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 s16-blast-radius-controlgit 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/s16-blast-radius-control)<a href="https://agentmods.dev/skills/dungnotnull/hybrid-harness-chaos-process-prm/s16-blast-radius-control"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s16-blast-radius-control/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/s16-blast-radius-control"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s16-blast-radius-control.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 | $0.00089 | $0.02814 |
| Opus 5 | $0.00044 | $0.01407 |
| Sonnet 5 | $0.00018 | $0.00563 |
| Haiku 4.5 | $0.00009 | $0.00281 |
Grade A, and why
chaos-blast-radius-control 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chaos Blast Radius Control
Purpose
Guarantee that chaos experiments affect only the intended targets, at the intended intensity, for the intended duration — with automatic abort mechanisms when the experiment exceeds safe boundaries.
Prerequisites
- Chaos experiment designs from s14 (Experiment Design)
- Environment tier permissions reviewed (see CLAUDE.md env tiers)
- Feature flag chaos gate config from s08 (recommended)
- Risk tolerance preferences from s02 (Taste Memory)
- Service criticality ratings from s01 (PRD)
Input Contract
| Input | Source | Required |
|---|---|---|
| Experiment designs | s12 (workflow_context.artifacts) | Yes |
| Environment tier permissions | CLAUDE.md (chaos allowed table) | Yes |
| Feature flag chaos gate | s08 output | No (recommended) |
| Risk tolerance preferences | s02 taste (risk_tolerance) | Yes |
| Service criticality ratings | s01 PRD | Yes |
Output Contract
| Output | Destination | Format |
|---|---|---|
| Blast radius config per experiment | .commandcode/artifacts/blast-radius-<name>.yaml |
YAML |
| Namespace-scoped RBAC | s06 (delegate update) | YAML |
| PodDisruptionBudget YAML | .commandcode/artifacts/pdb-<service>.yaml |
YAML |
| Blast radius expansion matrix | s18 (game day runbook) | Markdown |
| Safety runbook template | s18 (game day), s21 (alerts) | Markdown |
| OPA blast radius policies | s22 (governance) | Rego |
Blast Radius Dimensions
Blast Radius = Scope × Intensity × Duration
Scope: Which targets (namespace / label / pod count / node)
Intensity: How severe (packet loss % / CPU hog % / pods deleted %)
Duration: How long (seconds of fault injection)
All three must be minimized independently and expanded incrementally.
Scope Control Mechanisms
Level 1 — Pod Label Selector (finest granularity)
# Target ONLY pods with specific labels — nothing else is affected
spec:
appinfo:
appns: payments # Namespace boundary
applabel: "app=checkout-api,version=v2" # AND condition
appkind: deployment
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 · 357 lines · 89 tokens per session scan A 27fb05ee21eb
chaos-blast-radius-control is a skill published in the GitHub repository dungnotnull/hybrid-harness-chaos-process-prm (19 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 2,814 once invoked, about $0.0004 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.