Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ShulkwiSEC/bb-hugenpx agentmods add skills/shulkwisec/bb-huge/hackerone-brain-mcpWrote 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/skills/shulkwisec/bb-huge/hackerone-brain-mcp)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/hackerone-brain-mcp"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/hackerone-brain-mcp/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.
<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/hackerone-brain-mcp"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/hackerone-brain-mcp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.02400 |
| Opus 5 | $0.00024 | $0.01200 |
| Sonnet 5 | $0.00010 | $0.00480 |
| Haiku 4.5 | $0.00005 | $0.00240 |
Grade A, and why
hackerone-brain-mcp-server 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hackerone-brain-mcp-server — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HackerOne Brain (H1 Brain) MCP Server
When to Use
- When starting a new bug bounty program and need to pull scope/policy into
.claudemd. - When checking disclosed reports to avoid submitting duplicates.
- When researching what vulnerability types a program rewards highest.
- When building target-specific context for Claude's autonomous hunting sessions.
Prerequisites
- HackerOne API token (from HackerOne settings → API → Generate Token)
- Node.js 18+ installed
- Claude Code CLI with MCP server support enabled
H1_API_TOKENenvironment variable set
Core Concept
"H1 Brain is an MCP Server that pulls HackerOne program policy and disclosed reports directly into Claude's context." — Episode 166 [32:02]
MCP (Model Context Protocol) servers extend Claude's capabilities by providing structured access to external data sources. H1 Brain connects Claude to HackerOne's platform data.
Workflow
Phase 1: MCP Server Setup
Add H1 Brain to your Claude Code CLI MCP configuration:
// ~/.claude/mcp_servers.json
{
"h1-brain": {
"command": "npx",
"args": ["-y", "h1-brain-mcp"],
"env": {
"H1_API_TOKEN": "${H1_API_TOKEN}"
}
}
}
If the h1-brain-mcp package is not available publicly, build a custom MCP server:
// mcp-servers/h1-brain/index.ts
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
const H1_API_BASE = "https://api.hackerone.com/v1";
const H1_TOKEN = process.env.H1_API_TOKEN;
const server = new Server({ name: "h1-brain", version: "1.0.0" }, {
capabilities: { tools: {} },
});
// Tool: Get program policy and scope
server.setRequestHandler("tools/list", async () => ({
tools: [
{
name: "get_program_policy",
description: "Get a HackerOne program's policy, scope, and bounty table",
inputSchema: {
type: "object",
properties: { handle: { type: "string", description: "Program handle (e.g., 'github')" } },
required: ["handle"],
},
},
{
name: "search_disclosed_reports",
description: "Search publicly disclosed reports for a program",
inputSchema: {
type: "object",
properties: {
handle: { type: "string" },
query: { type: "string", description: "Search query (e.g., 'SSRF', 'IDOR')" },
},
required: ["handle"],
},
},
],
}));
server.setRequestHandler("tools/call", async (request) => {
const { name, arguments: args } = request.params;
if (name === "get_program_policy") {
const res = await fetch(`${H1_API_BASE}/hackerone/programs/${args.handle}`, {
headers: { Authorization: `Bearer ${H1_TOKEN}` },
});
const data = await res.json();
return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
}
if (name === "search_disclosed_reports") {
const res = await fetch(
`${H1_API_BASE}/reports?filter[program][]=${args.handle}&filter[disclosed]=true&page[size]=20`,
{ headers: { Authorization: `Bearer ${H1_TOKEN}` } }
);
const data = await res.json();
return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
}
return { content: [{ type: "text", text: "Unknown tool" }] };
});
const transport = new StdioServerTransport();
server.connect(transport);
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.
- 7d ago First seen · 280 lines · 49 tokens per session scan A 018f4ce030c5
hackerone-brain-mcp-server is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 2,400 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.
Other skills, from other repositories
hackerone-brain-mcp-server
Use the H1 Brain MCP Server to pull HackerOne program policies, scope definitions, and disclosed vulnerability reports directly into Claude's context. Based on Critical Thinking Bug Bounty Podcast Episode 166.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
governance-hotl
OpenMesha governance — fail-closed policy, HOTL for irreversible actions, audit log inspection. Use when reviewing denials, escalations, or audit trails.
governance-audit
Inspect Server OS policy decisions, capability grants, and the audit log.
safe-tool-use
Policy-aware tool usage, HITL, attestation, and plan quotas.
brandkit
Brand kit visual design and identity guidelines skill.