From b0ea47009c5851d7eac544183312eb522c188a24 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=BC=A0=E5=AE=89=E5=93=B2?= Date: Sun, 3 May 2026 06:46:33 +0800 Subject: [PATCH 1/2] Add agenttrace session audit skill --- README.md | 1 + .../agenttrace-session-audit/SKILL.md | 62 +++++++++++++++++++ 2 files changed, 63 insertions(+) create mode 100644 skills/development/agenttrace-session-audit/SKILL.md diff --git a/README.md b/README.md index 2cf2886..48c10d6 100644 --- a/README.md +++ b/README.md @@ -203,6 +203,7 @@ Agent Skills are portable, [open standard](https://agentskills.io/home), version ### Development +- [agenttrace Session Audit](https://github.com/Code-and-Sorts/awesome-copilot-agents/tree/main/skills/development/agenttrace-session-audit/SKILL.md) - Audit local AI coding-agent sessions for token/cost usage, tool failures, latency, anomalies, health, diffs, and CI gates. - [Playwright CLI](https://github.com/microsoft/playwright-cli/blob/main/skills/playwright-cli/SKILL.md) - Automate browser interactions, test web pages and work with Playwright tests. - [Frontend Design](https://github.com/anthropics/skills/blob/main/skills/frontend-design/SKILL.md) - Create distinctive, production-grade frontend interfaces with high design quality. - [Webapp Testing](https://github.com/anthropics/skills/blob/main/skills/webapp-testing/SKILL.md) - Toolkit for interacting with and testing local web applications using Playwright. diff --git a/skills/development/agenttrace-session-audit/SKILL.md b/skills/development/agenttrace-session-audit/SKILL.md new file mode 100644 index 0000000..e8d2a75 --- /dev/null +++ b/skills/development/agenttrace-session-audit/SKILL.md @@ -0,0 +1,62 @@ +--- +name: agenttrace-session-audit +description: Audit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Aider, Cursor, OpenCode, Kimi, Copilot-style, or generic JSON/JSONL sessions for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates. +license: MIT +metadata: + short-description: Audit AI agent session health +--- + +# 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 `go run ./cmd/agenttrace`. +3. Start with discovery unless the user gave a specific file or directory: + +```bash +agenttrace --doctor +agenttrace --overview +``` + +1. For a fast human report, use Markdown: + +```bash +agenttrace --overview -f markdown -o agenttrace-overview.md +``` + +1. For automation or CI, use JSON or health gates: + +```bash +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: + +```bash +agenttrace --latest +agenttrace --latest -f json +``` + +1. For a specific export or session directory: + +```bash +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. + +## 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 overwrite user reports unless the user asked for that output path. From c610c3f88db028d9cec2fa0b1d1d5d012e306251 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=BC=A0=E5=AE=89=E5=93=B2?= Date: Sun, 17 May 2026 17:02:21 +0800 Subject: [PATCH 2/2] Refresh agenttrace skill coverage --- skills/development/agenttrace-session-audit/SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/skills/development/agenttrace-session-audit/SKILL.md b/skills/development/agenttrace-session-audit/SKILL.md index e8d2a75..800cfa0 100644 --- a/skills/development/agenttrace-session-audit/SKILL.md +++ b/skills/development/agenttrace-session-audit/SKILL.md @@ -1,6 +1,6 @@ --- name: agenttrace-session-audit -description: Audit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Aider, Cursor, OpenCode, Kimi, Copilot-style, or generic JSON/JSONL sessions for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates. +description: Audit 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, OpenCode, OpenClaw, Pi, Kimi CLI, Copilot-style, or generic JSON/JSONL sessions for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates. license: MIT metadata: short-description: Audit AI agent session health