Recon Skills is a pack of security-testing skills covering reconnaissance, web applications, APIs, authentication, vulnerability validation, cloud infrastructure, and reporting. Security professionals use it for authorized assessments of systems they own or have written permission to test. The catalogue entries are individual skills from the pack.
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/uphiago/recon-skillsnpx agentmods add skills/uphiago/recon-skills/visual-reconWrote 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/uphiago/recon-skills/visual-recon)<a href="https://agentmods.dev/skills/uphiago/recon-skills/visual-recon"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/visual-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/uphiago/recon-skills/visual-recon"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/visual-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 Anti-Refusal · line 110 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00018 | $0.01519 |
| Opus 5.5 | $0.00007 | $0.00608 |
| Sonnet 5.5 | $0.00004 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
visual-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 1mo 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.
compatibility: Requires curl, httpx, python3 How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Recon
Automatically screenshot every live host to triage hundreds of subdomains visually instead of manually opening each one. Combined with technology fingerprinting, this reveals technology stacks, default CMS install pages, admin panels, and misconfigured services at a glance. Process 500+ hosts in minutes and identify high-value targets by visual inspection.
When to Use
- You have 100+ live subdomains and need to prioritize targets quickly.
- Manual browsing is too slow for bulk reconnaissance.
- Need to identify default install pages (WordPress setup, phpMyAdmin login, Jenkins dashboard).
- Want to compare visual fingerprints across subdomains (shared infrastructure).
- Target serves different content based on User-Agent or geolocation.
Prerequisites
terminalgowitness, httpx, and curl.gowitnessinstalled:go install github.com/sensepost/gowitness@latest.- A list of alive subdomains from
subdomain-enumeration.
Quick Start
gowitness file -f alive_subs.txt -P ./screenshots/ --no-http
Procedure
Phase 1 — Mass Screenshot Capture
# gowitness — fast, Go-based screenshot tool
gowitness file -f alive_subs.txt \
-P ./screenshots/ \
--no-http \
--timeout 15 \
--resolution-x 1440 \
--resolution-y 900
# With database for searchable results
gowitness file -f alive_subs.txt -P ./screenshots/ --no-http \
--db gowitness.db --chrome-window-x 1440 --chrome-window-y 900
# Query results
gowitness report list --db gowitness.db
gowitness report generate --db gowitness.db
# eyewitness — with HTML report generation
python3 EyeWitness.py \
-f alive_subs.txt \
--web \
-d ./eyewitness_output/ \
--timeout 15 \
--no-prompt
Phase 2 — Headless Mode for JS-Rendered Sites
# Single-page applications need JS execution
gowitness single -u https://[SPA_COMPANY] \
-P ./screenshots/ \
--chrome-window-x 1440 --chrome-window-y 900
# Batch headless capture
cat spa_urls.txt | while read url; do
gowitness single -u "$url" -P ./screenshots/
done
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.
- 1mo ago First seen · 179 lines · 18 tokens per session scan A 97e1c27dab5b
visual-recon is a skill published in the GitHub repository uphiago/recon-skills (1,312 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,519 once invoked, about $0.0001 per session on Opus 5.5. 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
securing-api-gateway-with-aws-waf
Securing API Gateway endpoints with AWS WAF by configuring managed rule groups for OWASP Top 10 protection, creating custom rate limiting rules, implementing bot control, setting up IP reputation filtering, and monitoring WAF metrics for security effectiveness.
auditing-aws-s3-bucket-permissions
Systematically audit AWS S3 bucket permissions to identify publicly accessible buckets, overly permissive ACLs, misconfigured bucket policies, and missing encryption settings using AWS CLI, S3audit, and Prowler to enforce least-privilege data access controls.
auditing-gcp-iam-permissions
Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI, Policy Analyzer, and IAM Recommender.
auditing-terraform-infrastructure-for-security
Auditing Terraform infrastructure-as-code for security misconfigurations using Checkov, tfsec, Terrascan, and OPA/Rego policies to detect overly permissive IAM policies, public resource exposure, missing encryption, and insecure defaults before cloud deployment.
detecting-compromised-cloud-credentials
Detecting compromised cloud credentials across AWS, Azure, and GCP by analyzing anomalous API activity, impossible travel patterns, unauthorized resource provisioning, and credential abuse indicators using GuardDuty, Defender for Identity, and SCC Event Threat Detection.
detecting-s3-data-exfiltration-attempts
Detecting data exfiltration attempts from AWS S3 buckets by analyzing CloudTrail S3 data events, VPC Flow Logs, GuardDuty findings, Amazon Macie alerts, and S3 access patterns to identify unauthorized bulk downloads and cross-account data transfers.