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 j4flmao/agent-skills --skill data-clean-roomgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/data-clean-room)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/data-clean-room"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/data-clean-room/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/j4flmao/agent-skills/data-clean-room"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/data-clean-room.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 159 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00116 | $0.04395 |
| Opus 5 | $0.00058 | $0.02197 |
| Sonnet 5 | $0.00023 | $0.00879 |
| Haiku 4.5 | $0.00012 | $0.00439 |
Grade A, and why
data-clean-room 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 — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Clean Room
Purpose
Enable privacy-preserving data collaboration between multiple parties using clean room architectures, private set intersection, differential privacy, and controlled query environments.
Agent Protocol
Trigger
Exact user phrases: "data clean room", "AWS Clean Rooms", "Snowflake Clean Room", "PSI", "Private Set Intersection", "privacy-preserving join", "data collaboration", "secure MPC", "multi-party computation", "differential privacy", "privacy-enhancing technologies", "PET", "clean room query", "privacy budget".
Input Context
Before activating, verify:
- Clean room platform (AWS Clean Rooms, Snowflake Clean Room, custom PSI, Google Ads Data Hub, Habu, InfoSum)
- Participating parties and data roles (contributor, querier, collaborator)
- Data types (PII, behavioral, transactional, demographic)
- Join keys (email, hashed email, device ID, customer ID)
- Query patterns (aggregation, JOIN, differential privacy)
- Compliance requirements (CCPA, GDPR, HIPAA, financial regulations)
Output Artifact
Clean room architecture with table schema, join key configuration, query constraints, privacy controls, and collaboration agreement as SQL, YAML, and JSON.
Response Format
-- Clean room table schema with privacy configuration
-- Clean room configuration
-- Query constraints and policies
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output.
Completion Criteria
- Join key strategy defined (hashed, salted, or PSI-based)
- Column-level access policies configured per party
- Query constraints with row count and aggregation limits
- Differential privacy budget (epsilon) configured
- Output validation rules documented
- Audit logging and compliance controls defined
Max Response Length
4096
Workflow
Clean Room Architecture
A clean room is a controlled environment where multiple parties contribute data for collaborative analysis without exposing raw data to each other.
What ships with it
8 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.
- references/clean-room-architecture.md 7.9 KB
- references/clean-room-data-types.md 4.8 KB
- references/clean-room-deployment.md 926 B
- references/clean-room-ops.md 9.9 KB
- references/clean-room-performance.md 3.9 KB
- references/clean-room-use-cases.md 933 B
- references/privacy-compute-patterns.md 10 KB
- references/privacy-compute.md 10 KB
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 · 515 lines · 116 tokens per session scan A 543b1707c210
data-clean-room is a skill published in the GitHub repository j4flmao/agent-skills (22 stars, last pushed 3d ago), licensed MIT. It adds 116 tokens to every session and 4,395 once invoked, about $0.0006 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
Australian Privacy Act
Privacy Act 1988 compliance, APPs, data breach notification, and privacy policy requirements.
implementing-gdpr-data-protection-controls
The General Data Protection Regulation (EU) 2016/679 (GDPR) is the EU's comprehensive data protection law governing the collection, processing, storage, and transfer of personal data. This skill cover.
data_analyst
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.
gdpr-privacy
Use when producing the GDPR artifacts a product publishes or hands over: a privacy policy true to what it processes, a cookie/consent banner, a lawful basis per purpose, an Art. 28 DPA, an SCC transfer mechanism, or a DSAR flow. Drafts for counsel review. NOT internal retention rules (that is data-policy), NOT…
data-policy
Use when building internal data-governance machinery: a retention schedule (period, lawful basis, expiry action, system where deletion runs), an Art. 6 lawful-basis register, an Art. 30 ROPA, or a consent capture/withdrawal model. NOT the public privacy notice or DSAR handling (that is gdpr-privacy), NOT SOC 2 posture…
gdpr-expert
Expert in GDPR compliance, data protection, privacy by design, consent management, DPO responsibilities, and EU data regulations. Use when the user mentions privacy, data protection, compliance, consent, a DPO, or eu regulation, or when the task involves GDPR Fundamentals, Key Principles, Data Subject Rights, or…