intel — Claude Code command: what it does, how to install
Fetches target intelligence on demand: scans NVD and GitHub advisories, checks HackerOne reports, and flags untested endpoints from hunt memory.
MIT ★ 16,193 updated 2026-10-29
/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsoulsWhat intel does
The /intel target.com command automates reconnaissance for a selected target. It queries NVD and GitHub Advisory records via web search to match the target's software stack. If present, learn.py acts as a local accelerator. The command functions without it.
Next, it checks HackerOne activity and cross-references findings against patterns in docs/disclosed-reports/. If you connected the HackerOne MCP server, it pulls disclosed reports automatically. The output prioritizes unreviewed endpoints and critical CVEs based on your local hunt memory files.
What it helps with
- find CVEs and advisories matching a target's tech stack
- cross-reference target endpoints with local hunt memory
- check disclosed HackerOne reports for relevant methodology
Example prompts for the agent
- /intel target.com
- /intel api.example.com
How to install intel
1Plugin marketplace
/plugin marketplace add elementalsouls/Claude-BugHunter/plugin install claude-bughunter@elementalsouls2Manually: put the files in place
.claude/commands/intel.mdCall it with /intel. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/intel.mdCall it with /prompts:intel. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/intel.prompt.mdManually: put the files in place
.gemini/commands/intel.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about intel
How to install the intel command in Claude Code?
First add the repository by running /plugin marketplace add elementalsouls/Claude-BugHunter. Next, install the package with /plugin install claude-bughunter@elementalsouls.
What does the intel command do?
It gathers security intelligence for a target domain by looking up CVEs, checking HackerOne disclosed reports, and flagging untested endpoints from your hunt history.
Is learn.py required to run the intel command?
No. The learn.py script is strictly an optional accelerator. Without it, Claude Code performs the web lookups directly.
Source text
intel.md · MIT
--- name: intel description: On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Pulls NVD/GitHub-Advisory CVEs + bundled disclosed reports + hunt memory context. Usage: /intel target.com --- # /intel Fetch actionable intelligence for a target. ## What This Does 1. Looks up CVEs and advisories matching the target's tech stack (NVD + GitHub Advisory via web search; `learn.py` is used as an accelerator only if present) 2. Fetches HackerOne Hacktivity for the target (via HackerOne MCP if available) and cross-references the bundled `docs/disclosed-reports/` 3. Cross-references with hunt memory — flags untested CVEs and new endpoints 4. Outputs prioritized intel with hunt recommendations ## Usage ``` /intel target.com ``` ## Output ``` INTEL: target.com ═══════════════════════════════════════ ALERTS: [CRITICAL] CVE-2026-XXXX — Next.js middleware bypass (CVSS 9.1) target.com runs Next.js 14.2.3 (vulnerable). Patch: 14.2.4. → You haven't tested this endpoint yet. Hunt candidate. [HIGH] New feature detected: /api/v3/billing/invoices Not in your tested_endpoints list. 3 new paths. → New = unreviewed. Priority hunt target. [INFO] 2 new disclosed reports on HackerOne for target.com → Read for methodology insights before hunting. MEMORY CONTEXT: Last hunted: 2026-03-24 (2 days ago) Tech stack: Next.js 14.2.3, GraphQL, PostgreSQL Untested CVEs: 1 critical, 0 high ``` ## Data Sources | Source | What | Auth required? | |---|---|---| | NVD (web) | CVEs matching tech stack | No | | GitHub Advisory (web) | Security advisories | No | | `docs/disclosed-reports/` | Bundled disclosed-report patterns | No (local) | | HackerOne Hacktivity / MCP (if connected) | Disclosed reports, program stats | No (public) | | Hunt memory | Previously tested endpoints | Local files | > `learn.py` is an optional accelerator. If it isn't present, Claude performs the > lookups above directly — the command works without it.
© Sachin Sharma · MIT · elementalsouls/Claude-BugHunter