CLI (npm audit, composer audit, etc.)
  • Detect hardcoded secrets and credentials

Phase 4: REPORT

Generate structured vulnerability report:

  • Categorize by severity: CRITICAL, HIGH, MEDIUM, LOW
  • Map findings to OWASP A01-A10 categories
  • Include file:line references and fix instructions

Phase 5: FIX

Delegate corrections to sniper agent:

  • Generate fix instructions per vulnerability
  • Invoke sniper with precise file:line + description
  • Validate all fixes applied correctly

Arguments

  • $ARGUMENTS specifies scan options and target path

Examples

  • /scan → Full OWASP + dependency + secrets audit
  • /scan --deps-only → Quick dependency vulnerability check
  • /scan --auth → JWT/OAuth/session security patterns
  • /scan src/api/ → Scan only API directory
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. yesterday First seen · 62 lines · 30 tokens per session scan A b31fe0f940ac

Subscribe to this mod's changes

scan is a command published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 485 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.