Session clock-time analyzer. Reads the foundry plugin''s timings.jsonl and invocations.jsonl logs (written by task-log.js) and produces a per-session and per-skill wall-time breakdown — local-tool work vs subagent spawns vs Skill invocations vs AskUserQuestion idle vs main-loop reasoning residual. Useful for answering "why did /oss:resolve run 30 minutes?" or "what eats clock time in /develop:fix?". Pure log read — no instrumentation, no skill edits, no LLM calls. TRIGGER when: user asks where wall-clock time goes during a skill/session, why a skill is slow, what dominates total runtime, or wants a per-skill rollup over a recent window; phrases: "where does time go", "why so slow", "profile last session", "clock breakdown", "session timing". SKIP: token/cost questions (model field is null in current logs — out of scope); per-line Python perf (use foundry:perf-optimizer); known failure or hang (use /foundry:investigate).
$npx -y skills add borda/ai-rig --skill profileInstalls into the current project.
Run `npx skills use "https://github.com/borda/ai-rig" --skill "borda/ai-rig/profile"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/borda/ai-rig" that are relevant to the current task. Run `npx skills add "https://github.com/borda/ai-rig"` and select the relevant skills, then follow their instructions.