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 cleanup-templategit 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/cleanup-template)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/cleanup-template"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/cleanup-template/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/cleanup-template"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/cleanup-template.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 | $0.00026 | $0.00823 |
| Opus 5 | $0.00013 | $0.00411 |
| Sonnet 5 | $0.00005 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
cleanup-template 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cleanup & Restoration Plan Generator
The cleanup plan is the anti-foothold roster — every artifact the kill chain will create must have a concrete removal command and a verifier, or dummy accounts / scheduled tasks / beacons routinely outlive the engagement.
When to Use
- After CONOPS is written (the kill chain phases dictate what artifacts will exist)
- User says "create cleanup plan", "list what we'll leave behind", "post-engagement teardown"
Workflow
Step 1: Map Kill Chain Phases → Expected Artifact Types
For every phase in CONOPS.kill_chain, infer which CleanupArtifact.artifact_type entries will be produced:
| Kill Chain Phase | Likely artifact_types |
|---|---|
| recon | tool (installed scanners), network-rule (firewall whitelist) |
| initial-access | account (test users), file (uploaded payloads), tool (web shells) |
| post-exploit | persistence-mechanism (scheduled-task / service / registry-run), account (created backdoor users), file (dropped binaries) |
| c2 | beacon (C2 implants), network-rule (egress allow), tool (sliver / cobalt-strike payloads) |
| exfiltration | file (staged exfil archives), network-rule (DNS tunneling) |
Step 2: Seed CleanupArtifact entries
For each expected artifact, set:
artifact_type— category abovehost— placeholder (e.g."<initial-access target>") — operations agents replace at run timepath— likely filesystem / registry / account-name locationpersistence_mech— concrete mechanism if applicableremoval_command— idempotent shell or API call to removeverifier_command— zero-exit on successcreated_by_objective— left blank; operations agents fill on creationremoved=False,removed_at=""
Step 3: Pre-engagement Baseline
Set pre_engagement_baseline to whatever snapshot reference the operator gives during the interview (volume ID, AWS AMI, hypervisor snapshot, manual filesystem hash list). If no baseline is available, record that explicitly — it's a critical risk signal for the engagement owner.
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.
- 9d ago First seen · 73 lines · 26 tokens per session scan A a5e4b9502eee
cleanup-template is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 823 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
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.