Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add serejaris/kimi-skills --skill log-diagnosticgit clone --depth 1 https://github.com/serejaris/kimi-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/serejaris/kimi-skills/log-diagnostic)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/log-diagnostic"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/log-diagnostic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/log-diagnostic"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/log-diagnostic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.01159 |
| Opus 5.5 | $0.00035 | $0.00464 |
| Sonnet 5.5 | $0.00018 | $0.00232 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
log-diagnostic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log Analyzer
对日志文件进行自动化分析，提供错误聚类、频率统计和时间分布报告。
功能
- 错误聚类：将相似的错误消息归类，消除噪声（IP、UUID、数字等动态部分），识别根本问题
- 频率统计：按错误类型统计出现次数，按严重程度排序
- 时间分布：展示错误在各小时和各日期的分布，帮助定位高发时段
支持的日志格式
| 格式 | 说明 | 自动检测 |
|---|---|---|
| JSON | 每行一个 JSON 对象，含 timestamp/level/message 等字段 |
以 { 开头 |
| syslog | RFC 3164 格式，如 Jan 1 12:00:00 host proc[pid]: msg |
月份名开头 |
| Nginx | access log 或 error log 格式 | IP 开头或日期路径格式 |
使用方式
python scripts/analyze_logs.py <日志文件路径> [选项]
参数
| 参数 | 说明 | 默认值 |
|---|---|---|
log_file |
日志文件路径（必填） | - |
--format |
指定日志格式：auto/json/syslog/nginx |
auto |
--top |
显示 Top N 错误聚类 | 20 |
--output |
输出结果到 JSON 文件 | 仅终端输出 |
--level |
过滤日志级别（如 ERROR、WARN） |
所有级别 |
--since |
只分析此时间之后的日志（ISO 格式） | 不限 |
--until |
只分析此时间之前的日志（ISO 格式） | 不限 |
示例
# 自动检测格式，分析整个日志文件
python scripts/analyze_logs.py /var/log/app.log
# 指定 Nginx 格式，只看 Top 10 错误
python scripts/analyze_logs.py /var/log/nginx/error.log --format nginx --top 10
# 只分析 ERROR 级别，输出 JSON 报告
python scripts/analyze_logs.py app.log --level ERROR --output report.json
# 分析指定时间范围内的日志
python scripts/analyze_logs.py app.log --since 2024-01-01T00:00:00 --until 2024-01-02T00:00:00
输出说明
终端输出
=======================================================
日志分析报告
=======================================================
📊 概览
检测格式: json
总行数: 15,234
已解析: 15,100 (解析失败: 134)
匹配条目: 12,800
错误数: 2,341
时间范围: 2024-01-01 00:03:12 ~ 2024-01-01 23:58:45
🔴 Top 错误聚类 (共 47 类)
#1 [×523 ] Connection refused to database at 10.0.1.5:5432
首次: 2024-01-01T00:15:30 末次: 2024-01-01T23:45:12
#2 [×312 ] Timeout waiting for response from user-service after 30000ms
首次: 2024-01-01T02:10:00 末次: 2024-01-01T22:30:45
#3 [×198 ] File not found: /data/uploads/img_99421.png
首次: 2024-01-01T08:00:00 末次: 2024-01-01T20:15:33
...
⏰ 时间分布 (按小时)
00:00 █████░░░░░░░░░░░░░░░ 42
01:00 ██░░░░░░░░░░░░░░░░░░ 18
...
14:00 ████████████████████ 523
...
📅 时间分布 (按日期)
2024-01-01 ████████████████████ 2,341
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 101 lines · 88 tokens per session scan A af6a91923271
log-diagnostic is a skill published in the GitHub repository serejaris/kimi-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 1,159 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
Error Log Summarizer
Parses raw error logs and produces a concise, prioritized summary of unique issues with root cause hints.
log-analysis
A guide to reading and searching system and application logs. Logs are text records that describe what software and servers are doing.
incident-postmortem
Escribe un postmortem de incidente estructurado o revisión post-incidente. Úsalo cuando se te pida escribir un postmortem, reporte de incidente, revisión P1/P2, reporte de apagón o RCA (análisis de causa raíz). Produce un postmortem sin culpables con cronología, causa raíz, factores contribuyentes, resumen de impacto…
agent-incident-postmortem
Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective…
agent-design-review
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools…