OSINT Agent Skills
A knowledge base that turns any autonomous AI agent into a senior OSINT analyst.
接入你的智能体
发布者自己的命令。不是 PlugMCP 端点。
用我们的密钥与日志托管一份副本。
npx -y @frangelbarrera/[email protected]Claude Code 没有针对本地命令的安装链接。复制下方命令并在终端中运行。
claude mcp add frangelbarrera-osint-agent-skills -- npx -y @frangelbarrera/osint-agent-skills@1.4.1在终端中运行。
{ "mcpServers": { "frangelbarrera-osint-agent-skills": { "command": "npx", "args": [ "-y", "@frangelbarrera/[email protected]" ] } }}claude_desktop_config.json
远程 URL 还是本机命令? 两种安装方式的区别
osint-agent-skills is not an agent. It is not a script. It is not a SaaS.
It is a structured knowledge base — a curated set of methodologies, tool registries, pivot playbooks, ethics rules, and report templates — that any autonomous AI agent can consume to instantly adopt the operating discipline of a senior open-source intelligence analyst.
If you point Claude Code, Cursor, Ollama, OpenCode, AutoClaw, or any other agent framework at this repository, the agent will:
system-prompt.md and adopt the OSINT Agent Skills persona.knowledge/methodologies/ to plan its investigation.tools/free-tools.yaml and tools/apis.yaml to execute lookups.knowledge/pivot-playbooks/ to chain findings into networks.templates/reports/intelligence-report.md.ethics/legal-frameworks.md throughout — never suggesting illegal techniques, never fabricating findings.This repository is agent-agnostic. It works the same way regardless of which LLM or agent framework you use.
Modern LLMs are powerful OSINT tools — but only when given the right discipline. Without an explicit operating framework, agents hallucinate IPs, skip source citations, blur the line between OSINT and intrusion, and produce reports that look authoritative but cannot be audited.
osint-agent-skills solves this by codifying the operating rules that a senior analyst would otherwise enforce through peer review. The system prompt is brutally explicit about anti-hallucination. The pivot playbooks tell the agent exactly what to do when it finds an email, a domain, a phone number, a cryptocurrency wallet, or a photograph. The ethics framework defines what is in-bounds by jurisdiction. The report templates enforce source citation and confidence labeling.
The result: when you ask an agent that has consumed this knowledge base investigate the domain example.com", you get a structured intelligence report with cited sources, performed pivots, and explicit limitations — not a stream of plausible-sounding prose.
git clone https://github.com/frangelbarrera/osint-agent-skills
cd osint-agent-skills
Then point your agent at the repository. Integration guides:
Test prompt after setup:
Investigate the domain
example.comusing OSINT Agent Skills methodology. Produce a full intelligence report.
The agent should load the system prompt, plan the investigation using the intelligence cycle, run DNS/WHOIS/RDAP/CT-lookups against free tools, follow the domain-to-infrastructure pivot playbook, and deliver a structured report.
osint-agent-skills/
system-prompt.md # The brain agent adopts this persona
agent-config.yaml # Declarative config that agents read
README.md # This file
LICENSE # MIT
CONTRIBUTING.md # How to contribute
CHANGELOG.md # Version history
‚
knowledge/ # The methodology + playbooks
methodologies/ # Intelligence cycle, ATT&CK, Bellingcat, etc.
domains/ # Person, domain, IP, company, phone, crypto, ...
techniques/ # Dorks, EXIF, Wayback, CT logs, ...
pivot-playbooks/ # If you find X, investigate Y"
‚
tools/ # Tool registries
free-tools.yaml # No API key required
apis.yaml # API key required
mcp-tools.json # MCP-format for Claude / Cursor
cli-tools.yaml # Local CLI tools (sherlock, holehe, ...)
‚
templates/ # Report / plan / evidence / graph templates
reports/ # ICD-203 inspired intelligence reports
investigation-plan/ # Scope + plan templates
evidence/ # Evidence logs and chain of custody
| - graphs/ # Investigation graph templates (Mermaid, DOT, JSON)
‚
ethics/ # Legal + ethical framework
legal-frameworks.md # Per-jurisdiction laws (US, EU, UK, LatAm)
jurisdiction-rules.md # Country-specific rules
code-of-conduct.md # Investigator code of conduct
privacy-guidelines.md # PII handling
anti-hallucination.md # Anti-fabrication rules
‚
case-studies/ # Worked examples of real investigations
integrations/ # How to wire into each agent framework
examples/ # Walkthroughs of common investigations
The system prompt (system-prompt.md, ~3000 words) defines:
Read it in full: system-prompt.md.
The pivot playbooks are the most operationally valuable part of this repository. Each playbook specifies:
Current playbooks:
This repository was built with one principle above all others: agents that consume this knowledge base do not fabricate findings.
The system prompt explicitly forbids inventing IP addresses, email addresses, usernames, dates, tool outputs, or confidence levels. Each finding in a report must cite a source. Each tool invocation must be real — if a tool failed or returned nothing, that is what gets reported.
If an agent that has consumed this knowledge base fabricates a finding, that is a critical defect and should be reported as an issue. See ethics/anti-hallucination.md for the full rule set.
Every tool response now includes an output_hash field — a sha256 over the canonical JSON form of {tool, endpoint, status, result}. This lets downstream verifiers (audit logs, report reviewers, external scripts) confirm that any data attributed to a tool call was actually produced by that tool call.
The verify_output_integrity tool takes a claimed hash + the response payload subset and returns {valid: true} if the recomputed hash matches, or {valid: false, expected_hash, actual_hash} otherwise. Designed for downstream verifiers — not for in-band LLM self-verification (an LLM that can compute sha256 in its head could forge a matching pair).
This repository distills and restructures methodology originally compiled in OSINT-BIBLE by Frangel Raúl Crespo Barrera. OSINT-BIBLE is a curated index of 426+ OSINT resources across 33 sections; osint-agent-skills adapts that material for autonomous agent consumption.
Case studies reference investigations originally published by Bellingcat, Mandiant, CrowdStrike, CISA, and other public-domain threat intelligence sources. Citations appear in each case study file.
Tool descriptions reference the official documentation of each tool. Pricing and rate-limit information was current as of the repository's last update — always verify with the provider before relying on a specific limit.
MIT. See LICENSE.
See CONTRIBUTING.md. Pull requests that add new pivot playbooks, new free tools, or new jurisdiction rules are especially welcome.
Security issues should be reported privately according to the project's security policy. Please do not open a public issue for a suspected vulnerability.
The latest published npm release is 1.6.0. Versions 1.4.1 and 1.5.0 are deprecated on npm because they predate security and reliability fixes included in 1.6.0.
The project does not claim that every hardening change constitutes a separately exploitable vulnerability. Security advisories will be published only when a specific issue, affected version range, impact, and patched version have been technically confirmed.
See CHANGELOG.md.
OSINT knowledge base + MCP server for autonomous AI agents — Claude Code, Cursor, Kimi K3, recon & threat intel playbooks.
{ "mcpServers": { "frangelbarrera-osint-agent-skills": { "command": "npx", "args": [ "-y", "@frangelbarrera/[email protected]" ] } }}工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
Osint Agent Skills 通过 stdio 在本地运行。
上次检查时间:2026-10-27。 OSINT knowledge base + MCP server for autonomous AI agents — Claude Code, Cursor, Kimi K3, recon & threat intel playbooks.