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 catpilotai/catpilot-ai-guardrails --skill pii-and-test-datagit clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrailsWrote 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/catpilotai/catpilot-ai-guardrails/pii-and-test-data)<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/pii-and-test-data"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/pii-and-test-data/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/catpilotai/catpilot-ai-guardrails/pii-and-test-data"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/pii-and-test-data.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 | $0.00097 | $0.04678 |
| Opus 5.5 | $0.00039 | $0.01871 |
| Sonnet 5.5 | $0.00019 | $0.00936 |
| Haiku 4.5 | $0.00010 | $0.00468 |
Grade A, and why
pii-and-test-data 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 1mo 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 — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baseline
Applies when: Writing test fixtures, seed data, illustrative doc/comment records, error messages, logs, telemetry, screenshots or recordings shared outside the org, migrations/ETL between environments, or LLM prompts, fine-tuning sets, and RAG corpora.
Always:
- Use reserved test ranges for identifiers that have one (
*@example.com, the555-01xxphone block, RFC 5737 IPs, provider test card numbers, SSA-reserved SSN ranges) instead of a real-looking value. - Generate names, addresses, and other free-form identifiers with a seeded synthetic generator (
faker,@faker-js/faker, etc.), not free-form invention. - Refuse to copy production rows into development, staging, demo, or test environments, including "just one row" or hash-based "anonymization."
- Keep emails, phone numbers, full names, addresses, government IDs, DOB, and payment/bank numbers out of logs, errors, and telemetry; identify by internal ID instead.
- Use synthetic test accounts for anything leaving the organization (demos, screenshots, recordings, shared transcripts).
- Screen data going into an LLM prompt, fine-tuning set, or RAG corpus with a PII/PHI/PCI scrubber before ingestion.
Never:
- A real, or real-looking, email, phone number, SSN, or card number in a fixture, comment, or doc example.
- Copying production rows into a lower environment, including a single row "to reproduce a bug."
- Hashing names or emails and calling it anonymization.
- Logging or erroring with a user's email, phone, full name, address, government ID, or payment/bank number.
- Recording or screenshotting the production app against a real customer account.
Open the full component before acting: it has the examples, the remediation steps, and the detection patterns.
Why
Production data carries legal, contractual, and operational obligations that test environments are not designed to honor. Every time a real customer record appears in a fixture file, a comment, a screenshot, a chat transcript, or a debug log, the organization picks up the same obligations for that copy as for the original — without the controls that protect the original.
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.
- 1mo ago Changed · +21 lines 0050f014d7f9
- 2mo ago First seen · 472 lines · 97 tokens per session scan A fb0e8397b62a
pii-and-test-data is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed 8d ago), licensed MIT. It adds 97 tokens to every session and 4,678 once invoked, about $0.0004 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 2026-08-31.
pii-and-test-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pii-and-test-datacatpilotai/catpilot-ai-guardrails | Skill | 2 | 8d ago | MIT | A | 97 | Claude Code |
| dcf-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| baoyu-article-illustratorNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 18 | Claude Code, Codex |
| flash-attentionNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| subagent-driven-developmentNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 17 | Claude Code, Codex |
| mcporterNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 16 | Claude Code, Codex |
| mem0-vercel-ai-sdkmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 146 | Claude Code, Codex |