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 alivirgo/Major-AI-Skills --skill ai-pii-redaction-reviewgit clone --depth 1 https://github.com/alivirgo/Major-AI-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/alivirgo/major-ai-skills/ai-pii-redaction-review)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/ai-pii-redaction-review"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ai-pii-redaction-review/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/alivirgo/major-ai-skills/ai-pii-redaction-review"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ai-pii-redaction-review.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 | $0.00053 | $0.01333 |
| Opus 5.5 | $0.00021 | $0.00533 |
| Sonnet 5.5 | $0.00011 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
ai-pii-redaction-review 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 21d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI PII Redaction Review AI Skill Guide (Claude)
Overview & Engine Architecture
Redaction is a perimeter control: sensitive data should not reach the provider, the trace store, or the ticket dump in the clear. Regex alone is not anonymization. Pseudonymization with a retained key remains personal data for the controller under GDPR-style regimes—describe outputs as redacted/pseudonymized, never “guaranteed anonymous.”
Claude operates as a Principal Privacy Engineer for AI pipelines, specializing in destination/policy scoping, typed stable placeholders, reversal-map isolation, multi-surface leakage checks, and metadata-only audit logs.
┌─────────────────────────────────────────────────────────────┐
│ PII Redaction Review Stack │
│ Policy (allowed classes) → detect → minimize → placeholder │
│ → scan artifacts/meta/logs → restore only at auth boundary │
│ → report categories + residual risk (no raw secrets) │
└─────────────────────────────────────────────────────────────┘
When to use / when not to
Use when preparing prompts, RAG chunks, tool outputs, eval fixtures, or support packets for external LLMs or shared logs.
Do not use when unauthorized to view the sample; never ship originals to an external redaction SaaS without approval (prefer in-perimeter detection).
Operational Capabilities & Agent Directives
- Establish destination, permitted data classes, task need-to-know, retention, and legal basis/owner before editing.
- Inventory: direct identifiers, credentials/secrets, quasi-identifiers in combination, sensitive free text (health, finance, biometrics).
- Prefer local detectors (e.g. Presidio-class NER + regex) + human field review.
- Drop fields not required; use typed stable placeholders (
<<EMAIL_1>>) when relationships matter; keep reversal maps out of outgoing payloads and usually out of disk logs. - Scan attachments, filenames, EXIF, headers, stack traces, and error messages—not only the main prompt.
- Do not put removed values in the deliverable report.
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.
- 21d ago Changed · +100 lines · +24 tokens per session cffb2d18a6f3
- 1mo ago First seen · 35 lines · 29 tokens per session scan A 93bdc55862b4
ai-pii-redaction-review is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,333 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
privacy-compliance
Comprehensive global privacy compliance agent skill covering GDPR, CCPA/CPRA, HIPAA Privacy Rule, EU AI Act, LGPD, cross-border data transfer mechanisms (SCCs, BCRs, EU-US DPF), PII identification and classification, data minimization, consent management, privacy-by-design patterns, DPIA workflows, data subject access…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
agents-md
Create, revise, or audit AGENTS.md files from repository evidence, verified commands, and correctly scoped instructions without overwriting maintainer intent.
api-endpoint-builder
Builds reviewable REST API endpoint scaffolds with validation, error handling, authentication, and documentation. Follows best practices for security and scalability.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
ask-copilot
Use GitHub Copilot CLI in non-interactive mode to ask questions, review code, or generate snippets without manual interaction.