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 harness/harness-ai --skill chaos-dr-testgit clone --depth 1 https://github.com/harness/harness-aiWrote 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/harness/harness-ai/chaos-dr-test)<a href="https://agentmods.dev/skills/harness/harness-ai/chaos-dr-test"><img src="https://agentmods.dev/badge/skills/harness/harness-ai/chaos-dr-test/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/harness/harness-ai/chaos-dr-test"><img src="https://agentmods.dev/badge/skills/harness/harness-ai/chaos-dr-test.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 | $0.00121 | $0.02359 |
| Opus 5.5 | $0.00048 | $0.00944 |
| Sonnet 5.5 | $0.00024 | $0.00472 |
| Haiku 4.5 | $0.00012 | $0.00236 |
Grade A, and why
chaos-dr-test 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 1mo 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.
This is a copy
100% identical to chaos-dr-test — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chaos DR Test
Create and edit Harness DR Test pipelines — pipelines with a DRTest stage
containing ChaosFault, ChaosProbe, ChaosAction, and Chaos steps — via MCP.
MANDATORY — Tool Result Verification:
- NEVER claim a tool call succeeded without an explicit success response from the tool.
- NEVER fabricate, assume, or pre-empt tool results. If you called a tool and did not receive a confirmed result, say so and retry.
- When a tool returns a review/elicitation prompt (e.g., "Waiting for user to review before update..."), the user's approval does NOT mean the operation completed. You MUST wait for the follow-up tool response confirming execution before reporting success.
- If the tool response is ambiguous or missing, tell the user honestly and offer to retry.
Scope Rules
Follow references/scope-establishment.md for establishing org/project scope before calling harness_list, harness_get, harness_create, harness_update, or harness_execute in this skill:
- Parse
org/projectfrom the user's message or a pasted Harness UI URL first. - Ask only for what is missing — do not re-ask for values already known.
- Restate the active scope before the first mutating call.
- Never invent a default org/project. If either is missing, ask the user to select it before calling a project-scoped resource; do not fall back to account scope silently.
Instructions
YAML Output Conventions
Output style — always emit block-style YAML for pipeline manifests (each key on its own line, list items on their own line with -, children indented). The YAML examples shown in references/components.md (Series + Parallel Steps, Full DRTest Pipeline, Chaos step) appear as minified JSON purely for token efficiency — JSON parses identically to YAML, so the examples remain authoritative for field names and structure, but the pipeline YAML you produce MUST be block-style matching the canonical scaffold below. Never put JSON in the request body for harness_create or harness_update pipeline YAML.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 156 lines · 121 tokens per session scan A 38bae47066c1
chaos-dr-test is a skill published in the GitHub repository harness/harness-ai (27 stars, last pushed 4d ago), licensed Apache-2.0. It adds 121 tokens to every session and 2,359 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to chaos-dr-test, differing in 3 lines, and is treated as a copy.
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.