agenttrace Session Audit

SkillAI & models

Lets your agent audit local AI coding sessions for cost, token use, failures, latency, and anomalies.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the agenttrace Session Audit skill

About this capability

Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

What this skill tells your AI

The instructions your AI receives, as published by davepoon/buildwithclaude in plugins/all-skills/skills/agenttrace-session-audit/SKILL.md and read by ahel’s review.

Use this skill when session logs need an operational read: spend, token burn, cache use, tool failures, retry loops, latency, health, anomalies, and CI gate readiness.

Workflow

  1. Prefer the installed agenttrace binary when it is available on PATH.
  2. If the binary is not available and the current directory is the luoyuctl/agenttrace repository, use cargo run -q -p agenttrace --.
  3. Start with discovery unless the user gave a specific file or directory:
agenttrace --doctor
agenttrace --overview
  1. For a fast human report, use Markdown:
agenttrace --overview -f markdown -o agenttrace-overview.md
  1. For automation or CI, use JSON or health gates:
agenttrace --overview -f json -o agenttrace-overview.json
agenttrace --overview --fail-under-health 80 --fail-on-critical --max-tool-fail-rate 15
  1. For a single recent session:
agenttrace --latest
agenttrace --latest -f json
  1. For a specific export or session directory:
agenttrace path/to/session-or-export.json
agenttrace --overview -d path/to/session-dir

Report Focus

  • Lead with the highest-risk sessions and the reason they matter.
  • Call out token/cost waste, repeated tool failures, retry loops, long gaps, and low health scores.
  • When proposing a CI gate, include the exact agenttrace command and threshold.
  • If no sessions are detected, run agenttrace --doctor and report the detected agent directories and next step.
  • Report the session capability level (Detailed, Aggregate, or Limited) before relying on latency or step evidence.
  • Treat Tool Steps as metadata-only evidence. Do not imply that Aggregate or Limited sources have a complete execution trace.

Guardrails

  • Treat prompts, code, and session contents as local/private data. Do not upload logs to external services.
  • Do not invent metrics. If a parser cannot infer cost, model, or latency, say which field is missing.
  • Do not compare missing event-level evidence as zero latency or zero failures; mark it unavailable.
  • Do not overwrite user reports unless the user asked for that output path.

Signals

GitHub stars
3k
Forks
500
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
agenttrace-session-audit
Source
github.com/davepoon/buildwithclaude