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 s14-experiment-designgit 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/s14-experiment-design)<a href="https://agentmods.dev/skills/dungnotnull/hybrid-harness-chaos-process-prm/s14-experiment-design"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s14-experiment-design/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/s14-experiment-design"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s14-experiment-design.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 | $0.00116 | $0.02556 |
| Opus 5 | $0.00058 | $0.01278 |
| Sonnet 5 | $0.00023 | $0.00511 |
| Haiku 4.5 | $0.00012 | $0.00256 |
Grade A, and why
chaos-experiment-design 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 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.
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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chaos Experiment Design
Purpose
Produce complete, safe, runnable chaos experiments following the hypothesis-driven scientific method. Every experiment has a clear hypothesis, defined steady state, bounded blast radius, and automated abort conditions.
Input Contract
| Input | Source | Required |
|---|---|---|
| PRD / service criticality analysis | s01 (workflow_context) | Yes |
| Pipeline YAML (chaos step location) | s04 output | Yes |
| Service definitions (target services) | s05 output | Yes |
| Blast radius budget per environment | s01 (env tier table) | Yes |
| Feature flag chaos gate config | s08 output | No (recommended) |
| Risk tolerance preferences | s02 taste (risk_tolerance) | Yes |
Output Contract
| Output | Destination | Format |
|---|---|---|
| ChaosExperiment manifest | .commandcode/artifacts/experiment-<name>.yaml |
Litmus YAML |
| ChaosEngine manifest | .commandcode/artifacts/engine-<name>.yaml |
Litmus YAML |
| Experiment design checklist | s13 (hypothesis input) | Markdown |
| Fault taxonomy map | s16, s17 (fault selection) | Reference |
| Pipeline chaos step config | s04 (pipeline update) | YAML |
| Experiment context | workflow_context.artifacts | YAML object |
Prerequisites
- LitmusChaos / Harness Chaos Engineering installed in target cluster
- Target namespace and service identified
- Steady state defined (see chaos/04-steady-state-definition)
- Observability stack active (metrics flowing before experiment starts)
- Rollback plan documented
- Blast radius approved for target environment (see CLAUDE.md env tiers)
Experiment Design Framework (5 Steps)
1. HYPOTHESIS → "If X fails, then Y should happen, and Z metric stays within N"
2. STEADY STATE → Baseline metrics confirmed healthy before injection
3. FAULT → Specific fault, target scope, duration, intensity
4. OBSERVE → Monitor during injection — did system behave as expected?
5. LEARN → Document findings, fix gaps, update runbooks
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 · 309 lines · 116 tokens per session scan A 559838d89d25
chaos-experiment-design is a skill published in the GitHub repository dungnotnull/hybrid-harness-chaos-process-prm (19 stars, last pushed 3mo ago), licensed MIT. It adds 116 tokens to every session and 2,556 once invoked, about $0.0006 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
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.