langwatch

langwatch/langwatch

Settings file Claude Code

Agent settings configuring enabledPlugins, env.

langwatch/langwatch

Skill Claude CodeCodex

Collaborative headed browser session for UI work. Launch Playwright Chromium visible to the user, handle auth, then interactively drive the browser while the user watches and gives real-time visual feedback. Edit code and refresh to verify fixes live. Use when the user says 'browser pair', 'paired browser', 'let's…

langwatch/langwatch

Skill Claude CodeCodex

Validate a feature works by driving a real browser with Playwright MCP. No test files — just interactive verification.

langwatch/langwatch

Skill Claude CodeCodex

Project-level code review: check changed files against LangWatch codebase rules (IDs, multitenancy, layering, naming, SRP).

langwatch/langwatch

Skill Claude CodeCodex

Maintain the canonical LangWatch feature map (/feature-map.json). Use when adding features, APIs, MCP tools, CLI commands, or skills — to update the central registry and keep surfaces in sync.

langwatch/langwatch

Skill Claude CodeCodex

Bring up the LangWatch dev stack via thuishaven (make haven up) — one-time proxy/CA setup, reusing existing local ClickHouse/Postgres/Redis, WSL2/no-colima fallback for langyagent, and the known gotchas that silently break it.

langwatch/langwatch

Skill Claude CodeCodex

Manage the LangWatch Kanban GitHub project board — sync statuses, view your board, find stale items, move issues, assign work.

langwatch/langwatch

MCP server Claude CodeCodexCursor +2

MCP server "playwright" as configured in langwatch/langwatch. Launched with bash -c d=$PWD; while [ "$d" != / ] && [ ! -f "$d/dev/scripts/playwright-mcp.sh".

langwatch/langwatch

MCP server Claude CodeCodexCursor +2

MCP server "playwright-headed" as configured in langwatch/langwatch. Launched with bash -c d=$PWD; while [ "$d" != / ] && [ ! -f "$d/dev/scripts/playwright-mcp.sh".

langwatch/langwatch

Instructions file

Instructions for langwatch/langwatch, covering langwatch, before you implement anything, development environment, running with no container runtime and local dev by hostname — thuishaven / portless (recommended).

langwatch/langwatch

Plugin Claude Code

Plugin marketplace listing 1 plugin: langwatch.

langwatch/langwatch

Plugin Claude Code

Records which repository and branch each coding-agent session worked in, and teaches the agent to read its own traces back from LangWatch.

langwatch/langwatch

Hook

Runs when a session starts, executing session-context.mjs and session-guidance.mjs via node (2 commands). From langwatch/langwatch.

langwatch/langwatch

Hook

Runs when the agent finishes a response, executing session-context.mjs via node. From langwatch/langwatch.

langwatch/langwatch

Skill Claude CodeCodex

Read LLM traces back from LangWatch with the langwatch CLI. Use when asked what an agent, prompt or model call actually did in production, when debugging a failed or slow LLM run, when looking up a trace or session by id, or when checking whether this coding session's own activity was captured.

langwatch/langwatch

Skill Claude CodeCodex

Expert AI engineering consultant for your agent development practices. Audits your codebase, traces, evaluations, and scenarios against best practices, then guides you to close the gaps, starting from low-hanging fruit and going deeper. Use when you want to level up your agent's engineering quality.

langwatch/langwatch

Skill Claude CodeCodex

Turns production evidence into tested improvements for your AI agent. Forms hypotheses from real traces and analytics, explains the reasoning behind each one, then executes with the user: scenario tests that reproduce production failures, prompt and code changes as reviewable PRs, new evaluators and monitors that…

langwatch/langwatch

Skill Claude CodeCodex

Deep-dive diagnosis of how your AI agent behaves in production. Explores LangWatch analytics and traces end to end to map failure patterns, dissatisfied users, token cost hotspots, edge cases, behavior changes, and outliers, then delivers an HTML report where every finding links to real example traces. Use when you…

langwatch/langwatch

Skill Claude CodeCodex

Connect the codebase's AI agent to LangWatch agent simulations over HTTP, so test suites run against it from the platform. Finds or adds the agent's chat endpoint, wires authentication for scenario traffic, makes the server adopt the W3C traceparent header so the judge reads the agent's own traces, registers the agent…

langwatch/langwatch

Skill Claude CodeCodex

Investigates the context economics of your own coding-agent sessions in LangWatch. Reads real sessions to find where carrying a fat context stops paying for itself, measured in cache rebuilds, compactions and cost per turn, and delivers a report with the context size your sessions should stay under, with example…

langwatch/langwatch

Skill Claude CodeCodex

Generate realistic synthetic evaluation datasets by analyzing the user's codebase, prompts, production traces, and reference materials. Interactive and consultant-style. Asks clarifying questions, proposes a plan, generates a preview for approval, then delivers a complete dataset uploaded to LangWatch. Use when user…

langwatch/langwatch

Skill Claude CodeCodex

Debug and improve your LangWatch traces. Inspects production traces for missing input/output, disconnected spans, unlabeled traces, and missing metadata. Use when traces look broken or incomplete.

langwatch/langwatch

Skill Claude CodeCodex

Root-cause production errors and misbehaving agent runs with LangWatch. Finds errored traces, inspects spans, checks monitor and evaluator scores, then narrows to a root cause. Use when something is failing or misbehaving in production (errors, bad answers, latency spikes).

langwatch/langwatch

Skill Claude CodeCodex

Drive the page the user has open through live UI actions. List the actions a page accepts, call them with typed payloads, and read the live state including unsaved edits. Use when the user is looking at a page you can operate, such as the evaluations workbench, and a change should happen in front of them rather than…