hvir: Skill for Claude Code

.claude/skills/hvir-create-issue/SKILL.md

hvir-create-issue is a skill for Claude Code, Codex from jarmak-personal/hvir. It costs 85 tokens per session (1,601 once invoked), scanned A, original, MIT.

A review process for turning a proposed bug, feature, refactor, documentation change, or maintenance task into a focused GitHub issue for hvir.

In plain words
What is it for?
Use it to sharpen the problem, preserve open questions, prepare an issue title and body, and request separate approval before publishing it.
Why use it?
It checks whether the proposal fits the product design and recorded architecture decisions before coding begins.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: mentions AGENTS.md.

This is jarmak-personal/hvir's own configuration. It tells Claude Code and Codex how to work on hvir itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hvir configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/jarmak-personal/hvir/main/.claude/skills/hvir-create-issue/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jarmak-personal/hvir

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for hvir-create-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/jarmak-personal/hvir/hvir-create-issue/github.svg)](https://agentmods.dev/skills/jarmak-personal/hvir/hvir-create-issue)
Your own site
<a href="https://agentmods.dev/skills/jarmak-personal/hvir/hvir-create-issue"><img src="https://agentmods.dev/badge/skills/jarmak-personal/hvir/hvir-create-issue/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.

agentmods 80×15 button for hvir-create-issue

Your own site · 80×15
<a href="https://agentmods.dev/skills/jarmak-personal/hvir/hvir-create-issue"><img src="https://agentmods.dev/badge/skills/jarmak-personal/hvir/hvir-create-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,601 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.01601
Opus 5 $0.00043 $0.00800
Sonnet 5 $0.00017 $0.00320
Haiku 4.5 $0.00009 $0.00160

Measured yesterday against content hash 0ec6f7f4fd1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hvir-create-issue 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 yesterday.

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.

.claude/skills/hvir-create-issue/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create an hvir issue

Turn an observation or idea into an issue that is worth discussing before code starts. Be opinionated about product fit and precise about what is known, while preserving unresolved questions for the issue discussion.

Require authorization before doing work

Do not research, evaluate, or draft an issue until the user explicitly asks to use this skill or clearly approves an agent's proposal to use it. Discovering a bug, improvement, or possible follow-up is not authorization. In that situation, offer at most one brief sentence such as “I can use hvir-create-issue to evaluate and draft this if you want,” then stop that workflow.

Treat drafting and publishing as separate approvals:

  1. The first approval authorizes product research and an issue draft.
  2. After presenting the exact title, body, and labels, ask whether to create the issue.
  3. Only a clear user approval after that preview authorizes the external write.

Do not infer either approval from silence, the usefulness of the finding, a general preference for issue-first development, or permission granted for a different issue.

Establish context

  1. Read AGENTS.md, CONTRIBUTING.md, docs/design.md, and the ADR index.
  2. Read the ADRs that govern the affected product area or seam.
  3. Inspect relevant local code or documentation when it helps test the proposal against the product as it exists.
  4. Ask only for missing information that materially changes the problem, scope, or fit. Make and state reasonable assumptions for smaller gaps.

Do not treat the reporter's proposed solution as the requirement. First identify the user or contributor problem and the observable outcome.

Classify product fit

State one of these conclusions before drafting:

  • Aligned: the outcome reinforces hvir's view-first, agent-aware workbench.
  • Needs design discussion: it may fit, but a product boundary or durable architecture choice is unresolved.
  • Conflicts with current direction: a design guardrail or ADR rejects the proposed approach. Name the exact conflict and recast the issue as a proposal to revisit that decision only if the reporter intends that discussion.
  • Out of scope: the outcome would turn hvir into an IDE, editor, extension platform, task runner, or session orchestrator, or otherwise violates an explicit non-goal. Explain this directly instead of manufacturing an implementation issue.

Read the full file on GitHub · 152 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. yesterday Changed · +10 lines 0ec6f7f4fd1a
  2. 10d ago First seen · 142 lines · 85 tokens per session scan A 73d75cc3a43f

Subscribe to this mod's changes

hvir-create-issue is a skill published in the GitHub repository jarmak-personal/hvir (2 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 1,601 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 2026-08-31.

Related

Other skills, from other repositories