Skip to main content
skill CX Codex

signals-scout-apm — Claude Code skill: what it does, how to install

signals-scout-apm watches OpenTelemetry traces in PostHog for error-rate and latency shifts per service, new error signatures and traffic drops, and files a report only on a confirmed change.

no license 202 installs ★ 101 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add PostHog/ai-plugin --skill signals-scout-apm -a claude-code
Open on GitHub

What signals-scout-apm does

The skill reads spans stored in PostHog and scores each operation against the same window seven days earlier. Error share and p95 latency are the signal; a raw count that grows alongside traffic is not. When both numbers climb together, that is volume.

Reports go out through the report channel itself (emit_report, edit_report). A regression the inbox already tracks and that is still moving gets edited rather than filed again. There is a second, quieter lane for standing waste: repeated N+1 calls, costly query shapes, spots that would benefit from caching. It runs only while the regression lane is quiet, and the pattern has to show up both now and a week ago on a sampled trace.

Everything happens inside the PostHog Signals agent sandbox: read access to analytics, write access to the scratchpad and report channel, the apm-* tool family and the bundled exploring-apm-traces skill. A project without spans ends the run early, since the scout checks apm-services-list and the 24-hour span count first and leaves a scratchpad note for later runs. $ai_* events and the logs stream belong to other scouts and stay untouched.

What it helps with

  • catch an error-share jump on one operation after a deploy
  • compare p95 latency with the same window a week back
  • separate a real regression from a traffic spike
  • surface error signatures the service never emitted before
  • list N+1 calls and expensive queries worth caching

Example prompts for the agent

  • Run the APM scout over the last 24 hours against last week — any error or p95 regressions?
  • Check the traces for new error signatures and traffic drops per service
  • Show operations still doing N+1 calls or heavy queries that were already there a week ago

How to install signals-scout-apm

1Skills CLI (Vercel)

npx skills add PostHog/ai-plugin --skill signals-scout-apm -a claude-code

2Manually: put the files in place

~/.claude/skills/signals-scout-apm/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/signals-scout-apm/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about signals-scout-apm

How do I install signals-scout-apm in Claude Code?

Run npx skills add PostHog/ai-plugin --skill signals-scout-apm -a claude-code. The skill file lands at ~/.claude/skills/signals-scout-apm/SKILL.md.

What does signals-scout-apm do?

It tracks error share and p95 latency per operation against a baseline from a week earlier, flags fresh error signatures and traffic cliffs, and audits recurring N+1 calls, heavy queries and caching candidates.

What does the skill need in order to run?

The PostHog Signals agent sandbox, read access to analytics, write access to the scratchpad and report channel, the apm-* tools and the bundled exploring-apm-traces skill. With no spans in the project the run closes empty.

Similar skills

All skills for DevOps and infrastructure →

From the same set82

The whole set →
exploring-mcp-sessions exploring-mcp-sessions investigates PostHog MCP sessions to inspect tool call sequences, agent intent, and run failures. CX Codex +1 202installs exploring-mcp-tool-quality exploring-mcp-tool-quality reads PostHog MCP analytics to rank tools by failure share, latency and reach, then drills into the ones that break. CX Codex +1 202installs exploring-mcp-intent-clusters exploring-mcp-intent-clusters analyzes PostHog MCP agent intent clusters to reveal what agents attempt to do, tool failure patterns, and semantic routing competition. CX Codex +1 202installs managing-reminders managing-reminders is a Claude Code skill that creates and manages private PostHog reminders with one-time or repeating schedules. It can nudge you about a task or resource. CX Codex +1 202installs exploring-mcp-tool-usage exploring-mcp-tool-usage — a routing skill for PostHog MCP analytics: it offers a menu of questions about tool calls, then hands you to the query that answers it. CX Codex +1 200installs checking-deploy-timing checking-deploy-timing tells you when a commit or PR reached prod-us or prod-eu by reading PostHog's hidden deploy annotations and matching them against the merge commit on GitHub. CX Codex +1 200installs setting-up-a-custom-rest-source setting-up-a-custom-rest-source — a skill for Claude Code and Codex that links arbitrary REST APIs to the PostHog data warehouse using a JSON manifest. Activates when importing custom endpoints without native connectors. CX Codex +1 199installs exploring-ai-failures exploring-ai-failures reads real production traces from PostHog and returns a ranked list of the ways your LLM feature breaks. CX Codex +1 198installs

Project sponsors

Companies that keep this analytics open