Browse the directory

Expert capability pack for drafting accurate safetyNotes and privacyNotes on HeyClaude hooks, MCP servers, skills, commands, and statuslines using CONTRIBUTING.md disclosure requirements and submission examples.

Source-backed rules for AI workflow directories that need consistent privacy metadata before accepting entries that touch prompts, files, local tools, hosted services, telemetry, generated artifacts, or personal data.

A source-backed collection for private research workflows: local-first planning, reproducible notebooks, local analytical processing, redaction, human review datasets, trace review, and secret scanning before outputs are shared.

Expert capability pack for Agent SDK OpenTelemetry export using CLAUDE_CODE_ENABLE_TELEMETRY, OTLP exporters, and monitoring-usage reference variables documented for Claude Code CLI subprocesses.

Expert incident timeline reconstruction capability pack for correlating deploy events, logs, traces, alerts, and chat transcripts into a source-backed, privacy-safe post-incident timeline with validation checkpoints.

Expert maintainer pull request triage capability pack for classifying open PRs, applying labels, routing reviewers, checking merge readiness, and producing privacy-safe queue summaries using GitHub pull request documentation workflows.

Browser-control MCP server and CLI that lets AI agents use a real Chrome session, including logged-in browser state, site adapters, DOM snapshots, authenticated fetches, network traces, screenshots, and page actions.

PreToolUse hook that reviews proposed writes to MCP configuration files and blocks inline credential values, credential-bearing URLs, and broad filesystem roots before they are saved.

Add PostHog to a Next.js app with client and server event capture, user identification, feature flags, session replay privacy controls, reverse-proxy planning, and production analytics validation.

Source-backed rules for reviewing feature flag changes across their full lifecycle, covering flag creation, naming, default values, kill switches, targeting, rollout safety, cleanup of stale flags, and privacy-safe configuration evidence.

Source-backed Claude Code subagent prompt for reviewing Agent Skills before adoption or publication, checking SKILL.md scope, descriptions, invocation control, supporting files, tool permissions, helpfulness, safety, and privacy risks against official Claude Code skills guidance.

Source-backed agent for reviewing AI workflow submissions before publication with data-flow mapping, privacy metadata, governance evidence, MCP/tool authority checks, retention disclosure, and compliance escalation gates.

Source-backed rules for AI coding assistants that must avoid exposing, copying, logging, committing, or normalizing secrets while editing code, configs, tests, prompts, documentation, and CI workflows.

Source-backed rules for reviewing AI-generated frontend UI changes for accessibility before merge, with semantic HTML, keyboard paths, focus management, labels, automated scan limits, manual checks, and privacy-safe evidence.

Source-backed rules for contributor pull requests that need clear commit messages, release-note-ready changelog entries, issue links, breaking-change markers, and privacy-safe history.

Source-backed rules for deciding when an AI-assisted code review must escalate high-risk changes to security, infrastructure, data, release, or domain owners before merge.

Source-backed rules for safely connecting MCP servers that expose local tools, resources, prompts, roots, transports, credentials, files, and logs to AI clients during active development sessions.

Source-backed rules for reviewing production database migrations before merge with lock-risk checks, expand-contract rollout, backfill controls, rollback limits, and privacy-safe migration evidence.

Open-source, self-hostable AI engine that runs LLMs, vision, voice, image, and video models on your own hardware behind one API, with drop-in OpenAI, Anthropic, and ElevenLabs API compatibility, composable on-demand backends, and no GPU required.

PreToolUse Write and Edit guardrail combining the hooks guide protected-file pattern with a local scan for common hardcoded credential shapes called out by GitHub secret scanning guidance before content is written.

Community reusable agent prompt for mapping Claude Code deployments to zero data retention requirements using official ZDR docs: logging boundaries, MCP data flows, session storage, and compliance evidence checklists for security review.

Source-backed rules for reviewing application logging changes, covering structured machine-readable events, consistent levels, correlation and trace context, actionable messages, log volume and cost, and keeping secrets and personal data out of logs.

A practical guide for handling secrets when connecting MCP servers and authoring Agent SDK tools in Claude Code: env expansion in .mcp.json, OAuth scope pins, keychain storage, local scope, and redaction before tool arguments reach the model.

Enterprise guide to zero data retention planning for Claude Code: contractual ZDR scope, logging boundaries, MCP data paths, and verification checkpoints.

A practical pre-installation review workflow for Model Context Protocol servers. Inventory tools, resources, prompts, credentials, network reach, storage, and runtime permissions before connecting a server to Claude or another MCP client.

Run the parts of your AI dev workflow that touch your code and data — tools, memory, and auxiliary models — on infrastructure you control, while still using Claude as the orchestrator. A practical architecture for a self-hosted, privacy-first developer stack.

The Claude Code data-handling controls that matter for teams working near PHI: no-training commercial policy, retention windows, Zero Data Retention, encryption, local transcript handling, telemetry opt-outs, and security model.

Scans for potential sensitive data exposure and alerts immediately.

Community reusable agent prompt for analyzing OpenTelemetry traces from agent hosts using official trace signal documentation: span hierarchy review, latency attribution, error propagation, and privacy-safe instrumentation recommendations.

Expert Claude Agent SDK custom tool authoring capability pack for designing typed in-process tools with createSdkMcpServer, allowedTools scoping, isError handling, and privacy-safe rollout checklists aligned to official custom-tools documentation.