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 dungnotnull/hybrid-harness-chaos-process-prm --skill s18-infrastructure-faultsgit clone --depth 1 https://github.com/dungnotnull/hybrid-harness-chaos-process-prmWrote 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/dungnotnull/hybrid-harness-chaos-process-prm/s18-infrastructure-faults)<a href="https://agentmods.dev/skills/dungnotnull/hybrid-harness-chaos-process-prm/s18-infrastructure-faults"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s18-infrastructure-faults/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/dungnotnull/hybrid-harness-chaos-process-prm/s18-infrastructure-faults"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s18-infrastructure-faults.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 | $0.00101 | $0.03259 |
| Opus 5 | $0.00051 | $0.01630 |
| Sonnet 5 | $0.00020 | $0.00652 |
| Haiku 4.5 | $0.00010 | $0.00326 |
Grade C, and why
chaos-infrastructure-faults scanned grade C 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
kubectl exec -it <POD_NAME> -- rm -rf /var/lib/data/diskfill/* How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chaos Infrastructure Faults (s16)
Purpose
Produce complete, safe, runnable infrastructure-level chaos experiments that test system resilience against node failures, resource exhaustion, disk pressure, and cloud provider outages.
Prerequisites
- Chaos experiment designs from s14 (Experiment Design)
- Delegate configured from s06 (Delegate Management)
- Kubernetes cluster access for infrastructure operations
- Steady state defined from s17 (Steady State)
- Blast radius approved from s16 (Blast Radius Control)
- Observability active and monitoring targets
Input Contract
| Input | Source | Required |
|---|---|---|
| Experiment design framework | s12 (workflow_context.artifacts) | Yes |
| Blast radius constraints | s14 output | Yes |
| Infrastructure topology (nodes, AZs, regions) | s01 or s05 context | Yes |
| Cloud provider (AWS/GCP/Azure) | s01 context | Yes |
| Risk tolerance (prod limits) | s02 taste (risk_tolerance) | Yes |
| Delegate/cluster access info | s06 output | Yes |
Output Contract
| Output | Destination | Format |
|---|---|---|
| Infra fault ChaosExperiments | .commandcode/artifacts/experiment-infra-<fault>.yaml |
Litmus YAML |
| Infra fault ChaosEngines | .commandcode/artifacts/engine-infra-<fault>.yaml |
Litmus YAML |
| Cloud-specific fault configs | .commandcode/artifacts/experiment-<cloud>-<fault>.yaml |
YAML |
| Recovery runbook | s18 (game day), s25 (postmortem) | Markdown |
| Infra fault risk assessment | s21 (alerting context) | YAML |
Infrastructure Fault Catalog
| Fault | LitmusChaos Name | Risk Level | Min Replicas | Prod Safe? |
|---|---|---|---|---|
| Node CPU Hog | node-cpu-hog | Medium | 3+ nodes | With 30% max |
| Node Memory Hog | node-memory-hog | Medium | 3+ nodes | With 30% max |
| Node Drain | node-drain | High | 3+ nodes | With PDB + approval |
| Node Restart | node-restart | Critical | 3+ nodes | No (staging only) |
| Disk Fill | disk-fill | High | N/A | With ephemeral only |
| Disk Loss (EBS) | ebs-loss | Critical | N/A | No (staging only) |
| EC2 Stop (AWS) | ec2-stop | Critical | N/A | No (staging only) |
| AZ Failure (AWS) | — (composite) | Extreme | Multi-AZ | Game day only |
| GCP VM Stop | gcp-vm-stop | Critical | N/A | No (staging only) |
| Azure VM Stop | azure-vm-stop | Critical | N/A | No (staging only) |
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.
- 12d ago First seen · 428 lines · 101 tokens per session scan C f59f17709099
chaos-infrastructure-faults is a skill published in the GitHub repository dungnotnull/hybrid-harness-chaos-process-prm (19 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 3,259 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.