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 roe-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/roe-template)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/roe-template"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/roe-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/roe-template"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/roe-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 | $0.00651 |
| Opus 5 | $0.00013 | $0.00326 |
| Sonnet 5 | $0.00005 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
roe-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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules of Engagement (RoE) Generator
The RoE is the legally binding foundation of every red team engagement. All other documents build on it.
When to Use
- Starting a new engagement
- User says "create RoE", "define scope", "set boundaries"
- Before any other planning document can be created
Workflow
Step 1: Interview the User
Drive each dimension through one ask_user_question call (per CRITICAL_RULES #8 — every operator-facing question goes through the tool). Cover these roughly in order, never bundling multiple questions in one turn:
Identity & Scope
- Engagement name (free-form,
allow_other=truewith sensible guesses) - Client organization (free-form,
allow_other=true) - Engagement type — single-select:
external/internal/hybrid/assumed-breach/physical - Start date / end date / testing window with timezone (free-form,
allow_other=true— suggest defaults like "Mon-Fri 09:00-18:00 client TZ") - In-scope targets (free-form,
allow_other=true— domains, IP ranges, cloud resources, applications) - Out-of-scope targets (free-form,
allow_other=true)
Boundaries & Escalation
7. Additional prohibited actions beyond schema defaults (multi-select with sensible options + allow_other=true)
8. Special permitted actions — phishing, password spraying, raw-socket scans (multi-select)
9. Escalation contacts — minimum 2 (client + red team lead). One ask per contact slot covering name, role, channel
10. Authorization reference / contract # (free-form, allow_other=true)
Step 2: Generate roe.json
Use the RoE schema from atlas.core.schemas. Write to the engagement directory.
See references/roe-example.json for a complete example and ../references/schema-quick-reference.md for all required fields and valid values.
Step 3: Validate
Run through the checklist in references/validation-checklist.md before presenting to user.
Generation Rules
- Always include default prohibited actions — DoS, unauthorized social engineering, unauthorized physical access, real data exfiltration, production data modification
- Scope must be specific — CIDR notation for IPs, wildcard notation for domains
- Testing window must include timezone
- At least 2 escalation contacts required
- Authorization reference must not be empty
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 63 lines · 26 tokens per session scan A 9ed1c4c8bf33
roe-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 651 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
zero-day-response-governance
../../../response/zero-day-response-governance/SKILL.md.
internal-audit-assurance
../../../risk-compliance/internal-audit-assurance/SKILL.md.
ai-ethics-governance
../../../platform-ai/ai-ethics-governance/SKILL.md.
third-party-vendor-risk
../../../platform-ai/third-party-vendor-risk/SKILL.md.
compliance-mapping
../../../risk-compliance/compliance-mapping/SKILL.md.
privacy-dpia
../../../risk-compliance/privacy-dpia/SKILL.md.