Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/shanananana/deepticketnpx agentmods add skills/shanananana/deepticket/log-queryWrote 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/shanananana/deepticket/log-query)<a href="https://agentmods.dev/skills/shanananana/deepticket/log-query"><img src="https://agentmods.dev/badge/skills/shanananana/deepticket/log-query.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00564 |
| Opus 5 | $0.00017 | $0.00282 |
| Sonnet 5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
log-query 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 7d 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.
What it actually says
日志查询 Skill
对接只读日志/指标查询。生产环境请替换为你们真实 API。
ad_agent 项目（workspace/project/ad-agent）
data/campaign_metrics.log 与 data/budget_audit.log 已在本地预生成，分析时直接查询，不要运行 generate。
仅当上述 log 文件不存在或为空时，才允许执行：
python scripts/generate_campaign_data.py --start 2026-07-24 --end 2026-08-01
正常分析流程（只读）：
cd workspace/project/ad-agent
python scripts/query_campaign_metrics.py --start 2026-07-24 --end 2026-07-27
python scripts/query_campaign_metrics.py --start 2026-07-28 --end 2026-08-01
python scripts/query_campaign_metrics.py --album-id album_bad_001 --start 2026-07-24 --end 2026-08-01
cat data/budget_audit.log
日志文件：
| 文件 | 说明 |
|---|---|
data/campaign_metrics.log |
日粒度 ROI/spend（JSONL） |
data/budget_audit.log |
预算变更审计（2026-07-28 起低 ROI 计划被放大） |
输出含 --- key finding --- 时，结合 budget_audit.log、config/campaigns.yaml 与 budget_allocator.py 做归因。
本地刷新 log（运维/演示用，不在 Agent 对话里跑）：项目根目录 ./scripts/refresh_ad_agent_logs.sh
适用场景
- 工单附带
logs字段或指标问题（ROI 下降、消耗异常） - 按 traceId / 时间范围查 ERROR
- 对比故障前后两个时间窗口
生产接入指引
- 在
skills/log-query/scripts/添加查询脚本（或 MCP） - 填写下方平台 API、索引名、字段规范
- Agent 应优先 只读查询，不要删除或修改日志
占位 API（请替换）
- 平台：
<YOUR_LOG_PLATFORM> - 查询入口：
<YOUR_LOG_QUERY_ENDPOINT> - 鉴权：环境变量
LOG_QUERY_TOKEN（勿提交 Git）
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.
- 7d ago First seen · 58 lines · 35 tokens per session scan A 275df12ae2b4
log-query is a skill published in the GitHub repository shanananana/deepticket (60 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 564 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
Incident Response Planner
Analyze an infrastructure incident alert and produce a structured response plan plus an executable on-call runbook. Use for incident, alert, on-call, and runbook requests.
incident-commander
Autonomous incident detection, root-cause analysis, and self-healing for Linux/Docker production environments. Activate when the user mentions: server down, high CPU, memory leak, disk full, service crash, deployment failure, alert firing, on-call page, or any infrastructure emergency. Also activates on scheduled…
dsh-k8s-diagnosis
Diagnose live Kubernetes failures (CrashLoopBackOff, OOMKilled, NodeNotReady, ImagePullBackOff, Network/CNI failures, HPA starvation, DNS failures, pending pods) with an evidence-first procedure: capture context, collect signals (events/status/logs), rank falsifiable hypotheses, verify one variable at a time, fix with…
design-incident-response
Use when creating or improving an incident response process for a production system or operational team.
kube-medic
Kubernetes Cluster Triage & Diagnostics — instant AI-powered incident triage via kubectl.
k8s-security-incident
A Kubernetes security-incident response guide. Kubernetes runs and manages containers, and a security incident is an event such as unauthorized access or harmful activity affecting that environment.