A practical guide to instrumenting LLM and agent applications with traces, metrics, logs, GenAI semantic attributes, sampling, and privacy-aware redaction so teams can debug model calls, tool use, retries, and cost.
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 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 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.
Connect Claude to Algolia-managed MCP servers for curated public search and recommendation access or internal, user-scoped search and analytics workflows.
A source-backed collection for reviewing API contracts before release: OpenAPI drift detection, JSON Schema validation, GraphQL schema checks, Spectral lint review, Pact consumer contract verification, and generated clients or stubs from approved specs.
Source-backed agent for reviewing Atlas database schema migrations with migration lint, analyzers, drift detection, CI/CD evidence, dev-database simulation, rollout risk, rollback planning, and production safety gates.
Connect Claude to Auth0's official local MCP server for tenant administration, application setup, Actions, logs, forms, and scoped Management API workflows.
Source-backed agent for reviewing typed Protobuf and gRPC API contract changes with Buf breaking-change evidence, lint results, buf.yaml policy, BSR schema checks, generated-code impact, consumer compatibility, and rollout decisions.
A practical architecture guide for building AI agents on Cloudflare Workers with Workers AI inference and durable per-agent state. Use the Agents API, Durable Objects, bindings, and Workers observability to keep agent sessions reliable across requests.
A source-backed guide for designing Model Context Protocol servers with explicit authorization boundaries, narrow tools, scoped resources, privacy-aware logging, and least-privilege runtime access.
Source-backed agent for managing Changesets release cutovers, version PRs, changelog evidence, package bump decisions, pre-release mode, publish gates, and npm registry safety.
A practical decision guide for choosing between Claude Code subagents, skills, slash commands, hooks, settings, and MCP servers. Pick the smallest extension surface that matches the workflow, risk, and sharing model.
Claude Code statusline that reads Anthropic Claude Code Analytics Admin API data and shows daily estimated cost, hourly pace, sessions, and budget pressure.
A source-backed Cloudflare collection for building AI apps on the edge: combine Workers, Workers AI, Agents, D1, KV, R2, Wrangler deployment operations, and Cloudflare MCP access with explicit environment and data boundaries.
Source-backed agent for turning Codecov patch coverage, project coverage, flags, components, carryforward behavior, PR comments, and changed-file context into targeted regression test plans.
Source-backed rules for requiring coding agents to provide fresh, scoped, and reviewer-visible test evidence before a pull request can be approved or merged.
Source-backed rules for AI workflow directories that need to classify commercial, sponsored, affiliate, vendor-authored, and thin promotional submissions before they enter the ordinary editorial content queue.
Source-backed rules for preparing direct content-only pull requests with one raw MDX file, reachable provenance URLs, issue closure, duplicate history, validation evidence, and no generated artifact churn.
Claude Code statusline that estimates context pressure from local session token counts and a configurable context limit, then prints a compact risk tier.
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 reviewing dependency update pull requests with supply-chain context, lockfile discipline, advisory checks, compatibility evidence, and privacy-safe metadata handling.
Source-backed agent for triaging dependency update pull requests with SemVer risk, Dependabot context, GitHub dependency review, OSV advisories, OpenSSF Scorecard signals, lockfile changes, test evidence, and privacy-safe notes.
Source-backed rules for public AI workflow registries that need to keep directory entries, source links, version claims, examples, install guidance, compatibility notes, and last-reviewed metadata fresh enough to trust.
A practical guide for comparing AI coding tools with repeatable benchmarks, fixed task sets, controlled environments, transparent scoring, and privacy-safe artifacts.
A source-backed frontend QA collection for AI-assisted UI work: combine WCAG accessibility checks, Playwright browser automation, Storybook component context, Chrome DevTools inspection, BrowserStack coverage, and test hooks before shipping user interfaces.
Source-backed rules for registry repositories that must keep contributor PRs focused on source files while generated indexes, feeds, downloads, search data, README output, and previews are rebuilt by trusted automation.
Claude Code statusline that counts GitHub Flavored Markdown task list items from a linked issue body or local issue-body file.
Claude Code statusline that uses git-machete branch layout data to show whether the current branch is managed, how many branches are outside the layout, and when fork-point overrides need review.
Claude Code statusline that surfaces sensitive environment-file risk and can optionally run git-secrets as a local pre-commit-style scanner.
Claude Code statusline that reads GitHub REST check runs for the active pull request head commit and summarizes failed, pending, and passing checks.
Source-backed agent for cleaning up open-source GitHub issue queues with reproducibility checks, labels, issue types, milestones, assignees, project views, duplicate links, and maintainer-safe response drafts.
Claude Code statusline that uses GitHub CLI to show repository health basics: archive state, open PR count, open issue count, and default branch.
Claude Code statusline that uses GitHub pull request search qualifiers to show review-requested queue counts for maintainers.
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 agent for designing Inspect AI benchmark tasks, datasets, solver plans, scorer rubrics, model matrices, eval logs, and release-quality prompt evaluation decisions.
Claude Code statusline that reads Istanbul JSON summary output and compares current line coverage with a local baseline percentage.
Source-backed agent for reviewing local-first Jupyter notebook workflows that use Jupytext text notebooks, paired notebooks, command-line sync, and version-control friendly reproducibility checks.
Claude Code statusline that shows the active kubectl context and namespace with a deployment-environment risk label.
Source-backed agent for live production incident debugging with impact framing, timeline reconstruction, alert/log/trace evidence, rollback options, escalation boundaries, and privacy-safe incident notes.
A practical guide for keeping Claude Code sessions focused during long coding work with scoped prompts, checkpoints, durable memory boundaries, source refreshes, and privacy-safe handoffs.
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.
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.
A practical migration guide for moving Cursor-style rules, prompts, MCP configuration, and team workflows into Claude Code memory, slash commands, MCP, settings, and reviewable project conventions.
Claude Code statusline that prints the current model label, provider label, and optional routing hint from local statusline input.
A source-backed collection for reproducible data analysis and notebook work: Marimo notebooks, DuckDB analytical SQL, Polars DataFrames, Hugging Face Datasets loading, Great Expectations quality checks, and Streamlit sharing.
Claude Code statusline that checks package publish readiness from package.json, optional npm login visibility, package privacy, and dirty package metadata files.
Connect Claude to Okta's official self-hosted MCP server for scoped identity administration, users, groups, applications, policies, logs, brands, and tenant management workflows.
A source-backed collection for building repeatable LLM eval and prompt testing workflows with open-source tools: prompt regression tests, RAG and agent metrics, human review datasets, traces, prompt optimization, and release gates.
Source-backed agent for security review of open-source pull requests, including untrusted fork boundaries, GitHub Actions permissions, secret and code scanning, dependency review, provenance signals, and maintainer-owned merge recommendations.
Claude Code statusline that reads OSV-Scanner JSON results and prints a compact dependency vulnerability count for review sessions.
PreToolUse hook that reviews proposed Bash commands for package, installer, and archive downloads, then blocks curl or wget download commands that do not include an adjacent checksum or signature verification step.
Connect Claude to PlanetScale's official hosted MCP server for organizations, databases, branches, schemas, Insights, documentation search, and scoped SQL query workflows.
Connect Claude to PostHog's official MCP server for product analytics, feature flags, experiments, dashboards, error tracking, logs, surveys, data warehouse, and project operations.
Claude Code statusline that checks the active pull request body for GitHub closing keywords and shows whether issue auto-closure linkage is present.
Read-only Claude Code Stop hook that checks the current GitHub pull request title against a Conventional Commits style pattern before the session ends, then falls back to the latest commit subject when no PR title is available.
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.
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.
PreToolUse hook that scans proposed writes to prompt, agent, rule, markdown, and context files for common prompt-injection phrases before the content is saved into an AI-readable surface.
Connect Claude to Pulumi's MCP server for Pulumi Cloud stacks, resource search, Registry context, policy findings, organization access, and Pulumi Neo infrastructure workflows.
A source-backed collection for keyboard-first Claude power users on macOS: Raycast launcher access, HeyClaude API/MCP/Raycast surface selection, MCP setup, skill installation, reusable slash commands, and Raycast extension development or publishing.
Source-backed agent for reviewing rendered frontend changes with screenshots, visual comparison evidence, viewport layout checks, keyboard/focus paths, accessibility scans, CLS risk, and privacy-safe QA artifacts.
A source-backed review workflow for pull requests that include AI-generated code. Treat generated diffs as untrusted implementation work, verify behavior in CI, inspect security-sensitive paths first, and merge only after a reviewer-owned checklist passes.
A source-backed Model Context Protocol starter collection for SaaS builders: connect product code, database state, payments, deployment telemetry, issue tracking, and production errors while keeping MCP authorization and tool boundaries explicit.
Source-backed rules for AI coding agents that propose, compose, review, or run shell commands during coding sessions where quoting, expansion, command injection, file writes, network calls, and destructive operations can cause harm.
A source-backed collection for operators running AI services on infrastructure they control: local model runtime, CPU and GPU inference, model gateway, self-hosted MCP access, retrieval storage, model API packaging, container rebuilds, and image security checks.
A source-backed safety checklist for introducing Claude Code hooks with scoped events, minimal authority, reviewable commands, clear ownership, and a rollback path.
Claude Code statusline that uses simple-git status data to show dirty worktree risk, staged changes, untracked files, and merge conflicts.
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.
Connect Claude to Twilio's hosted MCP server for read-only search and retrieval across public Twilio API specifications, Twilio Docs, SendGrid Docs, Segment Docs, and support articles.
Source-backed rules for reviewing TypeScript API client compatibility before merge, with exported type-surface diffs, inferred router inputs and outputs, runtime validator alignment, downstream compile checks, and privacy-safe evidence.
A source-backed guide for choosing between HeyClaude API endpoints, the HeyClaude MCP server, and the Raycast extension surface when building registry discovery, install-guidance, and PR-first submission workflows.
A practical guide to using Claude Code subagents as focused review and triage specialists for pull requests, issues, risks, tests, documentation, and follow-up planning.
Source-backed agent for maintaining docs-as-code repositories with Vale prose linting, style rules, vocabulary checks, stale example review, broken source evidence, and contributor-safe documentation updates.
A practical guide for preparing source-backed HeyClaude content pull requests that stay focused, cite verifiable sources, avoid generated artifacts, and pass content validation.
No reviewed entries yet.