Local pseudonymization for Claude Code & Cowork: Claude reads Word/Excel/PowerPoint/PDF/CSV/e-mail files only as consistent pseudonyms, prompts with personal data are stopped before they leave, and real names are restored locally into the finished document.
Plugin ainonymize from marketplace ainonymize in Leineder/ainonymize-claude. Commands read from the repo's manifest — 19 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
anonymizeWork with documents that contain personal or client data (contracts, HR files, patient letters, invoices, bank exports, CRM/CSV exports, e-mails) without that data leaving the computer. Use whenever the user asks to read, summarize, review, translate, compare, analyze or edit a local Word, Excel, Po
restorePut the real names and values back into a document or text that contains Ainonymize pseudonyms, locally, so the user gets the final version with real personal data without it ever entering the conversation. Use when the user wants the "real", "final", "original names" or "de-anonymized" version of s
/ainonymize:setupDownload and verify Ainonymize's local detection model now (one time, ~600 MB), so the first document does not have to wait
/ainonymize:statusShow Ainonymize's status — local model, guards, current scope and stored mappings (counts only)
ainonymizeruns: node ${CLAUDE_PLUGIN_ROOT}/server/cli.mjs mcp
node "${CLAUDE_PLUGIN_ROOT}/server/cli.mjs" hook session
node "${CLAUDE_PLUGIN_ROOT}/server/cli.mjs" hook prompt
node "${CLAUDE_PLUGIN_ROOT}/server/cli.mjs" hook read
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails
3 skills · 1 command · 1 agent
Install the "AAS Security Engineer" editorial skill bundle for Claude Code.
12 skills
Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture
24 skills · 2 agents
SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening
5 skills · 3 commands · 2 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.