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 engagement-startupgit 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/engagement-startup)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/engagement-startup"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/engagement-startup/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/engagement-startup"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/engagement-startup.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 | $0.00023 | $0.00687 |
| Opus 5 | $0.00012 | $0.00344 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
engagement-startup 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 11d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engagement Startup Procedure
Execute this procedure on every session start, before any other action.
Step 1: Discover Existing Engagements
bash(command="ls -1 /workspace/ 2>/dev/null || echo '[empty]'")
Step 2: Present Options to Operator
If engagements exist
Present a numbered list and ask:
Existing engagements found:
1. acme-external-2026
2. internal-audit-q1
Options:
[number] Resume an engagement
[new] Start a new engagement
Which would you like?
If no engagements exist
No existing engagements found. Let's set up a new one.
What is the target or scope for this engagement?
Step 3A: Resume Existing Engagement
- Read planning documents:
read_file("<engagement>/plan/roe.json") read_file("<engagement>/plan/conops.json") read_file("<engagement>/plan/deconfliction.json") read_file("<engagement>/plan/opplan.json") read relevant files under "<engagement>/findings/" - Summarize progress to the operator:
- Objectives completed / total
- Current phase (recon / exploit / post-exploit)
- Last completed objective and key findings
- Next pending objective
- Ask: "Continue from where we left off?"
- Begin the Ralph execution loop
Step 3B: New Engagement (docs already created by Soundwave)
Soundwave has already interviewed the operator and created the engagement documents (RoE, CONOPS, Deconfliction Plan) before the orchestrator was activated. The workspace and planning documents already exist.
- Verify documents exist:
If any are missing, delegate tobash(command="ls plan/roe.json plan/conops.json plan/deconfliction.json")soundwaveto regenerate:task("soundwave", "Engagement workspace: /workspace/. Regenerate missing planning documents.") - Check C2 Infrastructure:
bash(command="nc -z c2-sliver 31337 2>/dev/null && echo 'C2_REACHABLE' || echo 'C2_UNREACHABLE'")- If
C2_REACHABLE→ C2 framework is Sliver (server:c2-sliver, gRPC port 31337). Include this in ALL sub-agent delegations. - If
C2_UNREACHABLE→ C2 server is not available, skip C2-dependent objectives - IMPORTANT: The C2 framework is always Sliver regardless of the engagement name. Do NOT assume Metasploit from engagement names containing "msf".
- If
- Begin the Ralph execution loop (Phase 1: read CONOPS → build OPPLAN)
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.
- 11d ago First seen · 87 lines · 23 tokens per session scan A 410d4f81babc
engagement-startup is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 687 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 2026-08-30.
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.