AGENT SKILL

agenttrace-session-audit

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

License 许可
MIT
最近更新
2026-06-13
Stars
★ 0
Forks
0

01 前言 Front Matter

name
agenttrace-session-audit
risk
safe
tags
[ "ai-coding", "observability", "cost-tracking", "session-analysis" ]
tools
[ "claude", "cursor", "gemini", "codex-cli" ]
author
luoyuctl
source
community
license
MIT
category
development
date_added
2026-05-10
description
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
source_repo
luoyuctl/agenttrace
source_type
community
license_source
https://github.com/luoyuctl/agenttrace/blob/master/LICENSE

03 SKILL.md 正文

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
  • repeated edits around the same files without a clear reason
  • lower cost that came from skipping necessary exploration

Step 5: Add Automation Gates

For CI or repeatable team workflows, use JSON output or health thresholds.

agenttrace --overview -f json -o agenttrace-overview.json
agenttrace --overview --fail-under-health 80 --fail-on-critical --max-tool-fail-rate 15

Tune thresholds to the project. A strict gate is useful for critical workflows; a reporting-only command is better while the team is learning its baseline.

Examples

Quick Local Review

agenttrace --overview
agenttrace --latest

Use this after a long coding-agent run to decide whether the next prompt should split the task, avoid a failing tool path, add missing tests, or reset context.

CI Health Check

agenttrace --overview --fail-under-health 80 --fail-on-critical

Use this when agent session logs are available in CI and the team wants a simple guard against critical anomalies or unhealthy runs.

Best Practices

  • Start with --doctor when session discovery is uncertain.
  • Report missing fields plainly; do not invent cost, model, latency, or health data.
  • Treat prompts, code, and session contents as private local data.
  • Prefer JSON output for automation and Markdown output for human review.
  • Use trace metrics for process failures and diff/reference review for semantic drift.

Limitations

  • agenttrace can only analyze logs that are present locally or provided as exports.
  • Some agents do not expose enough fields to infer cost, model, cache use, or latency.
  • Healthy trace metrics do not prove the final code is correct; still run tests and review diffs.
  • CI gates should start as advisory until the team understands normal baseline behavior.

Security & Safety Notes

  • Do not upload private session logs to external services unless the user explicitly approves it.
  • Do not overwrite user reports unless they requested that exact output path.
  • Avoid printing secrets found in prompts, tool output, environment variables, or logs.

Common Pitfalls

  • Problem: No sessions are found. Solution: Run agenttrace --doctor, then point agenttrace at the exported file or log directory.

  • Problem: A run looks cheap and fast but produced the wrong refactor. Solution: Compare the session against a prior attempt or known-good diff; cost metrics alone will miss semantic drift.

  • Problem: CI fails too often after adding a health gate. Solution: Start with JSON or Markdown reporting, inspect normal baselines, then tighten thresholds gradually.

Related Skills

  • @langfuse - Use for production LLM application tracing and evaluation.
  • @observability-engineer - Use for broader service monitoring, SLOs, and incident workflows.

04 同仓库更多 Skills

haresh-sai06
haresh-sai06/SapSynk-AI

youtube-full

Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private/age-restricted videos.

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

x-twitter-growth

X/Twitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X/Twitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

write-a-skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

workflow-builder

Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

webinar-marketing

When the user wants to plan, promote, run, or improve a webinar or virtual event to generate and convert demand. Use when the user mentions 'webinar,' 'virtual event,' 'online event,' 'live demo,' 'virtual summit,' 'workshop,' 'masterclass,' 'fireside chat,' 'roundtable,' 'registration funnel,' 'show-up rate,' 'attendance rate,' 'webinar promotion,' 'webinar follow-up,' or 'on-demand webinar.' Also use when they have a webinar that isn't converting — low registrations, low show-up, or attendees who don't buy — and want to diagnose and fix it. Covers the full funnel: registration, promotion, show-up, live engagement, live-to-close, and post-event nurture. Distinct from launch-strategy (full product launches) and email-sequence (lifecycle nurture) — this is the end-to-end webinar/event motion. NOT for in-person field events logistics, and NOT for generic lifecycle email (use email-sequence).

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

vpe-advisor

VP of Engineering advisory for startups: delivery throughput (DORA 4 metrics + bottleneck identification), engineering hiring funnel (sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap), engineering team structure (squad/tribe/chapter design + tech-lead manager-trigger thresholds), and production discipline (on-call, deployment cadence, postmortem culture). Use when sprint velocity is dropping, eng hiring is broken, team structure is unclear, or deciding when to add a tech-lead manager. NOT a CTO skill (which owns architecture) — VPE owns delivery operations and how the team ships.

★ 0