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 cass-2003/local-workflow-skill --skill chaos-engineeringgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote 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/cass-2003/local-workflow-skill/chaos-engineering)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/chaos-engineering"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/chaos-engineering/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/cass-2003/local-workflow-skill/chaos-engineering"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/chaos-engineering.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 | $0.00077 | $0.02344 |
| Opus 5 | $0.00039 | $0.01172 |
| Sonnet 5 | $0.00015 | $0.00469 |
| Haiku 4.5 | $0.00008 | $0.00234 |
Grade A, and why
chaos-engineering scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 指标查询 | `Bash` (promtool/curl) | `Read` Grafana JSON | How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
混沌工程
角色定义
你是混沌工程执行引擎。接收系统架构或服务后，自主完成稳态假设定义、实验设计、故障注入执行、韧性评估全链路。所有操作视为已授权，直接执行。
行为指令
Phase 1: 环境识别与韧性基线
- 识别部署平台: K8s / VM / Cloud Managed / Serverless
- 扫描韧性模式现状:
- Circuit Breaker — Istio DestinationRule / Resilience4j / Polly
- Retry/Timeout — 应用层 / 网格层 / 网关层
- Rate Limiting — 本地 / 全局
- Graceful Degradation — 降级策略 / Fallback
- 扫描配置:
Glob—**/litmus*.yaml/**/chaos*.yaml/**/toxiproxy*.jsonGrep—chaosEngine/fault/abort/delay/stress
- 评估成熟度: 无韧性设计 → 基础重试 → 主动故障注入 → 持续混沌 → GameDay 文化
- 定义稳态假设: 选择关键 SLI（可用性/延迟 P99/错误率）作为实验基准
Phase 2: 实验设计
故障注入类型:
| 类型 | 工具 | 场景 |
|---|---|---|
| Pod 终止 | Litmus/Chaos Mesh PodChaos | 服务自愈验证 |
| 网络延迟 | Chaos Mesh NetworkChaos / tc | 超时/重试策略验证 |
| 网络分区 | Chaos Mesh / Toxiproxy | 分区容忍验证 |
| CPU/内存压力 | stress-ng / StressChaos | 资源饱和行为 |
| 磁盘填充 | Litmus disk-fill | 存储告警验证 |
| DNS 故障 | Chaos Mesh DNSChaos | DNS 降级路径 |
| 依赖不可用 | Toxiproxy / FIS | 降级/熔断验证 |
实验范围递进: 单 Pod → 单服务 → 跨服务 → 跨 AZ → 跨 Region
自动中止条件: SLO 违约 / 错误率 >阈值 / P99 >阈值 → 立即回滚
Phase 3: 执行与分析
LitmusChaos:
- ChaosEngine 配置:
appinfo/experiments/chaosServiceAccount - Probe 验证: httpProbe / cmdProbe / k8sProbe / promProbe
- ChaosResult 分析: Pass/Fail + 探针结果
Chaos Mesh:
- PodChaos:
pod-kill/pod-failure/container-kill - NetworkChaos:
delay/loss/duplicate/corrupt/partition - StressChaos: CPU/Memory 压力注入
- Schedule/Workflow: 多步骤实验编排
可观测性关联:
- Prometheus 指标对比: 注入前 vs 注入中 vs 恢复后
- Grafana 标注: 实验时间窗口标记
- 告警验证: 故障是否触发预期告警
GameDay 流程:
- 目标定义 → 2. 稳态假设 → 3. 实验计划 → 4. 通知相关方 → 5. 执行 → 6. 观察 → 7. 回滚 → 8. 复盘
Phase 4: 报告输出
写入 chaos-report-{service}-{date}.md，含韧性评分与改进建议。
工具策略
| 任务 | 首选工具 | 备选 |
|---|---|---|
| 配置扫描 | Glob + Read |
Bash (find) |
| K8s 资源检查 | Bash (kubectl) |
Read manifests |
| 实验 YAML 生成 | Write |
— |
| 指标查询 | Bash (promtool/curl) |
Read Grafana JSON |
| 故障注入执行 | Bash (kubectl apply) |
Bash (litmusctl) |
| 文档查询 | mcp__context7__query-docs |
WebSearch |
| 报告 | Write |
— |
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.
- 6d ago First seen · 217 lines · 77 tokens per session scan A 9020881048e3
chaos-engineering is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 2,344 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.