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 s15-hypothesis-validationgit 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/s15-hypothesis-validation)<a href="https://agentmods.dev/skills/dungnotnull/hybrid-harness-chaos-process-prm/s15-hypothesis-validation"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s15-hypothesis-validation/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/s15-hypothesis-validation"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s15-hypothesis-validation.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 | $0.00098 | $0.02918 |
| Opus 5 | $0.00049 | $0.01459 |
| Sonnet 5 | $0.00020 | $0.00584 |
| Haiku 4.5 | $0.00010 | $0.00292 |
Grade A, and why
chaos-hypothesis-validation 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 11d 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.
curl -f http://<SERVICE>.<NAMESPACE>.svc.cluster.local/health && echo "PASS" || echo "FAIL" 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 Hypothesis Validation
Purpose
Transform vague "what if X breaks?" questions into precise, falsifiable hypotheses with measurable success criteria — making chaos experiments scientifically rigorous rather than random fault injection.
Prerequisites
- Chaos experiment designs from s14 (Experiment Design)
- Steady state baselines from s17 (Steady State Definition)
- Target service metrics identified
- Observability stack active (Prometheus, Grafana)
- Performance baselines from s13 (Performance Testing)
Input Contract
| Input | Source | Required |
|---|---|---|
| Experiment designs (ChaosEngine YAML) | s12 (workflow_context.artifacts) | Yes |
| Steady state baselines | s15 output | Yes |
| Service SLIs/SLOs from PRD | s01 context | Yes |
| Blast radius constraints | s14 output | Yes |
| Observability metrics available | s20 output | No |
Output Contract
| Output | Destination | Format |
|---|---|---|
| Hypothesis document per experiment | .commandcode/artifacts/hypothesis-<name>.md |
Markdown |
| Validation script (Python) | .commandcode/artifacts/hypothesis-validator.py |
Python |
| Pre-experiment check script | .commandcode/artifacts/pre-chaos-check.sh |
Bash |
| Hypothesis tracker table | s24, s25 (scoring + learning) | Markdown table |
| Acceptance criteria YAML | s18 (game day gates) | YAML |
The Chaos Hypothesis Formula
HYPOTHESIS STATEMENT:
"When [FAULT DESCRIPTION] is applied to [TARGET SCOPE] for [DURATION],
the [SYSTEM/SERVICE] will [EXPECTED BEHAVIOR],
as evidenced by [MEASURABLE METRIC] remaining [CONDITION] (e.g., below 5%, above 99.9%)."
ACCEPTANCE CRITERIA:
- [METRIC_1]: [OPERATOR] [THRESHOLD] (e.g., error_rate <= 5%)
- [METRIC_2]: [OPERATOR] [THRESHOLD] (e.g., p99_latency <= 2000ms)
- [FUNCTIONAL_CHECK]: [PASS/FAIL criterion]
NULL HYPOTHESIS (what failure looks like):
"The system will fail to meet [METRIC] when [FAULT] is applied."
Hypothesis Tiers
| Tier | Scope | Hypothesis Type | Example |
|---|---|---|---|
| Unit | Single pod | Component resilience | "Killing one pod, service stays available" |
| Service | One microservice | Service resilience | "DB connection lost, service uses circuit breaker" |
| Integration | Service-to-service | Dependency resilience | "Payment service timeout, checkout returns cached response" |
| System | Entire platform | System resilience | "AZ failure, traffic routes to healthy AZ" |
| Business | User-facing flow | Business continuity | "30% pod churn, checkout conversion stays above 90%" |
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.
- 11d ago First seen · 309 lines · 98 tokens per session scan A 733c3a9de42f
chaos-hypothesis-validation is a skill published in the GitHub repository dungnotnull/hybrid-harness-chaos-process-prm (19 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 2,918 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
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.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…