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 gyanranjan/polyagent-skills --skill desensitizergit clone --depth 1 https://github.com/gyanranjan/polyagent-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/gyanranjan/polyagent-skills/desensitizer)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/desensitizer"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/desensitizer/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/gyanranjan/polyagent-skills/desensitizer"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/desensitizer.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 | $0.00071 | $0.00618 |
| Opus 5 | $0.00036 | $0.00309 |
| Sonnet 5 | $0.00014 | $0.00124 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
desensitizer 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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desensitizer
Purpose
Remove or mask sensitive information from any content while preserving its structure and usefulness for the intended purpose (sharing, demos, testing, compliance).
When to Use
- User needs to remove PII from documents or data
- User wants to create anonymized versions of real data
- User needs to prepare content for external sharing
- User asks to mask credentials, API keys, or secrets in configs/code
When NOT to Use
- User asks for legal/privacy policy interpretation without providing masking work
- User requests irreversible deletion from live systems (this skill handles content transformation)
Inputs
Required:
- Content to desensitize
Optional:
- What to mask (specific fields, all PII, secrets only)
- Replacement strategy (fake data, redaction, hashing, placeholders)
- Compliance context (GDPR, HIPAA, etc.)
Process
Step 1: Identify Sensitive Data
Scan for: names, emails, phone numbers, addresses, SSNs, credit cards, API keys, passwords, IP addresses, and domain-specific sensitive fields.
Step 2: Choose Masking Strategy
Based on context: replace with realistic fake data (for demos), redact with [REDACTED] (for compliance), or hash (for data analysis).
Step 3: Apply Masking
Replace all identified sensitive data consistently — same real name maps to same fake name throughout the document.
Step 4: Verify
Review the output to ensure no sensitive data leaked through and the document remains usable.
Output Format
Desensitized version of the input in the same format.
Quality Checks
- All obvious direct identifiers (names, emails, phone numbers, IDs) are handled
- Secret patterns (keys/tokens/passwords) are masked consistently
- Replacement strategy preserves structure needed for downstream use
- Same source entity maps to the same replacement value throughout
Common Skills Used
common-skills/quality-checklist.md— Verify completeness of desensitization
Edge Cases
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.
- 10d ago First seen · 76 lines · 71 tokens per session scan A 40b959c5d992
desensitizer is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 71 tokens to every session and 618 once invoked, about $0.0004 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.
Other skills, from other repositories
redacta
Pseudonymises medical and clinical documents by replacing patient identifiers with labelled tokens (e.g. [PATIENTNAME1], [NHSNUMBER1], [DATEOFBIRTH1]) so the text can be safely processed by AI or shared, with clinical meaning intact. Combines a deterministic pattern layer (NHS numbers with Modulus-11 validation, UK…
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…
implementing-cloud-dlp-for-data-protection
Implementing Cloud Data Loss Prevention (DLP) using Amazon Macie, Azure Information Protection, and Google Cloud DLP API to discover, classify, and protect sensitive data across cloud storage, databases, and data pipelines.
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
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-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…