20-phi-redaction-first

20-phi-redaction-first is a cursor rule for Cursor from vaquarkhan/compliance-agent-skills. It costs 285 tokens per session, scanned A, original, MIT.

A rule set that directs compliance-related tasks to guidance for standards and laws such as HIPAA, GDPR, PCI-DSS, and SOC 2. It uses clues in the user's request to choose the relevant area.

In plain words
What is it for?
It helps select guidance for healthcare data, payment-card security, privacy requests, audit controls, government systems, education records, and other listed frameworks.
Why use it?
Compliance work covers different requirements depending on the data, industry, and jurisdiction. Routing reduces the chance of applying the wrong review process.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It helps select guidance for healthcare data, payment-card security, privacy requests, audit controls, government systems, education records, and other listed frameworks.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/vaquarkhan/compliance-agent-skills/20-phi-redaction-first
Install

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.

Clone the repo
git clone --depth 1 https://github.com/vaquarkhan/compliance-agent-skills

Made for: Cursor.

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 20-phi-redaction-first

README.md
[![agentmods](https://agentmods.dev/badge/rules/vaquarkhan/compliance-agent-skills/20-phi-redaction-first/github.svg)](https://agentmods.dev/rules/vaquarkhan/compliance-agent-skills/20-phi-redaction-first)
Your own site
<a href="https://agentmods.dev/rules/vaquarkhan/compliance-agent-skills/20-phi-redaction-first"><img src="https://agentmods.dev/badge/rules/vaquarkhan/compliance-agent-skills/20-phi-redaction-first/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 20-phi-redaction-first

Your own site · 80×15
<a href="https://agentmods.dev/rules/vaquarkhan/compliance-agent-skills/20-phi-redaction-first"><img src="https://agentmods.dev/badge/rules/vaquarkhan/compliance-agent-skills/20-phi-redaction-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 285 This file is loaded in full into every session.
When invoked 285 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00285 $0.00285
Opus 5 $0.00143 $0.00143
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured 9d ago against content hash f761067e68f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

20-phi-redaction-first 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 9d 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.

.cursor/rules/20-phi-redaction-first.mdc · 39 lines

What it actually says

PHI Redaction First

Upstream gate

redaction.py + Presidio analyze all user prompts before agent.py sends text to the model.

Token handling

  • Masked tokens like <PERSON_1> are intentional — do not guess original values.
  • Deanonymization is restricted to authorized downstream delivery via deanonymize_response tool.
  • Between engagements, assume a fresh redaction session (reset_session()).

Entity coverage

Default types include PERSON, US_SSN, PHONE_NUMBER, EMAIL_ADDRESS, MEDICAL_LICENSE, DATE_TIME, CREDIT_CARD, and others — see DEFAULT_ENTITY_TYPES in redaction.py.

Hooks

COMPLIANCE_PHI_REDACTION=required — session hooks block work if Presidio unavailable.

Skill

For pipeline tuning: hipaa-phi-redaction-pipeline
Reference: references/phi-redaction-patterns.md

PCI note

Credit card entity detection helps prevent accidental PAN in prompts — never process PAN in LLM workflows regardless of redaction.

Minimum necessary

Scope LLM access to redacted, minimum-necessary text. Prefer structured queries over full clinical notes.

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. 9d ago First seen · 39 lines · 285 tokens per session scan A f761067e68f3

Subscribe to this mod's changes

20-phi-redaction-first is a cursor rule published in the GitHub repository vaquarkhan/compliance-agent-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 285 tokens to every session, about $0.0014 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 2026-08-31.