don-cheli-sdd: Skill for Claude Code

.agent/skills/doncheli-data-policy/SKILL.md

doncheli-data-policy is a skill for Claude Code from doncheli/don-cheli-sdd. It costs 54 tokens per session (467 once invoked), scanned A, original, Apache-2.0.

A project audit that records what personal or sensitive information an application collects, uses, stores, logs, or sends to other services. It checks the findings against common privacy and security requirements such as GDPR, CCPA, and SOC 2.

In plain words
What is it for?
Find personal-data fields in models, requests, logs, and integrations; build a data inventory; flag gaps; and draft a Privacy Notice section when requested.
Why use it?
It helps reveal sensitive data handling and missing policy details without claiming that a project is compliant when the evidence is incomplete.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

This is doncheli/don-cheli-sdd's own configuration. It tells Claude Code how to work on don-cheli-sdd itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything don-cheli-sdd configures →

Part of the don-cheli-sdd plugin — 28 skills, 115 commands, 1 agent shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to doncheli/don-cheli-sdd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/doncheli/don-cheli-sdd/main/.agent/skills/doncheli-data-policy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/doncheli/don-cheli-sdd

Made for: Claude Code.

Or install don-cheli-sdd, the plugin that ships this one along with the rest of its 28 skills, 115 commands, 1 agent.

Wrote 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.

agentmods badge for doncheli-data-policy

README.md
[![agentmods](https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-data-policy/github.svg)](https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-data-policy)
Your own site
<a href="https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-data-policy"><img src="https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-data-policy/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.

agentmods 80×15 button for doncheli-data-policy

Your own site · 80×15
<a href="https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-data-policy"><img src="https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-data-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

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 →

  • high Tool Misuse · line 43
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00467
Opus 5 $0.00027 $0.00234
Sonnet 5 $0.00011 $0.00093
Haiku 4.5 $0.00005 $0.00047

Measured 12d ago against content hash ad36ca008c10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

doncheli-data-policy 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 12d 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.

.agent/skills/doncheli-data-policy/SKILL.md · 46 lines

What it actually says

Don Cheli: Data Policy Auditor

Instructions

  1. Scan the codebase for PII and sensitive data patterns:
    • Database models / schemas for fields like email, phone, name, address, IP, location
    • API request/response payloads
    • Logging statements that may capture sensitive fields
    • Third-party integrations that receive user data
  2. Build a data inventory table: field name, model, purpose, retention, shared with
  3. Check against common compliance requirements:
    • GDPR: lawful basis, right to erasure, data minimization
    • CCPA: disclosure, opt-out
    • SOC2: access controls, encryption at rest/transit
  4. Flag violations as [critical | warning | info]
  5. Generate a draft Privacy Notice section if requested (--generate-notice)
  6. Save the audit to .dc/data-policy-audit-<date>.md
  7. Never make assumptions about compliance status — only report findings and flag gaps

Output Format

## Data Policy Audit — 2026-03-28

### Data Inventory
| Field     | Model      | Purpose       | Retention | Shared With     |
|-----------|-----------|---------------|-----------|----------------|
| email     | User       | Auth, comms   | Indefinite| SendGrid, Auth0|
| ip_address| AuditLog   | Security      | 90 days   | Internal only  |

### Compliance Gaps
🔴 CRITICAL: ip_address logged in plain text in audit_logs — encrypt or hash
🟡 WARNING:  No data retention policy enforced for User.email — GDPR Art. 5(e)
🟢 INFO:     No right-to-erasure endpoint found — required for GDPR compliance

### Recommendations
1. Add @Encrypted() decorator to ip_address field
2. Implement DELETE /users/:id endpoint that purges all PII
3. Document data retention in Privacy Policy
Changes

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.

  1. 12d ago First seen · 46 lines · 54 tokens per session scan A ad36ca008c10

Subscribe to this mod's changes

doncheli-data-policy is a skill published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 467 once invoked, about $0.0003 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.