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 web-recongit 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/web-recon)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/web-recon"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/web-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/mingyiseclab/mingyi-atlas/web-recon"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/web-recon.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 | $0.00035 | $0.00883 |
| Opus 5 | $0.00017 | $0.00441 |
| Sonnet 5 | $0.00007 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
web-recon scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS "$URL" -o /tmp/probe.html -w '%{http_code}\n' How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Application Reconnaissance — Hub
Sub-skills under this directory:
| Sub-skill | Path | When to load |
|---|---|---|
| Discovery | load_skill("/skills/standard/recon/web-recon/discovery/SKILL.md") |
directory/file fuzzing, vhost, JS analysis |
| API enumeration | load_skill("/skills/standard/recon/web-recon/api-enumeration/SKILL.md") |
REST/GraphQL/parameter fuzzing |
| CMS scanning | load_skill("/skills/standard/recon/web-recon/cms-scanning/SKILL.md") |
WordPress/Joomla/Drupal detected |
| WAF detection | load_skill("/skills/standard/recon/web-recon/waf-detection/SKILL.md") |
proxy/CDN suspected |
| Auth mapping | load_skill("/skills/standard/recon/web-recon/auth-mapping/SKILL.md") |
login flow analysis |
| Cookie audit | load_skill("/skills/standard/recon/web-recon/cookie-audit/SKILL.md") |
sink behind session, race-condition recon |
For overall recon workflow, scope rules, and handoff format, see load_skill("/skills/standard/recon/workflow.md") (root workflow).
Tag-Driven Fast Paths
When the orchestrator passes challenge tags, skip straight to the matching sub-skill:
| Tag | First action | Sub-skill to load |
|---|---|---|
sqli |
Fire a single error-triggering payload on every form/param | /skills/standard/exploit/web/sqli/SKILL.md recon section |
ssti |
Probe every reflection point with {{7*7}} |
/skills/standard/exploit/web/ssti-exploitation/SKILL.md recon section |
lfi |
Path-traversal probe on every file/path param | discovery.md |
idor |
Enumerate object IDs on every user-data endpoint | api-enumeration.md |
auth |
Map the full auth flow before other recon | auth-mapping.md |
HTTP Request Deduplication Pattern
When iterating parameters (IDs, pages, paths), always deduplicate via recon/probed.txt to avoid re-probing the same URLs after context summarization:
URL="http://<TARGET>/api/resource/$ID"
if grep -Fxq "$URL" recon/probed.txt 2>/dev/null; then
echo "SKIP: $URL"
else
echo "$URL" >> recon/probed.txt
curl -sS "$URL" -o /tmp/probe.html -w '%{http_code}\n'
head -10 /tmp/probe.html
fi
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 70 lines · 35 tokens per session scan A 0562a988c06a
web-recon is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 883 once invoked, about $0.0002 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.