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 data-handling-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/data-handling-template)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/data-handling-template"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/data-handling-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/data-handling-template"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/data-handling-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 | $0.00037 | $0.00832 |
| Opus 5 | $0.00018 | $0.00416 |
| Sonnet 5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
data-handling-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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Handling Plan Generator
The data handling plan defines what evidence the agent collects, where it lives, how long it's kept, and who can read it. Replaces the deprecated free-form RoE.data_handling string with structured per-class fields.
When to Use
- After RoE is written (RoE constraints + scope drive which data classes appear)
- User says "create data handling", "retention policy", "evidence storage", "PII handling", "compliance"
Workflow
Step 1: Start From the Schema Defaults
The DataHandlingPlan schema seeds four default classes — credentials, pii, source-code, business-data — with conservative retention. Keep these by default; override only when the engagement requires stricter or looser rules.
Step 2: Add Engagement-Specific Classes
Based on the interview:
| Engagement type | Likely additional classes |
|---|---|
| Healthcare client | health-records (classification: secret, retention: 7 days, framework: HIPAA) |
| Financial client | cardholder-data (classification: secret, retention: 0 days — never store, framework: PCI-DSS) |
| EU client / data subjects | Mark existing pii with framework: GDPR; consider personal-data-eu for stricter handling |
| Defense / classified | controlled-unclassified (classification: secret, retention: 0 days off-network) |
Step 3: Set Evidence Storage Path
Default "/workspace/<engagement>/evidence/" works for sandbox-isolated engagements. Override only when:
- Engagement requires an external-bucket destination (S3 / Azure Blob with client KMS)
- Multiple engagement workspaces share an evidence repository
Step 4: Compliance Frameworks
Set compliance_frameworks from the interview. Common entries: GDPR, HIPAA, PCI-DSS, SOC2, NIST 800-53, FedRAMP, ISO 27001.
The orchestrator (Atlas) reads this list and refuses to start objectives that violate the matching framework's evidence-handling rules.
Step 5: Purge Hard Cap
purge_after_days is the GLOBAL upper bound — every artifact older than this is deleted regardless of per-class retention. Default 90 days; reduce for engagements with tighter regulatory exposure.
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 · 73 lines · 37 tokens per session scan A 577a4c92d0f6
data-handling-template is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 832 once invoked, about $0.0002 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.