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 MingyiSecLab/Mingyi-Atlas --skill discoverygit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/discovery)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/discovery"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/discovery/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/mingyiseclab/mingyi-atlas/discovery"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00021 | $0.01347 |
| Opus 5 | $0.00010 | $0.00674 |
| Sonnet 5 | $0.00004 | $0.00269 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
discovery scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
code=$(curl -s -o /dev/null -w "%{http_code}" "https://<target>/$path") How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Discovery — Directories, vHosts, JavaScript
Surface the application's path tree, alternate virtual hosts, and JS-embedded endpoints/secrets. This is the first pass of web recon — feeds every later sub-skill.
1. Directory & File Discovery
ffuf (Recommended — Fast, Flexible)
# Basic directory fuzzing
ffuf -u https://<target>/FUZZ -w /usr/share/wordlists/dirb/common.txt -mc 200,301,302,403
# With file extensions
ffuf -u https://<target>/FUZZ -w /usr/share/wordlists/dirb/common.txt \
-e .php,.asp,.aspx,.jsp,.html,.js,.json,.xml,.txt,.bak,.old,.sql,.zip,.tar.gz
# Filter by response size (exclude default pages)
ffuf -u https://<target>/FUZZ -w wordlist.txt -fs <default_size>
# Recursive scanning (depth 2)
ffuf -u https://<target>/FUZZ -w wordlist.txt -recursion -recursion-depth 2
# Throttled for stealth
ffuf -u https://<target>/FUZZ -w wordlist.txt -rate 10 -mc 200,301,302,403
Sensitive Files to Check
# Common sensitive paths
for path in .env .git/config .htaccess robots.txt sitemap.xml \
wp-config.php web.config server-status .DS_Store \
backup.sql dump.sql database.sql .svn/entries \
crossdomain.xml clientaccesspolicy.xml; do
code=$(curl -s -o /dev/null -w "%{http_code}" "https://<target>/$path")
echo "$code $path"
done
2. Virtual Host (vHost) Discovery
# vHost fuzzing via Host header
ffuf -u https://<target_ip>/ -H "Host: FUZZ.<target>" \
-w /usr/share/wordlists/subdomains.txt -fs <default_size>
# With TLS SNI
ffuf -u https://FUZZ.<target>/ -w /usr/share/wordlists/subdomains.txt \
-mc 200,301,302,403 -fs <default_size>
Why vHost discovery matters:
- Multiple applications may share one IP but respond differently based on Host header
- Internal/staging apps often hidden behind non-public vhost names
3. Nginx/Apache Alias Off-By-One Probe
When a server uses alias /var/www/static/ for /static, an off-by-one allows reading parent directory:
- Configured:
location /static { alias /var/www/static/; }→/static../becomes/var/www/static/../→ escapes to/var/www/ - Vulnerable to:
/static../<file>requests reading outside the alias root
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.
- 7d ago First seen · 117 lines · 21 tokens per session scan A f9edef30680b
discovery is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,347 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
web-enumeration
../../../red-team/web-enumeration/SKILL.md.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.12
Ensure access keys are rotated every 90 days or less.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.