agent-step-toolkit

Run and debug LangGraph.js conversations: /run-langgraph-conversation executes a single- or multi-turn test conversation against the local dev server — finding the running instance that serves the project on any port before starting one — and captures the thread, with an opt-in raw SSE streaming capture (token/handoff/custom event order); /follow-langgraph-conversation investigates any thread end-to-end: locates the instance that OWNS the thread, inventories the available monitoring sources (dev-server checkpoint history, LangSmith traces incl. EU/self-hosted endpoints, process/container logs), reads handoff signals and step-batch tool envelopes, and produces root-cause analysis. Discovers ports, owning instances, graph ids, and LangSmith credentials/endpoint from the project's own config and the live environment (langgraph.json, dev script, docker-compose, .env, running processes/containers).

2 skills

LangSmith-parity observability over Kafka for any LangGraph.js / LangChain.js agent: /add-kafka-observability installs or upgrades a vendored src/observability/ library that attaches a BaseTracer subclass globally through two redundant paths — the configure hook plus the configure-slot LangSmith's own tracer occupies, so it attaches even on platform runtimes that sever async-context ancestry (one startup() call, zero per-node instrumentation) — and publishes EVERY traced run — graph invocation, LangGraph nodes, LLM calls with full prompts/outputs/token usage, tool runs, errors, trace hierarchy, plus opt-in backend HTTP call runs via the traceBackendCall helper — as start/end events to a Kafka topic (standard envelope keyed by event id, thread_id correlation, zod-validated, secret-redacted, 512KB-truncated) over a bounded non-blocking fire-and-forget producer (librdkafka, acks=all, idempotent, bounded shutdown). By default EVERY run is emitted (full LangSmith parity); apps that have payload-verified which of their runs duplicate root/llm/tool content can opt into run filtering (KAFKA_RUN_FILTER_MODE=allow|deny + run_type:name globs, the name side also matching metadata.langgraph_node; the root run always survives — it carries the full invocation input/final state and is the turn-boundary marker for timeline consumers). Disabled by default (KAFKA_ENABLED); runs alongside LangSmith for parallel validation so LangSmith can be unplugged with no code change. Conversation content (prompts, completions, graph state, tool params) is masked by a policy the APPLICATION supplies — startup({ contentMask }) plus digit/deep-walk primitives that compose with a domain masker the project already owns, covering both numeral runs and digits SPOKEN as words (Greek + English packs, inflection/accent-tolerant — how PINs and OTPs actually arrive on a voice channel); the library ships the SEAM, not the policy (which digits are a tax id and which an order reference is a fact about the app's

1 skill

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

Use Alibaba Open Code Review from local Codex.

2 skills