Metabigor logo

Metabigor

CommunityPopular
j3ssie
metabigor

Use when operating the metabigor CLI for OSINT recon and infrastructure mapping without API keys. Covers finding network ranges from an ASN, org, domain, or IP (net); enumerating subdomains from certificate logs (cert); enriching IPs with ports/CVEs via Shodan InternetDB (ip); searching public GitHub code for secrets and subdomains (github); clustering IPs by ASN (cluster); pivoting to related domains via crt.sh/WHOIS/analytics (related); detecting CDN/WAF vendors and isolating candidate origins (cdn); collecting archived URLs and WARC-mined endpoints (url); refreshing the offline databases (update); and chaining these commands into a recon pipeline.

Overview

Publisherj3ssie
Repositorymetabigor
Skill namemetabigor
Stars
1.8K
Forks
214
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by j3ssie on GitHub. Read the source before you install it.

Installation

Install the Metabigor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/j3ssie/metabigor.git /tmp/metabigor
mkdir -p .claude/skills
cp -r /tmp/metabigor/public/skills/metabigor .claude/skills/metabigor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Metabigor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Metabigor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Metabigor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Metabigor

CLI-first OSINT tool that maps a target's infrastructure from free sources, no API keys. Part of the Osmedeus Engine. Every command takes targets the same four ways and renders through one -f/--format flag, so any command pipes cleanly into the next.

TL;DR

bash
metabigor net AS13335                  # network ranges (CIDRs) behind an ASN
metabigor cert hackerone.com           # subdomains from certificate logs
metabigor ip 1.1.1.1                   # open ports + CVEs for an IP (free, no key)
metabigor related tesla.com            # other domains the target owns
metabigor cdn --exclude -I ips.txt     # drop CDN/WAF IPs, keep candidate origins
metabigor url hackerone.com -f flat    # every archived URL, ready to pipe

metabigor <command> -h is authoritative for the version you have installed.

Mental model

  • Zero configuration, no API keys. net/cluster work fully offline from a bundled database. The url command optionally reads keys from the environment only (VT_API_KEY/VIRUSTOTAL_API_KEY, INTELX_API_KEY, URLSCAN_API_KEY) — never from a flag or config file.
  • Results to stdout, logs to stderr. Pipes stay clean at any log level, so metabigor cert x.com | other-tool always works. Progress is quiet by default; add -v for step-by-step lines.
  • One output flag. -f/--format text|flat|json|csv covers every command. There are no per-command format flags.
  • Everything composes. The flat format emits the bare primary value so one command's output is the next command's input.
  • Non-zero exit on failure, so metabigor drops into &&, set -e, and CI.

The four ways to pass targets

Identical on every command; the merged list is deduplicated.

bash
metabigor cert example.com                 # as an argument
metabigor cert example.com tesla.com       # several arguments
metabigor cert -i example.com              # with -i (use when a target looks like a flag)
metabigor cert -I domains.txt              # from a file, one per line (# comments ignored)
cat domains.txt | metabigor cert           # on stdin

Stdin is read only when no target was given another way, so metabigor net AS13335 never blocks inside a script or CI job.

Command router

I need to…Use
Find CIDRs announced by an ASNmetabigor net AS13335
Find which ASN owns an IPmetabigor net 1.1.1.1 --detail
Find ranges by company namemetabigor net --org Cloudflare
Query live BGP sources, not the local DBmetabigor net --live tesla.com
Enumerate subdomains from cert logsmetabigor cert hackerone.com
Cert search by organizationmetabigor cert "HackerOne Inc"
Strip *. from wildcard cert entriesmetabigor cert example.com --clean
Cert IDs, issuers, validity datesmetabigor cert example.com --detail
Ports / hostnames / CVEs for an IPmetabigor ip 1.1.1.1
Enrich a whole CIDRmetabigor ip 1.1.1.0/28
Search public GitHub code (grep.app)metabigor github hackerone.com
Pull only subdomains out of code matchesmetabigor github tesla.com --subs
Show the matching code linesmetabigor github "api_key=" --detail
Group IPs by owning ASNmetabigor cluster -I ips.txt
Pivot to related domains (all sources)metabigor related hackerone.com
Pivot via specific sourcesmetabigor related tesla.com --sources crt,whois
Collect archived URLs (keyless sources)metabigor url hackerone.com
Scope URL collection to one hostmetabigor url blog.hackerone.com --no-subs
Detect CDN/WAF vendor for an IPmetabigor cdn 1.1.1.1
Drop CDN/WAF IPs, keep originsmetabigor cdn --exclude -I ips.txt
Keep only CDN/WAF-protected IPsmetabigor cdn --only -I ips.txt
Refresh the offline ASN/country DBsmetabigor update
Print / install these agent skillsmetabigor skills get --full

Output formats

-f/--format on every command. Default is text.

FormatFlagWhat you getUse it for
Text (default)-f textReadable `ab
Flat-f flatThe bare primary value, one per linePiping into other tools
JSON-f jsonOne JSON object per linejq, automation
CSV-f csvRows behind one headerSpreadsheets, reports
bash
metabigor ip 1.1.1.0/28                 # 1.1.1.1 | 80,443 | one.one.one.one
metabigor ip 1.1.1.0/28 -f flat         # 1.1.1.1:80
metabigor ip 1.1.1.0/28 -f json | jq .  # {"ip":"1.1.1.1","ports":[80,443],...}
metabigor ip 1.1.1.0/28 -f csv -o ports.csv

-o <file> also writes results to a file (overwrite; --append to add).

Per-command notes

Things -h alone won't make obvious.

  • net auto-detects the target type; override with --asn, --ip, --domain, or --org (mutually exclusive). --detail adds ASN / org / country columns. --live swaps the offline DB for live BGP sources (bgp.he.net) — slower, but current.
  • cert prints a plain domain list by default. --detail gives the grouped certificate view (IDs, issuers, dates); --clean strips *.; --wildcard keeps only wildcard entries. Feed it into a resolver: metabigor cert t.com | dnsx -silent.
  • ip uses Shodan InternetDB (free, no key). IPs it knows nothing about are skipped; pass --all to keep them. CIDRs expand to hosts.
  • github needs Chrome/Chromium (grep.app blocks plain HTTP clients). Searches run one at a time regardless of -c to respect grep.app's rate limit. --subs returns subdomains only; --detail shows code; --pages N goes deeper.
  • cluster groups IPs/CIDRs by owning ASN, largest cluster first. Fully offline.
  • related sources: crt (crt.sh), whois (viewdns.info reverse WHOIS), analytics (shared Google Analytics / Tag Manager IDs), or all (default). Results are deduped across sources and tagged with the first source that found each.
  • cdn classifies IPs by CDN/WAF vendor. --exclude drops protected IPs (leaving candidate origins); --only keeps just the protected ones. The two are mutually exclusive.
  • url includes subdomains by default (queries *.target) — the single biggest lever on volume; --no-subs narrows it. GhostArchive is mined: its WARCs expose sub-request URLs (XHR/JSON endpoints) that no CDX index lists. Filters are off by default. See references/url-command.md.
  • update refreshes both the IP-to-ASN and IP-to-country databases in ~/.metabigor. A copy ships with the binary and unpacks on first use, so this is only needed to pick up newer routing data.

Global flags

  -i, --input string        Target to look up (also accepts arguments or stdin)
  -I, --input-file string   File of targets, one per line (use - for stdin)
  -o, --output string       Also write results to this file
  -f, --format string       Output format: text, json, csv, flat (default "text")
      --append              Append to the output file instead of overwriting it
  -c, --concurrency int     Number of parallel workers (default 10)
  -t, --timeout int         Request timeout in seconds (default 40)
      --retry int           Retries per failed request (default 3)
      --proxy string        Upstream proxy, e.g. http://127.0.0.1:8080
  -v, --verbose             Show step-by-step progress
  -q, --quiet               Show results and errors only
      --debug               Show HTTP traffic and internal traces (implies --verbose)
      --no-color            Disable colored log output

Recon pipeline

The point of the flat format: chain commands into a workflow.

bash
# ASN -> ranges -> live hosts with ports
metabigor net AS13335 -f flat | metabigor ip -f flat

# domain -> related domains -> their subdomains
metabigor related tesla.com -f flat | metabigor cert

# resolve subdomains, then split CDN from candidate origins
metabigor cert tesla.com | dnsx -silent -resp-only | metabigor cdn --exclude

# collect archived URLs and probe them
metabigor url tesla.com -f flat | httpx -silent

More multi-step workflows: references/recipes.md.

Escape hatches

bash
metabigor <command> -h     # authoritative flags for your installed version
metabigor version          # version, build date, commit
metabigor skills get --full  # print this skill and every reference

Resources

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Metabigor AI skill do?

Use when operating the metabigor CLI for OSINT recon and infrastructure mapping without API keys. Covers finding network ranges from an ASN, org, domain, or IP (net); enumerating subdomains from certificate logs (cert); enriching IPs with ports/CVEs via Shodan InternetDB (ip); searching public GitHub code for secrets and subdomains (github); clustering IPs by ASN (cluster); pivoting to related domains via crt.sh/WHOIS/analytics (related); detecting CDN/WAF vendors and isolating candidate origins (cdn); collecting archived URLs and WARC-mined endpoints (url); refreshing the offline databases...

Why use Metabigor on TypingMind?

Because you install it once and use it with any model. Metabigor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Metabigor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/j3ssie/metabigor/tree/main/public/skills/metabigor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Metabigor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Metabigor?

As many as you like. As long as a model supports skills, you can use Metabigor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Metabigor AI skill free?

Yes. It is published on GitHub by j3ssie under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇