| name | agenttrace-session-audit |
| description | Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates. |
| category | development |
| risk | safe |
| source | community |
| source_repo | luoyuctl/agenttrace |
| source_type | community |
| date_added | 2026-05-10 |
| author | luoyuctl |
| tags | ["ai-coding","observability","cost-tracking","session-analysis"] |
| tools | ["claude","cursor","gemini","codex-cli"] |
| license | MIT |
| license_source | https://github.com/luoyuctl/agenttrace/blob/master/LICENSE |
agenttrace Session Audit
Overview
Use this skill to inspect local AI coding-agent sessions with
agenttrace. It focuses on the process
behind a run: token and cost spikes, tool failures, retry loops, latency gaps,
anomalies, health scores, and session-to-session diffs.
agenttrace is local-first and reads session logs from tools such as Claude Code,
Codex CLI, Gemini CLI, Aider, Cursor exports, OpenCode, Qwen Code, Kimi, and
generic JSON or JSONL traces.
When to Use This Skill
- Use when a user asks why an AI coding run was slow, expensive, shallow, or unreliable.
- Use when reviewing local agent logs before retrying a failed or suspicious task.
- Use when building a lightweight CI health gate for AI-assisted coding sessions.
- Use when comparing two attempts and looking for changed tool paths, retries, or cost patterns.
How It Works
Step 1: Discover Available Sessions
Prefer an installed agenttrace binary when it is available on PATH. If the
current repository is luoyuctl/agenttrace, use go run ./cmd/agenttrace
instead.
agenttrace --doctor
agenttrace --overview
If no sessions are detected, report the directories checked by --doctor and
ask for the exported session file or log directory.
Step 2: Produce a Human-Readable Audit
Use Markdown when the user wants a concise report they can inspect or share.
agenttrace --overview -f markdown -o agenttrace-overview.md
In the report, lead with the highest-risk sessions and explain why they matter:
critical anomalies, repeated tool failures, token or cost waste, long latency
gaps, low health scores, and suspiciously shallow sessions.
Step 3: Inspect One Session or Directory
Use the latest session for a quick check, or pass an explicit export path when
the user provides one.
agenttrace --latest
agenttrace --latest -f json
agenttrace path/to/session-or-export.json
agenttrace --overview -d path/to/session-dir
Step 4: Compare Attempts When Semantics Matter
Token and latency metrics can look healthy even when an agent confidently takes
the wrong implementation path. When the risk is semantic drift, pair the trace
audit with a diff against a previous or known-good attempt.
Look for:
- changed files or commands that diverge from the intended task
- missing tests or verification steps compared with the reference attempt
