Borrowing it
Nothing to install: this file belongs to MT-gar/Nexus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MT-gar/Nexus/main/.claude/skills/devflow/agents/triage/SKILL.mdgit clone --depth 1 https://github.com/MT-gar/NexusWrote 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/mt-gar/nexus/triage)<a href="https://agentmods.dev/skills/mt-gar/nexus/triage"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/triage/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/mt-gar/nexus/triage"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/triage.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 | $0.00052 | $0.00960 |
| Opus 5.5 | $0.00021 | $0.00384 |
| Sonnet 5.5 | $0.00010 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
defect-aggregation 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.
What it actually says
Skill:defect-aggregation(缺陷聚合)
1. 业务用途
将来自多个渠道(Issue 工单、错误日志、用户反馈、监控告警)的缺陷信息聚合为规范缺陷看板:自动相似度去重(重复上报合并,保留来源证据),按严重级别定级,为 RCA 提供干净、无冗余的输入。对应 8 步闭环的"任务输入"环节。
2. 输入输出 Schema
输入:
{ title: string, description?: string, source: "issue"|"log"|"user_feedback"|"alert"|"manual",
severity?: "critical"|"high"|"medium"|"low", dedup_threshold?: number (0-1,默认 0.6) }
输出(ingest_defect):
{ defect_id: string, merged: boolean,
merged_into?: string, // merged=true 时:被合并到的规范缺陷 ID
similarity?: number } // 与规范缺陷的相似度
输出(分诊结论消息):
{ 缺陷清单: Array<{ defect_id, title, severity, merged }>,
建议: { 待处理缺陷数, 优先级排序 } }
3. 调用触发条件
- manager 创建"缺陷聚合"任务(分配给我)
- 新增 issue/日志/告警需要入库(可直接调用)
4. 依赖工具
| 工具 | 用途 |
|---|---|
ingest_defect |
多源录入 + 相似度去重(Jaccard 归一化相似度 ≥ 阈值自动合并) |
list_defects |
缺陷看板查询(含按 status/severity/source 过滤) |
update_defect |
定级分诊(status=triaged)、后续环节回写(rca_task_id/fix_task_id) |
claim_task / update_task / wait_for_work |
任务生命周期(基础设施) |
5. 失败重试 / 降级机制
- 录入字段缺失(无 title)→ 拒绝并报告来源,跳过该条
- 去重误判(merged 但实为不同缺陷)→ 用
ingest_defect(dedup_threshold=0)强制新建,并报告 manager - 去重算法为确定性 Jaccard 相似度,无外部依赖;生产可升级 embedding 向量去重(接口不变)
- 降级:聚合服务不可用时直接以任务 description 作为缺陷录入依据
6. 安全权限边界
- ✅ 允许:
ingest_defect/list_defects/update_defect(仅限定级与关联回写) - ❌ 禁止:创建/认领非聚合类任务、审批操作、发布操作、直接修改他人缺陷的 severity 之外字段
- ⚠️ 缺陷内容可能含用户敏感信息(日志摘录),消息中只传摘要与 ID,不传全文
7. 多场景复用价值
- 缺陷聚合(本场景:研发缺陷)
- 告警降噪(监控告警去重合并 — 零人工运维方向)
- 客服工单聚合(多渠道工单去重分级 — 智能客服方向)
- 金融风控信号聚合(风险信号去重降噪)
8. 与多 Agent 协作链路
devflow-manager ──聚合任务──▶ triage-agent ──分诊结论──▶ devflow-manager ──RCA 任务──▶ rca-agent
只与 manager 通信;产出(缺陷看板 + 分诊结论)是后续所有环节的输入真相源。
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 · 73 lines · 52 tokens per session scan A fbcabb058a9b
defect-aggregation is a skill published in the GitHub repository MT-gar/Nexus (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 960 once invoked, about $0.0002 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 2026-09-20.
Other skills, from other repositories
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
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…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…