Custom AI Agent is a Burp Suite extension that adds AI-assisted security analysis, scanning, and connections to external AI agents through MCP. It is intended for security testers and bug bounty researchers using local or cloud AI providers during manual and automated web-application testing.
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.
npx agentmods add instructions/six2dez/burp-ai-agent/agents-mdgit clone --depth 1 https://github.com/six2dez/burp-ai-agentWrote 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.
[](https://agentmods.dev/instructions/six2dez/burp-ai-agent/agents-md)<a href="https://agentmods.dev/instructions/six2dez/burp-ai-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/six2dez/burp-ai-agent/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
burp-ai-agent AGENTS.md 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Burp AI Agent Extension (Kotlin) — Codex Instructions
Non-negotiables
- All explanations and comments MUST be in English.
- All code MUST be in English.
- Kotlin + Gradle Kotlin DSL.
- Burp Montoya API.
- Target: Burp Community + Pro, cross-platform (macOS/Linux/Windows).
- Production-grade: stable, defensive coding, deterministic modes, audit logging.
Architecture constraints
- Keep a strict boundary between:
- UI (Swing)
- Context collection (Burp selections)
- Redaction pipeline (privacy modes)
- Backend adapters (pluggable)
- Supervisor (start/stop/restart)
- Audit logging (JSONL + hashes)
- Passive AI Scanner (background traffic analysis)
- New backends must be addable without refactoring core logic (ServiceLoader).
Features required
- Burp tab UI
- Context menu actions for:
- Requests/responses
- Repeater tabs
- Scanner findings (Pro)
- Backends at launch:
- Codex CLI
- Gemini CLI
- Claude CLI
- Copilot CLI
- OpenCode CLI
- Ollama (local)
- LM Studio (local)
- NVIDIA NIM
- Perplexity
- Generic OpenAI-compatible
- Anthropic (native Messages API, not a CLI wrapper)
- Burp native AI
- Supervision of external agents (launch/restart/stop)
- Embedded UI + optional external terminal spawning
- Privacy modes: cookie stripping, token redaction, host anonymization
- Audit/session logs + reproducible prompt bundles
- AI Passive Scanner for automatic traffic analysis
MCP integration
- Built-in MCP server (SSE + optional stdio)
- Prefer designs that allow integration with Burp MCP tools.
- Do not leak raw traffic outside Burp when privacy mode is enabled.
- MCP tools include: issue_create for programmatic issue creation
AI Passive Scanner
- Background analysis of proxy traffic using selected AI backend
- Automatic issue creation when confidence >= 85%
- Configurable: rate limit, in-scope only, max size
- Issues prefixed with [AI] for identification
Quality bar
- Use small, testable components
- Favor pure functions for redaction
- Add unit tests where feasible
- No demo-only shortcuts
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.
- 6d ago First seen · 64 lines · 513 tokens per session scan A f96dd2449aa5
burp-ai-agent AGENTS.md is an instructions file published in the GitHub repository six2dez/burp-ai-agent (1,483 stars, last pushed 3d ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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 2026-08-30.
Other instructions, from other repositories
DorkAgent CLAUDE.md
Instructions for yee-yore/DorkAgent, covering claude.md, project overview, commands, running the tool and interactive mode (menu-driven interface).
Burp-MCP-Security-Analysis-Toolkit CLAUDE.md
Instructions for SnailSploit/Burp-MCP-Security-Analysis-Toolkit, covering burp mcp security analysis toolkit, your environment, core principles, skill loading protocol and available skills.
osmedeus AGENTS.md
Instructions for j3ssie/osmedeus, a project described as: A Modern Orchestration Engine for Security.
ARL-Next AGENTS.md
AGENTS.md instructions for owl234/ARL-Next, covering 🤖 ai agent 核心准则, 1. 核心思维与行为红线, 2. 编码与架构规范, 3. ci/cd 与部署闭环 and 4. 文档与输出规范.
fucking-awesome-web-security CLAUDE.md
Claude Code instructions for Correia-jpv/fucking-awesome-web-security, covering claude.md, what this repo is, files of note, editing rules and entry schema.
metabigor AGENTS.md
Instructions for j3ssie/metabigor, a project described as: OSINT power without API key hassle.