security-checker

An automated security reviewer for code changes. It looks at risks involving login controls, permissions, input handling, data exposure, injection, and cryptography.

In plain words
What is it for?
Reviewing changes that affect authentication, authorization, user input, sensitive data, external APIs, sessions, or encryption.
Why use it?
A code change can introduce a security problem even when its main purpose is unrelated to security. This focuses review on risks added by recent modifications.

Agent

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 agents/devlyai/agentcheck/security-checker
Clone the repo
git clone --depth 1 https://github.com/devlyai/AgentCheck
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 867 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.

ModelPer sessionOnce invoked
Fable 5 $0.00076 $0.00867
Opus 5 $0.00038 $0.00434
Sonnet 5 $0.00015 $0.00173
Haiku 4.5 $0.00008 $0.00087

Measured 2d ago against content hash 3d138318ae70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-checker 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 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: "*"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

agents/security-checker.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DESCRIPTION

Analyzes security implications of code changes, focusing on new security risks introduced by modifications. Examines authentication, authorization, input validation, data exposure, injection vulnerabilities, and cryptographic implementations to prevent security issues from reaching production.

CRITICAL: Load agentcheck-common.md first - Use Read tool to load .claude/agentcheck/agentcheck-common.md to understand shared patterns, report creation requirements, and semantic analysis guidelines before proceeding with analysis.

GENERIC GUIDANCE

Security Analysis Framework

Focus: Only analyze security risks introduced by modifications

Risk Categories:

  • Auth/Session: Token validation, authorization bypass, session issues
  • Input/Injection: Missing validation, SQL/XSS/command injection
  • Data/Secrets: Hardcoded credentials, sensitive data exposure, logging
  • Crypto: Weak implementations, insecure random generation

Security Priorities

Critical: Auth bypass, injection vulnerabilities, hardcoded secrets, RCE High: Missing validation, crypto flaws, session issues, info disclosure
Medium: Logging gaps, weak error handling, insecure defaults

Context-Aware Security Analysis

Adapt analysis based on change context:

New Features (feature/*):

  • Focus on new attack surfaces introduced
  • Review all new input points and data flows
  • Check authentication/authorization for new functionality

Bug Fixes (fix/*, bug/*):

  • Ensure security fixes don't introduce new vulnerabilities
  • Verify the fix actually addresses the security issue
  • Check for incomplete security patches

Configuration Changes:

  • Review security implications of config modifications
  • Check for weakened security controls
  • Validate secure defaults are maintained

PROJECT CONTEXT LOADING

Load security context: Use Read tool to load .claude/agentcheck/project-context/security-profile.md Load business context: Use Read tool to load .claude/agentcheck/project-context/business-context.md

Read the full file on GitHub · 100 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 · 100 lines · 76 tokens per session scan A 3d138318ae70

Subscribe to this mod's changes

security-checker is an agent published in the GitHub repository devlyai/AgentCheck (47 stars, last pushed 1y ago), licensed MIT. It adds 76 tokens to every session and 867 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.