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 contact-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/contact-template)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/contact-template"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/contact-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/contact-template"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/contact-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 | $0.00856 |
| Opus 5 | $0.00013 | $0.00428 |
| Sonnet 5 | $0.00005 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
contact-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 7d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contact / Communications Plan Generator
Slim version of the traditional white-cell/blue-cell/red-cell matrix tailored for autonomous-AI engagements. The agent itself is the "red cell"; only humans staff the white / blue cells. Full multi-cell rosters belong in an external comms doc, not here.
When to Use
- After RoE is written (escalation_contacts seed the primary operator)
- User says "create contact plan", "communications", "who do we notify", "escalation chain"
Workflow
Step 1: Identify Primary Operator
This is the single human responsible for the engagement on the operator side. Resolve from the RoE escalation_contacts:
- If exactly one contact has the role "engagement lead" or "primary operator" — use that
- Otherwise ask via
ask_user_questionwho the primary is
Fields: name, role, channel (resolvable — Signal, email, PagerDuty service-key, Slack channel), availability
Step 2: Build Escalation Chain
Ordered list of fallbacks. The agent walks this chain when the primary is unreachable past the abort plan's response window (default 15 minutes).
Typical chain:
- Primary operator
- Engagement owner (lead pentester / red team manager)
- Client SOC lead (only contacted on deconfliction events)
Step 3: Abort Signal Recipient
The contact paged on EMERGENCY-severity abort triggers. Usually = primary operator but can differ (e.g., engagements with a dedicated on-call rotation).
Optional — leave None only if the engagement explicitly opts out of EMERGENCY paging (rare).
Step 4: External SOC Endpoint (Optional)
If the client has an integration endpoint for deconfliction (HTTP webhook, Splunk HEC token, internal ticketing API), record the URL here. The agent POSTs before active scanning begins so the SOC can pre-allowlist red-team activity.
Empty = no external integration; deconfliction happens via the primary operator only.
Step 5: Blackout Windows
ISO 8601 datetime ranges during which the agent must not run active operations (passive recon — DNS, public WHOIS — is usually OK). Format: "<start>/<duration-or-end>", e.g.:
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.
- 7d ago First seen · 83 lines · 26 tokens per session scan A b2cb1b6d3e01
contact-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 856 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
usap-program-manager
Security program manager and passive lifecycle orchestrator (cs-security-program-manager). Use for security roadmap planning, program health scanning, debt tracking, facilitated reviews, or when the user says "security roadmap", "program planning", "security debt", "proactive scan", or "program review".
findings-tracker
../../../governance/findings-tracker/SKILL.md.
incident-commander
../../../response/incident-commander/SKILL.md.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
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.