AI for Developers
Claude Code, coding agents, skills, MCP, and the engineering guides, tools, and installables that make AI-assisted development actually ship.
Start here
Read these in order — each one assumes the last.
- 01GuideWhat Is Claude Code?A grounded explanation of Claude Code: an agentic command-line coding tool that reads files, runs commands, and works in a loop toward a goal.
- 02GuideInstalling Claude CodeHow to install Claude Code, authenticate, and start your first session in a real project — plus the minimal CLAUDE.md that makes it productive from day one.
- 03GuideCLAUDE.md Best PracticesHow to write a CLAUDE.md that actually helps — what to include, what to leave out, and how to keep it current.
- 04GuideWhat Are Claude Skills? The Complete GuideClaude Skills are folders with a SKILL.md that teach Claude repeatable procedures. How they work, where they run, and how to install or write one.
- 05GuideClaude Code Hooks: Automate Formatting, Tests, and GuardrailsHow Claude Code hooks work — the major hook events, the settings.json configuration shape, exit codes and JSON output, plus three hooks worth copying.
Guides123
Tutorials and deep-dives
Claude Free vs Pro vs Max vs Team (2026): Which Plan Unlocks What
Every Claude plan compared as of September 2026: prices, usage tiers, and which plan unlocks Claude Code, Cowork, Design, Excel, Chrome, projects, and models.
What Is Claude Cowork? The Complete Guide for Non-Developers
Claude Cowork explained for non-developers: what the desktop agent does with your files and apps, how it differs from chat and Claude Code, plans, and safety.
10 Best Claude Skills for API Development
Choose Claude skills for error contracts, idempotency, pagination, limits, webhooks, CORS, GraphQL, OpenAPI, tools, and MCP servers.
10 Best Claude Skills for Building AI Applications
Compare Claude skills for structured output, fallbacks, evals, hallucinations, routing, token cost, semantic caching, PII, guardrails, and tools.
10 Best Claude Skills for DevOps and SRE
Use Claude skills for incidents, rollbacks, SLOs, alerts, dashboards, logs, traces, containers, CI, and safer releases.
10 Best Claude Skills for Security Work
Compare Claude skills for secrets, dependencies, permissions, auth, RBAC, threats, headers, PII, data retention, and LLM guardrails.
7 Best Claude Skills for Documentation
Use Claude skills to verify code examples and create accurate READMEs, API docs, runbooks, onboarding guides, ADRs, and diagrams.
8 Best Claude Skills for Database Work
Compare Claude skills for safe migrations, data backfills, indexes, query plans, pooling, deadlocks, vector search, and SQL tuning.
9 Best Claude Skills for Code Review
Choose Claude skills for security, correctness, maintainability, and focused pull request review without relying on one vague review prompt.
9 Best Claude Skills for Frontend Development
Compare Claude skills for accessibility, Web Vitals, React renders, bundles, localization, browser security, test data, tests, and caching.
9 Best Claude Skills for Performance Engineering
Compare Claude skills for caching, Web Vitals, bundles, React renders, load tests, cold starts, CPU profiles, memory leaks, and prompt caches.
9 Best Claude Skills for Release Management
Use Claude skills for readiness reviews, canaries, rollbacks, API deprecations, migrations, versioning, changelogs, and release notes.
9 Best Claude Skills for Software Testing
Compare Claude skills for regression, unit, integration, contract, property, mutation, prompt, and test-data workflows.
AGENTS.md for Codex: Project Instructions That Actually Work
Write an effective AGENTS.md for OpenAI Codex — what belongs in it, how nested overrides work, and how to verify the instructions Codex loaded.
Codex Automations: Schedule Reliable Background Work
Schedule Codex tasks for recurring checks and follow-ups — choose chat or standalone runs, local projects or worktrees, skills, permissions, and stopping rules.
Codex config.toml: Settings, Precedence, and Safe Defaults
Configure OpenAI Codex with config.toml — user and project scopes, precedence, sandbox and approvals, MCP, subagents, profiles, and safe defaults.
Codex MCP Setup: Connect Tools and Live Context
Connect OpenAI Codex to MCP servers through the CLI, desktop app, IDE, or config.toml — with practical scoping, OAuth, and tool-approval guidance.
Codex Skills: Build Reusable Workflows with SKILL.md
Create, install, and test Codex skills with SKILL.md — including trigger descriptions, repo and user paths, progressive disclosure, and distribution.
Codex Subagents: Parallel Work Without Losing Control
Use Codex subagents for parallel exploration, review, tests, and implementation — including decomposition, custom agents, permissions, and merge discipline.
Contract Testing for Microservices: Consumer, Provider, and CI
Catch breaking service changes before deployment with consumer-driven contracts, provider verification, state fixtures, compatibility gates, and schema tests.
Idempotency Keys: Design APIs That Are Safe to Retry
Design idempotent API mutations with client keys, atomic claims, response replay, payload fingerprints, in-flight handling, TTLs, and downstream safety.
OpenAI Codex: A Practical Guide for Developers
Learn how OpenAI Codex works across the terminal, IDE, desktop app, and cloud — then set up a safe, repeatable workflow for real repositories.
Postgres Connection Pooling: Sizing, Timeouts, and Serverless
Size Postgres connection pools across application instances, configure lifecycle timeouts, diagnose saturation, and choose PgBouncer or a managed pooler.
Red-Teaming LLM Applications: From Attack Cases to Regression Tests
Red-team an LLM application across prompts, RAG, tools, agents, and data boundaries — scope assets, generate attacks, score impact, fix, and retest in CI.
SLOs and Error Budgets: A Practical Reliability Guide
Define user-centered SLIs and SLOs, calculate error budgets, create burn-rate alerts, set release policy, and keep reliability targets meaningful.
Software Supply Chain Security: Dependencies, Builds, and Releases
Secure the software supply chain from dependency selection through release — lockfiles, provenance, least privilege, secret controls, SBOMs, and response.
Web Performance Budgets: Turn Speed Into a Release Gate
Define and enforce web performance budgets for Core Web Vitals, JavaScript, images, fonts, third parties, and critical journeys in CI and production.
The Best MCP Servers in 2026
The MCP servers actually worth connecting in 2026 — Context7, GitHub, Chrome DevTools, Playwright, Serena, Exa, Firecrawl, and official vendor servers.
The AI Engineer Roadmap for 2026
A staged path from API calls to production agents — the skills that matter in 2026, what to skip, and the guides and tools for each stage, in order.
Adding MCP Servers to Claude Code: Local, Remote, and Project-Scoped
The complete claude mcp add reference — stdio vs HTTP transports, local/project/user scopes, .mcp.json with env expansion, OAuth via /mcp, and the gotchas.
Tools62
The AI tooling directory
Context7
Upstash's MCP server that pulls up-to-date, version-specific library documentation into your agent's context — the cure for hallucinated APIs.
Github MCP Server
GitHub's official MCP server — repos, issues, PRs, Actions, and security data for your agent, as a free hosted remote or a local Docker server.
Opencode
The open-source AI coding agent — a terminal TUI from Anomaly with 75+ model providers, LSP-powered context, parallel agents, and shareable sessions.
Codex CLI
OpenAI's open-source terminal coding agent with sandboxed execution and two-layer approval controls.
Cursor
An AI-first code editor built on VS Code with deep in-editor agent features, parallel agents, in-house Composer models, and a plugin marketplace.
Meshy
Evaluate Meshy with a versioned prop pilot, owner-set requirements, real inspection reports and actual target-application viewer evidence.
Claude Context
Zilliz's MIT-licensed MCP server that indexes your codebase into Milvus or Zilliz Cloud and gives your agent hybrid semantic code search.
Crush
Charm's terminal coding agent: nearly any model, including local ones, switched mid-session, with LSP context, MCP and Agent Skills. Source-available (FSL).
DeepWiki MCP
Cognition's free, no-auth remote MCP server for DeepWiki: generated wikis and grounded Q&A for any public GitHub repository, from inside your agent.
Desktop Commander
MIT-licensed MCP server that gives Claude Desktop and other MCP clients terminal control, file system search, and diff-based file editing.
GitMCP
Free, open-source remote MCP server that turns any public GitHub repo or Pages site into docs and code-search tools for your agent. No signup or key.
Jules
Google's asynchronous coding agent: it clones your GitHub repo into a cloud VM, proposes a plan built with Gemini, and opens a pull request once you approve.
Kiro
AWS's agentic IDE and CLI that turns a prompt into a spec of requirements, design and tasks, then checks the code against it with property-based tests.
Qwen Code
Alibaba Qwen's Apache-2.0 coding agent for the terminal, editor and desktop: OpenAI, Anthropic, Gemini and Qwen APIs, any provider, or local models.
Ref Context
Ref's documentation-search MCP server: search-then-read tools over public docs, your private GitHub repos, and PDFs. Hosted, and an API key is required.
Repomix
MIT tool that packs a local codebase or GitHub repo into one AI-friendly file, as a CLI or an MCP server your agent can grep and read in slices.
Claude
Anthropic's AI assistant app for web, desktop, and mobile, with Projects, connectors, Artifacts, skills, memory, and code execution.
Claude Cowork
Anthropic's agent for knowledge work that completes multi-step tasks in your folders, connectors, and browser, on desktop, web, and mobile.
Claude Design
An Anthropic Labs tool for making prototypes, decks, and one-pagers with Claude, using your design system, with PPTX, PDF, HTML, and Canva export.
Claude For Chrome
Anthropic's Chrome extension that lets Claude read pages, click, fill forms, and run tasks in your signed-in browser, with site permissions and action checks.
Claude For Excel
Anthropic's Excel add-in that explains, edits, debugs, and builds spreadsheet models in place, with cell-level citations, on paid Claude plans.
Alttext AI
Evaluate AltText.ai drafts against inspected observations, page purpose, correction notes and the actual publishing review process.
Dedupe
Evaluate Dedupe through an owner-reviewed matching pilot with known pairs, preserved source keys, candidate coverage checks and unresolved cases.
Augment Code
AI coding assistant built for large, real-world codebases — a Context Engine that indexes the whole repo, with agents and chat in IDEs and a CLI.
Factory
Factory is an agent-native software development platform whose Droids plan, write, test, and ship code from the terminal, IDE, and web with org context.
Trae
Trae is an AI-native IDE from ByteDance — a VS Code-style editor with a built-in Builder agent and an autonomous SOLO mode that writes code across a project.
Wave Terminal
Open-source terminal that blends the CLI with inline file previews, a built-in editor, a web browser, and a context-aware AI assistant in one window.
Kilo Code
Open-source AI coding agent for VS Code and JetBrains, begun as a Roo Code fork and rebuilt on OpenCode, with bring-your-own-key and zero model markup.
OpenHands
Open-source autonomous AI software-development agent (formerly OpenDevin) — writes code, runs commands, and browses the web in a sandbox.
Glossary44
AI terms, defined precisely
Alternative Text
Choose useful wording for an image placement by keeping inspected observations, page purpose and human approval together.
Physically Based Rendering
Review an AI material handoff without confusing supplied map files with verified appearance in the target scene.
UV Mapping
Understand why a 3D handoff keeps mesh, surface-layout and texture versions together before approving their actual target appearance.
AI Connectors
AI connectors are the integrations that let an assistant like Claude read and act in tools such as Google Drive, Slack, and Notion; in Claude, MCP servers.
Claude Cowork
Claude Cowork is the agentic mode of Anthropic's Claude app that completes multi-step knowledge-work tasks in your files, connectors, and browser.
Claude Plugins
Claude Plugins are installable bundles of skills, slash commands, sub-agents, and MCP connectors that set up Claude Code or Claude Cowork for a role or team.
llms.txt
llms.txt is a proposed Markdown file at a site's root that gives AI models a curated summary and link list, so they can find the right pages at inference time.
AGENTS.md
AGENTS.md is a versioned instruction file that tells coding agents how to work in a repository — including commands, conventions, boundaries, and checks.
Agent Skills
Agent Skills are reusable procedures packaged as folders with a SKILL.md file — loaded by an AI agent on demand when a task matches, now an open standard.
A2A (Agent2Agent Protocol)
A2A is an open protocol that lets AI agents discover each other's capabilities and delegate tasks across vendors, complementing MCP's tool connections.
Context Engineering
Context engineering is the discipline of curating exactly what enters an LLM's context window so it has the right information and nothing else.
Extended Thinking
Extended thinking is the reasoning tokens a model generates before its final answer, trading latency and cost for higher accuracy on hard problems.
LLMOps
LLMOps is the practices and tooling for running LLM apps in production: prompt versioning, evals, tracing, cost and latency monitoring, and guardrails.
Model Routing
Model routing sends each request to the cheapest model that can handle it, escalating only hard cases to a stronger model — cutting cost and latency.
ReAct (Reasoning + Acting)
ReAct is an agent loop that interleaves reasoning with tool actions — Thought, Action, Observation, repeat — so the model plans, calls a tool, and revises.
Tree of Thoughts
Tree of Thoughts is a prompting method that explores multiple reasoning branches as a search tree, evaluating and backtracking among them.
Agent Harness
An agent harness is the system around the model that makes it an agent — the loop, tools, context management, permissions, and recovery machinery.
Chunking
Chunking splits documents into retrievable pieces before embedding — the RAG design decision that quietly determines retrieval quality.
Constitutional AI
Constitutional AI trains models against written principles — the model critiques and revises its own outputs by them, reducing reliance on human labels.
Frontier Model
A frontier model is one of the most capable AI models available — the leading edge from labs like Anthropic, OpenAI, and Google, defining the state of the art.
Jailbreak
A jailbreak is a prompt crafted to bypass a model's safety training and policies — making it produce output it was trained to refuse.
Prompt Template
A prompt template is a parameterized prompt — fixed instructions with variable slots — turning prompts from strings into versioned, testable components.
Red-Teaming (AI)
AI red-teaming is adversarial testing — attacking your model or agent with jailbreaks, injections, and misuse scenarios to find failures before users do.
Token Streaming
Token streaming delivers model output incrementally as it's generated — via SSE or websockets — so users see text immediately instead of waiting.
Tracing (LLM)
LLM tracing records every step of a model-driven request — prompts, tool calls, retrievals, tokens, latency — so multi-step behavior is debuggable.
Agent Engineering
Agent engineering is the discipline of building reliable AI agents — designing the tools, context, guardrails, evals, and recovery paths around the model.
Agent Memory
Agent memory is how an AI agent retains information beyond its context window — working state during a task and persistent knowledge across sessions.
Agentic AI
Agentic AI is the class of AI systems that act toward goals — planning, calling tools, and iterating on results — rather than only generating content.
Chain-of-Thought (CoT)
Chain-of-thought prompting has a model work through intermediate reasoning steps before answering — improving accuracy on multi-step problems.
Fine-Tuning
Fine-tuning continues training a pretrained model on your own examples, changing its weights to teach durable behavior, format, or domain style.
Agents42
Specialized subagents for focused work
Agent Architect
Use this agent to design a new Claude Code subagent or review an existing one — scoping, description, toolset, model, and output contract. Examples — "design an agent that triages flaky tests", "review my code-reviewer agent for scope creep", "why won't Claude auto-delegate to my agent?".
Rust Pro
Use this agent for idiomatic Rust — ownership, lifetimes, error handling, traits, async with tokio, and the cargo toolchain. Examples — fixing borrow-checker errors, designing a trait API, making async code compile cleanly under tokio.
React Specialist
Use this agent for React architecture — hooks, state, performance, Server Components, and patterns. Examples — fixing re-render issues, designing component state, adopting RSC.
API Architect
Use this agent to design APIs — resource modeling, versioning, pagination, error contracts, REST vs GraphQL. Examples — designing a public API, reviewing an API spec, planning a breaking change.
Cloud Architect
Use this agent to design a cloud architecture on AWS, GCP, or Azure — compute, networking, data stores, IAM, and cost trade-offs. Examples — choosing serverless vs containers for a new service, designing a multi-account network boundary, picking a database and estimating its monthly cost.
Code Reviewer
Use this agent to review code changes for correctness, security, and maintainability before merging. Examples — reviewing a PR diff, auditing a new module, checking a refactor for regressions.
Debugger
Use this agent to diagnose failing tests, runtime errors, or unexpected behavior by forming and testing hypotheses. Examples — a stack trace to root-cause, a flaky test, a "works locally but not in CI" bug.
Security Auditor
Use this agent to find security vulnerabilities — injection, auth flaws, secrets, unsafe deserialization, dependency risks. Examples — auditing an API surface, reviewing auth code, pre-release security pass.
Workflow Orchestrator
Use this agent to break large tasks into coordinated multi-step plans and delegate to other agents. Examples — planning a multi-file refactor, orchestrating a migration, decomposing an epic.
Image Description Reviewer
Review still-image text alternatives against page purpose, verified visual evidence and source data; flag missing meaning, invented detail and chart-description conflicts without claiming conformance.
Kotlin Pro
Use this agent for idiomatic Kotlin — null safety, coroutines and structured concurrency, Flow, sealed classes with exhaustive when, data classes, and extension functions — on Android and the JVM. Examples — fixing a coroutine leak, replacing callbacks with Flow, removing !! null-safety holes.
Php Pro
Use this agent for idiomatic, modern PHP 8.3+ — strict types, enums, readonly and promoted properties, Composer/PSR-4 autoloading, and safe PDO data access. Examples — modernizing a PHP 5-era class, killing an ORM N+1, hardening a query against SQL injection.
Swift Pro
Use this agent for modern Swift 6 — value semantics, optionals done right, async/await and actors, Sendable/data-race safety, and idiomatic SwiftUI. Examples — fixing a data race under strict concurrency, untangling force-unwrap crashes, making a SwiftUI list scroll smoothly.
C# Pro
Use this agent for modern C#/.NET 8+ — records, pattern matching, nullable reference types, correct async/await, LINQ, Span<T>, and source generators — plus ASP.NET Core and EF Core. Examples — building a minimal-API service, fixing an EF Core N+1 or tracking leak, hunting a deadlock from sync-over-async, or turning on nullable reference types across a project.
CI/CD Engineer
Use this agent to design, speed up, and harden CI/CD pipelines on any provider (GitHub Actions, GitLab CI, CircleCI, Buildkite). Examples — setting up a build→test→deploy pipeline from scratch, cutting a 25-minute CI run down with caching and matrix parallelism, adding a canary or blue-green deploy with automatic rollback, or reviewing a workflow for leaked secrets, over-broad tokens, and unpinned third-party actions.
CLI Tooling Engineer
Use this agent to design or build a command-line tool — subcommand and flag layout, --help and error UX, exit codes, --json/machine output, config precedence, stdin/stdout/stderr and pipe behavior, TTY/color/NO_COLOR detection, and CLI testing. Examples — "design the command and flag surface for our new deploy CLI", "this tool prints errors to stdout and returns 0 on failure — fix its ergonomics", "make our command pipe-friendly and add a --json mode for CI".
Context Engineer
Use this agent to engineer what an LLM agent carries in its context window — deciding what to include vs exclude vs retrieve on demand, designing project/agent memory (CLAUDE.md), compacting growing history, and allocating the token budget across system prompt, memory, retrieved docs, tool results, and conversation. Examples — "my agent forgets the schema we agreed on three turns ago", "the agent gets dumber and more inconsistent as the chat grows", "we're burning 60k tokens of tool output every turn", "what should this support agent always know vs look up?".
Database Architect
Use this agent to design data models and storage strategy from access patterns — schema design, normalization vs deliberate denormalization, relational vs document vs key-value vs wide-column vs graph selection, indexing, partitioning/sharding, transaction boundaries, and consistency models. Examples — modeling a new feature's schema, choosing a database for a write-heavy event workload, reviewing a schema for missing indexes or scaling cliffs, planning how to shard a table that no longer fits one node.
Eval Driven Developer
Use this agent to drive AI feature development with evals the way TDD drives code with tests — define success criteria and a representative eval set BEFORE iterating on prompts/models, then optimize against measured scores instead of vibes. Examples — "make the summarizer better" (turn it into measurable criteria first), "our prompt change keeps regressing quality, set up a loop that catches it", "add an eval gate to CI so a model swap can't silently degrade output", "we tweak prompts and pray — give us a baseline and a change-by-change scoreboard".
Incident Responder
Use this agent during a live production incident to restore service fast and learn from it — triage and severity, mitigation-first action (roll back, fail over, shed load), change correlation, status updates, and the blameless postmortem. Examples — an alert just fired and the API is 5xx-ing, a deploy broke checkout and you need to decide rollback vs. forward-fix, latency is climbing and the pager is going off, or you're writing the postmortem the morning after.
Java Pro
Use this agent for idiomatic, modern Java (17/21+) — records, sealed types, pattern matching, virtual threads and structured concurrency, the Streams API, and JVM/GC performance. Examples — modernizing a legacy POJO-and-thread-pool service to records and virtual threads, diagnosing a GC pause or allocation hotspot, reviewing concurrency correctness, or fixing a Spring Boot service that blocks the wrong threads.
QA Automation Engineer
Use this agent for end-to-end and UI test automation — building flake-resistant Playwright/Cypress suites, stabilizing flaky browser tests, structuring page objects and fixtures, and reviewing E2E suites. Examples — adding E2E coverage for a checkout or signup flow, killing a test that fails 1-in-5 in CI, choosing a framework and folder structure, replacing sleeps with web-first waits, or auditing a suite that's slow and brittle.
MCP Server Engineer
Use this agent to build, harden, or productionize a Model Context Protocol (MCP) server — designing tools/resources/prompts, choosing stdio vs. Streamable HTTP, taking a server remote with OAuth and stateless scaling, and testing it with the MCP Inspector. Examples — "wrap our internal API as an MCP server with three tools", "take our stdio server remote so the team can share it", "our tools confuse the model — fix the names, schemas, and descriptions".
Prompt Injection Auditor
Use this agent to audit an LLM app or agent for prompt-injection exposure — mapping where untrusted content enters the model's context (user, RAG, tools, web), assessing the blast radius if an injection succeeds, probing with adversarial inputs, and recommending architectural mitigations. Examples — "audit our RAG agent for indirect prompt injection", "what's the blast radius if our agent gets injected — which tools and credentials are exposed?", "review our LLM app's trust boundaries and tell us what to fix".
Agent Reliability Reviewer
Use this agent to make an AI agent production-ready — reviewing its loops, cost controls, error handling, tool use, human-in-the-loop gates, checkpointing, and observability, then reporting concrete failure modes and fixes. Examples — "is our agent safe to ship?", "our agent loops forever / burns tokens, harden it", "add guardrails and recovery before we put this agent in front of users".
Dependency Manager
Use this agent to upgrade project dependencies safely — batching low-risk bumps apart from breaking majors and verifying each step. Examples — clearing months of stale packages, taking a single major version with migration notes, resolving a peer-dependency conflict.
GraphQL Architect
Use this agent to design GraphQL schemas and resolvers — types, nullability, connections, dataloaders, federation, depth/complexity limits. Examples — designing a new schema from requirements, killing N+1 queries in resolvers, planning a deprecation, hardening a public graph.
Terraform Specialist
Use this agent for Terraform and infrastructure-as-code — module design, remote state, plan/apply safety, drift, and provider pinning. Examples — reviewing a plan for destroys before apply, designing a reusable module, resolving state drift after a console change.
Git Github Expert
Use this agent for Git and GitHub workflows — rebases, conflict resolution, history surgery, PRs, and Actions. Examples — resolving a messy merge, rewriting history safely, fixing a workflow file.
Backend Developer
Use this agent to build server-side features — endpoints, business logic, data access, background jobs. Examples — a new REST/GraphQL endpoint, a queue worker, a database integration.
Skills92
Reusable capabilities Claude loads on demand
API Deprecation Planner
Plan the retirement of an API endpoint, field, event, tool, or version without surprising active consumers. Use when replacing an interface, removing legacy behavior, publishing a sunset, migrating internal or external clients, or deciding whether observed traffic is safe to turn off.
Background Job Reliability Auditor
Audit scheduled jobs, queue consumers, workers, and asynchronous workflows for delivery assumptions, idempotency, retries, poison messages, concurrency, timeouts, checkpoints, shutdown, and observability. Use when a job duplicates work, silently stops, falls behind, fails only at scale, or needs review before production.
Cache Policy Designer
Design a cache policy from data ownership, freshness, privacy, invalidation, and failure requirements across browser, CDN, reverse-proxy, application, and data caches. Use when adding caching, debugging stale responses, reviewing Cache-Control behavior, reducing origin load, or deciding whether a value can be cached safely at all.
Code Example Verifier
Verify documentation code examples against the current repository and toolchain, then fix snippets, imports, commands, and expected output without changing the documented intent. Use when docs examples may be stale, an SDK or API changed, users report copy-paste failures, or before publishing tutorials, READMEs, migration guides, and release documentation.
Data Retention Auditor
Audit where personal or sensitive data is collected, copied, retained, backed up, logged, exported, and deleted, then compare actual lifecycle behavior with stated policy. Use when adding a data field, preparing a privacy review, implementing account deletion, reducing stored data, or checking whether retention controls work across primary and secondary systems.
Flaky Test Diagnoser
Diagnose a test that passes and fails without relevant code changes by reproducing the instability, classifying its trigger, and isolating the shared state, timing, ordering, concurrency, randomness, or environment dependency behind it. Use when CI retries hide failures, a test fails only in the suite, or a failure cannot be reproduced reliably on one machine.
Incident Postmortem Writer
Turn incident notes, alerts, chat logs, deploy history, and traces into a blameless, evidence-backed postmortem with impact, timeline, contributing conditions, detection and response gaps, and owned corrective actions. Use after a production incident, failed deployment, security event, or near miss when the team needs a durable learning document rather than a root-cause guess.
Least Privilege Auditor
Audit application, CI, cloud, database, and agent permissions against observed usage, then produce a safe reduction plan with verification and rollback. Use when credentials have broad scopes, service roles grew organically, CI tokens can write too much, an agent or MCP server has excessive tools, or before a security review or compliance audit.
Localization Readiness Auditor
Audit an application or feature for localization readiness across extracted messages, interpolation, pluralization, date and number formatting, layout expansion, right-to-left behavior, sorting, search, assets, metadata, and test coverage. Use before adding a locale, reviewing hard-coded UI text, or investigating a feature that breaks outside English.
Monorepo Boundary Auditor
Audit a monorepo's package boundaries, dependency direction, public entry points, ownership, build graph, and affected-test rules, then report cycles and cross-layer imports with a staged repair plan. Use when packages are tightly coupled, builds invalidate too much, teams import internals, dependency cycles appear, or a monorepo migration needs enforceable architecture boundaries.
Regression Test Writer
Turn a reported bug into the smallest test that fails for the real reason before the fix and passes afterward. Use when reproducing a defect, reviewing a bug fix with no guard test, converting an incident into permanent coverage, or preventing a previously fixed edge case from returning.
Release Readiness Reviewer
Review whether a specific release is ready to ship by checking scope, tests, compatibility, migrations, configuration, observability, rollout, rollback, support, security, and ownership against explicit evidence. Use before a production deployment, major version, risky feature launch, migration, or go/no-go meeting.
Rollback Plan Writer
Write a tested rollback and forward-recovery plan for a release, including triggers, commands, compatibility constraints, data handling, verification, ownership, and stop conditions. Use before high-risk deploys, schema or configuration changes, dependency upgrades, model or provider migrations, feature launches, and any release where 'just redeploy the old version' is incomplete or unsafe.
Safe Data Backfill Planner
Plan and implement a resumable production data backfill with bounded batches, checkpoints, rate limits, correctness verification, observability, and a pause or rollback path. Use when populating a new column, repairing historical rows, re-keying records, migrating derived data, or updating millions of records without overwhelming the database or replicas.
Conventional Commits
Generate clear Conventional Commits messages from staged changes. Use when committing code and you want a well-structured, consistent commit message.
PR Description
Draft a clear pull request description from the branch diff against its base. Use when you have a finished branch and want a reviewer-ready PR body before opening the PR.
Secret Scanner
Scan a repo or a diff for committed secrets — API keys, tokens, private keys, .env files, and high-entropy strings — then triage real leaks from fixtures. Use before pushing, in review, or when a credential may have leaked.
3D Asset Handoff Sheet
Build a 3D asset handoff sheet from supplied export metadata, target-app technical reports and human viewer notes, preserving mesh/UV/material versions and untested checks.
API Error Contract Designer
Design or normalize an API's error contract so clients get stable machine-readable codes, safe human messages, field-level validation details, correlation IDs, and consistent HTTP semantics. Use when adding endpoints, replacing ad hoc error strings, documenting SDK behavior, or fixing clients that branch on fragile message text.
Skill Auditor
Audit an installed set of Claude Code skills for the failure modes that make them misfire — overlapping descriptions that misroute tasks, trigger phrasing that never matches, bloated bodies, missing boundaries, and over-broad tool grants — and return a prioritized fix list with rewritten descriptions. Use when a skill fires on the wrong tasks, never fires at all, or a skills folder has grown past what anyone reviews.
CORS Configurator
Diagnose and fix a failing cross-origin browser request — read the exact console error, work out whether it's a simple or preflighted request, and set the minimal correct Access-Control-* response headers (including the wildcard-with-credentials trap and the OPTIONS preflight) on the server. Use when the browser blocks a fetch/XHR with a CORS error but the API itself works from curl or Postman.
Dockerfile Optimizer
Shrink and harden an existing Dockerfile — multi-stage builds, cache-friendly layer order, a lean pinned base image, a .dockerignore, and a non-root runtime user — without changing what the image runs. Use when an image is too large, builds are slow because the cache never hits, or a scan flags the container running as root.
License Compliance Checker
Audit the licenses of a project's dependencies for compatibility with how the project is distributed — flagging copyleft (GPL/AGPL/LGPL), missing or unknown licenses, and other obligations that conflict with your own license or SaaS/proprietary model. Use before shipping or open-sourcing, when adding a dependency, or when legal/procurement asks for a license inventory. This is a licensing review, not a vulnerability scan.
Agent Memory Designer
Design a project's CLAUDE.md and memory hierarchy by exploring the repo to learn its real build/test/lint commands, architecture, and non-obvious gotchas, then writing a concise, skimmable memory that keeps only what belongs in context. Use when onboarding a repo to Claude Code with no CLAUDE.md, or when an existing one is bloated, stale, or being ignored.
Alerting Rules Tuner
Cut alert noise and make every page mean something — rewrite alerting rules to fire on user-felt symptoms (error rate, latency SLO burn, failed requests) instead of causes (high CPU, full disk), with duration windows and severity routing so only urgent, actionable conditions reach a human. Use when on-call is fatigued by low-value pages, when real incidents get missed in the noise, or when alerts fire on causes rather than impact.
Architecture Diagram Generator
Generate accurate architecture diagrams as Mermaid — straight from the codebase, not from imagination — by first choosing which view answers the question (container/component, sequence, ER, or state) and then reading the real entry points, module boundaries, service calls, and schema. Use when onboarding to an unfamiliar repo, documenting a system, or visualizing one complex flow.
Auth Flow Reviewer
Read-only review of authentication AND authorization flows — session/token model, cookie flags, CSRF, token rotation, password-reset/email-verification, OAuth redirect/state, and per-route object-level access checks — for exploitable gaps. Use before shipping login/session/token code, when adding a protected route or sharing-by-URL feature, or during a security pass. Reports findings by severity with location, impact, and the concrete fix; never edits code.
Canary Release Planner
Design a canary / progressive rollout so a bad release reaches 1% of users instead of 100% — staged traffic with bake times, gating metrics compared against the concurrently-running stable baseline, and automated promote-or-rollback. Use when shipping a risky change, when you want automatic rollback on regression, or when moving off all-at-once deploys.
Circular Dependency Breaker
Detect and break a circular import — map the exact cycle with a real tool, then break the right edge by extracting the shared piece into a leaf module, inverting a layering dependency, merging two falsely-split modules, or (last resort) deferring an import. Use when you hit an import cycle error, an undefined-on-import or 'cannot access before initialization' bug, or a bundler/linter flags a cycle.
Cold Start Optimizer
Cut cold-start latency for serverless functions and slow-booting apps by measuring the init breakdown, then attacking the dominant phase — artifact size, eager imports, eager connections, or under-provisioned memory — instead of reflexively buying provisioned concurrency. Use when serverless p99 spikes on the first request, when a function times out during init, or when scale-to-zero is hurting user-facing latency.
Commands53
Slash commands for Claude Code
Create PR
Push the current branch and open a GitHub pull request with a generated title and body.
Review PR
Review a pull request for correctness, security, and style, and summarize findings.
Check Entity Match Ledger
Check entity-match-ledger.json for source-linked evidence values, duplicate pairs, reviewer presence and contradictory match groups without merging records.
Check Annotation Batch
Check annotation-batch.json for approved labels, distinct response reviewers, exact text evidence and unresolved disagreements while preserving the input.
Check Survey Paths
Check survey-paths.json for complete single-choice routes, cycles, reachable nodes and expected test paths without editing the file or contacting a form service.
Git Undo
Safely reverse the last Git operation in the current repo — pick the right tool (restore, reset --soft/--mixed, revert, or reflog recovery) based on what happened and whether it was already pushed, and confirm before anything destructive.
Optimize Imports
Remove unused imports and organize the rest in a file or directory per the project's conventions — preferring the project's own import tool where one is configured — without changing behavior.
Scaffold CLI Command
Scaffold a new subcommand for an existing CLI (or a minimal new CLI) in the project's language — flag/argument parsing, --help text, input validation, and correct exit codes — matching the framework and conventions already in use.
Add Caching
Add a caching layer to one expensive function or endpoint correctly — confirm it's cacheable, design the cache key/TTL/layer/invalidation, handle stampedes, wrap the call in one place, and report the design.
Clean Branches
Safely prune merged and stale Git branches: drop dead remote-tracking refs, list merged candidates for review, then delete with the safe -d variant.
Create Skill
Scaffold a new Claude Code skill into .claude/skills/<name>/SKILL.md — a model-invoked capability with a trigger-rich description, scoped tools, and a lean body that pushes detail into resource files.
Create Slash Command
Scaffold a new Claude Code slash command into .claude/commands/ — a valid Markdown file with frontmatter, a least-privilege allowed-tools allowlist, and a $ARGUMENTS-driven body of numbered steps ending in a Report.
Create Subagent
Scaffold a new Claude Code subagent definition file into .claude/agents/ with a routing-ready description, scoped tools, and a system prompt.
Estimate Effort
Produce a grounded effort and complexity estimate for a task by exploring the codebase read-only.
Find N+1 Queries
Scan code read-only for N+1 query patterns — loops that query per iteration and handlers that fan out per-row — and report each with a location, why it is N+1, and the concrete eager-load/batch/set-based fix.
Generate E2E Test
Scaffold a resilient end-to-end test for a user flow grounded in the real UI.
Git Bisect
Drive git bisect to find the exact commit that introduced a regression.
Hunt Flaky Tests
Reproduce a flaky test, find the real source of nondeterminism, and fix the cause.
Rename Symbol
Safely rename a symbol project-wide, distinguishing the real symbol from coincidental substring matches.
Resolve Merge Conflicts
Walk through resolving the in-progress merge, rebase, or cherry-pick conflict in the current repo by understanding both sides, then verify before continuing.
Review Tests
Review the quality of a test suite, not just whether it passes — find weak assertions, missing edge cases, and tests coupled to implementation.
Scaffold Dockerfile
Scaffold a production-grade multi-stage Dockerfile and .dockerignore for the current project.
Scaffold GitHub Action
Scaffold a hardened GitHub Actions workflow for a stated goal, wired to the project's real test/lint/build commands.
Scaffold RAG Pipeline
Scaffold a Retrieval-Augmented Generation pipeline — ingestion (load, chunk, embed, upsert) and retrieval (search, rerank, grounded prompt with citations) — fitted to the project's stack.
Seed Data
Generate realistic, referentially-consistent seed data and a re-runnable seed script from your actual schema — types and constraints respected, plausible values, FK-dependency insert order, idempotent, never aimed at production.
Setup Pre-commit Hooks
Set up fast pre-commit hooks that catch problems before they land — detect the repo's existing stack and hook mechanism, run lint/format/typecheck plus a secret scan on staged files only, keep the slow test suite in CI, and make the setup reproducible for the whole team.
Trace Data Flow
Trace how a value, field, or variable flows through the codebase from source to sink.
Write Design Doc
Explore the codebase and write a decision-oriented design doc / RFC for a feature or system change.
Setup Claude CI
Wire Claude Code into this repo's CI the safe way — install the GitHub App or scaffold the workflow YAML, scope permissions to the minimum, set secrets correctly, and verify with a real trigger.
Add MCP Server
Add an MCP server to the current project the safe way — pick the transport and scope, wire secrets through env vars, vet provenance, and verify the connection before trusting it.