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 skills add briiirussell/cybersecurity-skills --skill recongit clone --depth 1 https://github.com/briiirussell/cybersecurity-skillsWrote 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/briiirussell/cybersecurity-skills/recon)<a href="https://agentmods.dev/skills/briiirussell/cybersecurity-skills/recon"><img src="https://agentmods.dev/badge/skills/briiirussell/cybersecurity-skills/recon/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/briiirussell/cybersecurity-skills/recon"><img src="https://agentmods.dev/badge/skills/briiirussell/cybersecurity-skills/recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 49 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00074 | $0.01002 |
| Opus 5 | $0.00037 | $0.00501 |
| Sonnet 5 | $0.00015 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
recon scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://crt.sh/?q=%25.$ARGUMENTS&output=json" | jq -r '.[].name_value' | sort -u How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recon — Penetration Testing Reconnaissance
Perform structured reconnaissance against an authorized target, organizing findings into an actionable attack surface map.
Cross-references: osint-recon for the deeper open-source-intelligence pass (people, organizations, historical data) — this skill is the active/passive target-mapping side, osint-recon is the broader investigative side; they pair naturally. web-pentest for the next stage once recon has produced an attack surface map and an authorized target list. owasp-audit for source-code review when you have access to the target's code.
Authorization Check
Before running any commands, confirm:
- The user has written authorization for the target (pentest engagement, bug bounty program, CTF/lab environment)
- The target is within the defined scope
If authorization is unclear, ask before proceeding. Never assume authorization.
Methodology
Phase 1: Passive Recon
Gather information without touching the target directly.
DNS enumeration:
- Run
dig any $ARGUMENTSfor A, AAAA, MX, TXT, NS, CNAME records - Attempt zone transfer:
dig axfr @ns-server $ARGUMENTS - Enumerate subdomains via certificate transparency:
curl -s "https://crt.sh/?q=%25.$ARGUMENTS&output=json" | jq -r '.[].name_value' | sort -u
WHOIS and registration: Run whois $ARGUMENTS for registrant, nameserver, and creation date info.
Search engine dorking: Use targeted queries — site:, inurl:, filetype:, intitle: — to find exposed pages, documents, and admin panels.
Technology fingerprinting: Identify frameworks, CMS, server software, and JavaScript libraries from public-facing pages.
Public code repositories: Search GitHub/GitLab for the target's org name, domain, API keys, or internal paths.
Historical data: Check the Wayback Machine for old endpoints, removed pages, and configuration files.
Phase 2: Active Recon (explicit authorization only)
Port scanning:
nmap -sC -sV -oN scan-results.txt $ARGUMENTS
Start with top 1000 ports. Expand to full range (-p-) if needed. Use -Pn if the host appears down but is in scope.
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.
- 12d ago First seen · 114 lines · 74 tokens per session scan A 380c788913c7
recon is a skill published in the GitHub repository briiirussell/cybersecurity-skills (387 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,002 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…