mcp-browser: Agent for Claude Code

.claude/agents/security.md

security is an agent for Claude Code from bobmatnyc/mcp-browser. It costs 119 tokens per session (6,019 once invoked), scanned A, a copy of security, MIT.

A security-focused coding agent for finding vulnerabilities, assessing attack paths, and applying secure coding practices. It also describes limits and procedures for reading large files during security reviews.

In plain words
What is it for?
Use it for vulnerability reviews, security-sensitive code changes, attack-surface analysis, and secure implementation work.
Why use it?
It helps reduce the chance that security checks miss important risks or consume too much code at once during analysis.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the TodoWrite tool.

This is bobmatnyc/mcp-browser's own configuration. It tells Claude Code how to work on mcp-browser itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-browser configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bobmatnyc/mcp-browser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bobmatnyc/mcp-browser/main/.claude/agents/security.md
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-browser

Made for: Claude Code.

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 security

README.md
[![agentmods](https://agentmods.dev/badge/agents/bobmatnyc/mcp-browser/security/github.svg)](https://agentmods.dev/agents/bobmatnyc/mcp-browser/security)
Your own site
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-browser/security"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-browser/security/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 security

Your own site · 80×15
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-browser/security"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-browser/security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,019 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod 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 $0.00119 $0.06019
Opus 5.5 $0.00048 $0.02408
Sonnet 5.5 $0.00024 $0.01204
Haiku 4.5 $0.00012 $0.00602

Measured 1mo ago against content hash e01bb1aefcc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security 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.

Origin

This is a copy

88% identical to security — 231 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/security.md · 736 lines

How it starts

The opening of the file, as written. The whole thing — 736 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Agent - AUTO-ROUTED

Automatically handle all security-sensitive operations. Focus on vulnerability assessment, attack vector detection, and secure implementation patterns.

Memory Protection Protocol

Content Threshold System

  • Single File Limit: 20KB or 200 lines triggers mandatory summarization
  • Critical Files: Files >100KB generally summarized, never loaded fully
  • Cumulative Threshold: 50KB total or 3 files triggers batch summarization
  • SAST Memory Limits: Maximum 5 files per security scan batch

Memory Management Rules

  1. Check Before Reading: Always verify file size with LS before Read
  2. Sequential Processing: Process ONE file at a time, extract patterns, discard
  3. Pattern Caching: Cache vulnerability patterns, not file contents
  4. Targeted Reads: Use Grep for specific patterns instead of full file reads
  5. Maximum Files: Never analyze more than 3-5 files simultaneously

Forbidden Memory Practices avoid read entire files when Grep pattern matching suffices avoid process multiple large files in parallel avoid retain file contents after vulnerability extraction avoid load files >1MB into memory (use chunked analysis) avoid accumulate file contents across multiple reads

Vulnerability Pattern Caching

Instead of retaining code, cache ONLY:

  • Vulnerability signatures and patterns found
  • File paths and line numbers of issues
  • Security risk classifications
  • Remediation recommendations

Example workflow:

1. LS to check file sizes
2. If <20KB: Read → Extract vulnerabilities → Cache patterns → Discard file
3. If >20KB: Grep for specific patterns → Cache findings → Never read full file
4. Generate report from cached patterns only

Response Format

Read the full file on GitHub · 736 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. 1mo ago First seen · 736 lines · 119 tokens per session scan A e01bb1aefcc6

Subscribe to this mod's changes

security is an agent published in the GitHub repository bobmatnyc/mcp-browser (2 stars, last pushed 10mo ago), licensed MIT. It adds 119 tokens to every session and 6,019 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to security, differing in 231 lines, and is treated as a copy.

Related

Other agents, from other repositories

docs-specialist

Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.

ZaxbyHub/opencode-swarm · 34 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

seo-meta-optimizer

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

echoVic/blade-code · 39 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

code-reviewer

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

opencue/cuecards · 35 tokens

scramjet:instruction-semantics-analyzer

Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.

LeanAndMean/scramjet · 35 tokens