langfuse

Use when editing worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, pricing tiers, tokenizer IDs, or matchPattern regexes for OpenAI, Anthropic, Bedrock, Vertex, Azure, or Gemini model pricing.

Instrument Langfuse with PostHog product analytics, and decide whether new frontend work should be instrumented. Use when (1) adding a meaningful user action to the frontend — a button, onClick/onSubmit handler, form, dialog, toggle, tRPC mutation call, or a new feature surface in `web/**` — pause and propose instrumentation before finishing; (2) asked to instrument a feature, add analytics or usage tracking, or answer "how do people use X"; (3) adding or reviewing `capture()` events, `usePostHogClientCapture`, or any code that touches `posthog`.

Upgrade pnpm workspace dependencies to target/latest versions: direct/transitive bumps, release-age checks, temporary overrides, minimumReleaseAgeExclude, lockfile/dedupe verification.

Seed local Langfuse test data with one command: large/branching observation trees (v3 and v4 events), long sessions, bulk traces for list performance. Use whenever a task needs ClickHouse/Postgres test data — e.g. "seed a complex trace", "make a tough session", "fill the trace list", "test v4 events UI", or when debugging trace/session/list rendering or performance. Never write ad-hoc seed scripts or raw ClickHouse inserts.

Use when writing or reviewing Storybook stories (`.stories.tsx`) for React components.

Use when designing, implementing, reviewing, or hardening Langfuse repo-owned autonomous agents, especially GitHub Actions that invoke Claude, Codex, or another LLM agent on a schedule or workflow_dispatch, create pull requests, update workflow prompts or allowlists, handle GitHub tokens/secrets, use untrusted web content, or self-improve repo agent instructions.

MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.

Tune Langfuse infrastructure autoscaling safely across web, web-iso, and web-ingestion. Use when Codex needs to review or change Terraform scale settings, RPM targets, scale-up/scale-down boundaries, min/max task counts, cost/performance tradeoffs, dashboard scaling markers, Datadog event-loop metrics, trace/span evidence, GitHub pull requests, or Linear follow-up tickets for `web`, `web-iso`, or `web-ingestion` containers in the langfuse/infrastructure repository.

Langfuse-specific Datadog query recipes for production telemetry research. Use when asked to investigate tenant or project activity, public API endpoint usage, queue consumer behavior, spans, logs, metrics, or ad hoc production questions across prod-us, prod-eu, prod-hipaa, and prod-jp. This skill is for reusable query shapes and measured research; pair it with debug-issue-with-datadog when the task is an incident or root-cause analysis.

Navigate Langfuse repositories, code areas, and agent skills. Use when a user or agent asks where Langfuse code lives, which Langfuse repo to inspect, which Langfuse skill applies, how to search across Langfuse repositories, or how to orient in the Langfuse org before implementing, debugging, documenting, supporting, or operating Langfuse.

Prepare Langfuse weekly production reviews that audit what broke, what was fixed, what remains open, and where Datadog, incident.io, or Linear tracking needs cleanup. Use when asked for a production review, "what broke last week", fixed/open production bugs, Datadog alerted monitors/pages, Datadog error log patterns, incident.io incidents, incident.io alert load, pager load by engineer or time of day, or a source-table engineering review across incident.io, Linear bugs, Datadog alerts, and Datadog logs.

Review an engineer's recurring work queue across Linear, Pylon, and GitHub. Use when asked to triage assigned issues, waiting or urgent work, customer-support follow-ups, stale tickets, or pull requests where the engineer is a direct or team reviewer; return concrete action recommendations and gate all writes on explicit human approval.

Shared backend guide for Langfuse's Next.js, tRPC, BullMQ, and TypeScript monorepo. Use when creating or reviewing tRPC routers, public REST endpoints, BullMQ queue processors, backend services, middleware, Prisma or ClickHouse data access, OpenTelemetry instrumentation, Zod validation, env configuration, or backend tests across web, worker, or packages/shared.

Shared workflow for browser-based review of user-visible frontend changes in Langfuse. Use when a change affects UI behavior, layout, styling, navigation, or browser-visible regressions and should be checked with the Playwright MCP server before signoff.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Shared code review workflow for Langfuse. Use when reviewing a PR, branch, diff, or local changes for correctness, regressions, risk, and missing tests. Start with references/review-checklist.md for repo-specific review rules and use package AGENTS.md files plus any matching shared skills when the change touches those areas.

Security review patterns for Langfuse. Use during code review, design, or planning whenever a change accepts user-supplied URLs, host/endpoint/baseURL fields, secrets, cross-tenant data, new outbound HTTP requests, new integrations (webhooks, blob storage, LLM connections, image proxies), redirect-following behavior, or new auth/permission scopes. Covers SSRF/outbound URL validation today and is intentionally extensible to other recurring security findings (tenant isolation, secret handling, redirect mishandling, file upload, RBAC scope drift).

Use when building, changing, or refactoring large Langfuse frontend features, virtualized lists, large tables, controller components, local feature state, Zustand stores, row selection, high-frequency UI state, or rendering-performance issues.

Shared workflow for editing Langfuse's repo-owned agent setup under `.agents/`. Use when changing AGENTS files, shared skills, `.agents/config.json`, generated shim behavior, provider discovery paths, or install-time agent sync.

Langfuse repo Git, GitHub, commit, branch, pull request, issue search, release, and production-promotion workflow. Use when staging, committing, pushing, opening PRs, searching GitHub issues, or changing release/promotion behavior.

Deduplicate measured bug or regression evidence against Linear, then either add evidence comments to related existing issues or create concise Linear bug issues in Triage. Use when Codex has confirmed evidence from Datadog, benchmarks, traces, timings, flamegraphs, logs, or production measurements and needs Linear search, comments, labels, Datadog links, or bug ticket creation without fix suggestions, but only after a human has approved sharing the findings in Linear.

Debug a user-reported issue, Linear ticket, or incident report by combining Datadog (APM, logs, metrics) with the Langfuse repo to establish a root cause. Use when given a Linear issue URL/ID (e.g. LFE-XXXX), a GitHub issue, or a pasted error/report and asked to investigate, root-cause, or triage. Produces a structured analysis — error breakdown, hypothesis-by-class, suggested patches with code references.

Analyze Langfuse Cloud infrastructure cost structure using Metabase cost marts. Use when asked about cloud spend, AWS versus ClickHouse cost splits, cost drivers by provider/service/usage type/account, daily cost per tracing event, infra cost dashboards, or cost regressions visible in Metabase.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Shared workflow for writing Langfuse changelog entries after a feature is complete. Use when a branch is ready for merge and a changelog entry or changelog draft is needed.