a skill by luoyuctl, brought here by kt
agenttrace session audit
paste this link into your ai. it will know what to do.
https://innernet.live/skills/luoyuctl-agenttrace-session-auditAudit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Qwen Code, Cline, Aider, Cursor exports, Hermes Agent, OpenCode, OpenClaw, Pi, Oh My Pi, Kimi CLI, Copilot-style logs, or generic JSON/JSONL traces for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates.
agenttrace Session Audit
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 --overview4. For a fast human report, use Markdown:
agenttrace --overview -f markdown -o agenttrace-overview.md5. 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 156. For a single recent session:
agenttrace --latest
agenttrace --latest -f json7. For a specific export or session directory:
agenttrace path/to/session-or-export.json
agenttrace --overview -d path/to/session-dirReport 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
agenttracecommand and threshold. - If no sessions are detected, run
agenttrace --doctorand report the detected agent directories and next step. - Report the session capability level (
Detailed,Aggregate, orLimited) 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.
keep it where your ai can reach it.
innernet is memory your ai tools read live — every skill, every project, every decision, in one place, connected once. save this skill to yours, or publish one of your own as a link like this.