Borrowing it
Nothing to install: this file belongs to jarmak-personal/hvir. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jarmak-personal/hvir/main/.claude/skills/write-hvir-tests/SKILL.mdgit clone --depth 1 https://github.com/jarmak-personal/hvirWrote 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/jarmak-personal/hvir/write-hvir-tests)<a href="https://agentmods.dev/skills/jarmak-personal/hvir/write-hvir-tests"><img src="https://agentmods.dev/badge/skills/jarmak-personal/hvir/write-hvir-tests/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/jarmak-personal/hvir/write-hvir-tests"><img src="https://agentmods.dev/badge/skills/jarmak-personal/hvir/write-hvir-tests.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 | $0.00055 | $0.01357 |
| Opus 5 | $0.00028 | $0.00678 |
| Sonnet 5 | $0.00011 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
write-hvir-tests 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write hvir tests
Choose evidence from the behavior and its owner, not from the nearest framework or existing test file. Preserve hvir's real Electron, Chromium, node-pty, system Git, packaging, capacity, and SSH contracts while keeping pure policy cheap and direct.
This skill owns test-design procedure. It does not select Git branches, worktrees, issue scope, or
pull-request lifecycle; use hvir-implement-issue for those implementation responsibilities.
Establish the behavior and owner
Before choosing a test file or framework:
- Read
AGENTS.md,docs/design.md, the governing issue, and the ADRs that own the behavior. - State the user or contributor-visible contract in one sentence. Separate it from the current implementation and from incidental DOM, log, class-name, timing, or call-order observations.
- Trace the production path through its actual owners. Inspect renderer models and effects,
preload/IPC adapters, main coordinators, workers,
ProjectHost, the PTY supervisor, harness providers,TerminalPane, and external boundaries only where they participate. - Name the policy owner, effect/resource owner, public seam, and immediate external dependency.
- Search by behavior as well as symbol name for existing tests, domain fixtures, fake ports, production events, semantic snapshots, cleanup owners, clocks, deferred completions, and scenario groups.
When the task selects or reviews test altitude, read
references/behavior-altitude-matrix.md completely
before editing tests. Use it as a stable owner/evidence map, not as an inventory or migration
ledger.
Stop for alignment when the requested test would change product behavior, create test-only authority, weaken an accepted security or lifecycle contract, or replace a required real environment with a fake. Otherwise record the selected behavior, owner, lowest real altitude, and any deliberately retained higher-altitude contract before editing.
What ships with it
2 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.
- 10d ago First seen · 110 lines · 55 tokens per session scan A f4e3c54514e2
write-hvir-tests is a skill published in the GitHub repository jarmak-personal/hvir (2 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,357 once invoked, about $0.0003 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 2026-08-31.
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.