exploring-llm-traces
SkillABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verif
Install
git clone https://github.com/PostHog/ai-plugin.git ~/.claude/skills/exploring-llm-tracesWhat is exploring-llm-traces?
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.
What this can do
Capabilities declared in this component's own frontmatter — not inferred.
Inherit all session tools
Declares no tool restrictions — inherits every session tool
~149 tokens of context used while enabled, before you invoke anything
Documentation
README · ~8 min readExploring LLM traces with MCP tools
PostHog captures LLM/AI agent activity as traces. Each trace is a tree of events representing a single AI interaction — from the top-level agent invocation down to individual LLM API calls.
Available tools
| Tool | Purpose |
|---|---|
posthog:query-llm-traces-list | Search and list traces; can return large multi-trace payloads |
posthog:query-llm-trace | Get a single trace by ID with full event tree |
posthog:read-data-schema | Discover custom event/person properties before filtering |
posthog:execute-sql | Ad-hoc SQL for complex trace analysis |
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just skills.
Skillssimilar to this one
All skills →claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
88.9K stars
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add
32.8K stars
session-report
Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.
32.8K stars
MCP Servers
All mcp servers →codebase-memory-mcp
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
36.7K stars
dbhub
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
3.3K stars
monitor
BetterDB MCP server - Valkey observability for Claude Code and other MCP clients
1.2K stars
Subagents
All subagents →claude-security
The dedicated Claude Security orchestrator. Hand it an unattended job — "fully scan this repository and patch what you find; I understand it will use a lot of tokens" — and it runs the whole thing itself: capturing the revision, driving the multi-agent scan through the claude-security:scan workflow,
32.8K stars
code-explorer
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development
32.8K stars
retro-analyst
Reliability pattern analyst for retrospectives, recurring-incident clustering, and systemic improvement recommendations.
1 stars
Commands
All commands →help
Get help with FiftyOne skills, understand available workflows, and troubleshoot setup issues
32.8K stars
troubleshoot-connector
Troubleshoot ZPA App Connector issues -- enrollment, connectivity, upgrades, and resource utilization.
investigate-sandbox
Investigate ZIA Sandbox file analysis -- check sandbox reports, quota, SSL prerequisite, and diagnose file block/quarantine issues.
Plugins
All plugins →chrome-devtools-mcp
Control and inspect a live Chrome browser from your coding agent. Record performance traces, analyze network requests, check console messages with source-mapped stack traces, and automate browser actions with Puppeteer.
47.9K stars
session-report
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects transcripts.
32.9K stars
context-mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
19.4K stars