hf.issue

A command that turns a rough software problem into a detailed GitHub issue. GitHub issues are shared records for bugs, improvements, and development tasks.

In plain words
What is it for?
Use it to create issues with relevant files, background information, and acceptance criteria from a short description.
Why use it?
It removes the work of researching the codebase and writing all the technical context before filing an issue.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/t-rav/hydraflow/hf.issue
Clone the repo
git clone --depth 1 https://github.com/T-rav/hydraflow

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,377 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02377
Opus 5 $0.00000 $0.01189
Sonnet 5 $0.00000 $0.00475
Haiku 4.5 $0.00000 $0.00238

Measured 2d ago against content hash a6207e3b74b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hf.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 2d 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.

.claude/commands/hf.issue.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a GitHub Issue

Take a rough description from the user, research the relevant codebase, and create a well-structured GitHub issue with full context, file references, and acceptance criteria.

Usage

/gh-issue add a Stop hook that checks for Langfuse tracing in new LLM code
/gh-issue the tasks service Google Drive auth flow doesn't handle token refresh

$ARGUMENTS contains the rough issue description from the user.

If $ARGUMENTS is empty, ask the user to describe the issue.

Instructions

Phase 0: Resolve Configuration

Before doing anything else, resolve these three values. Use the EXACT fallback logic below — do NOT pass empty strings to gh issue create:

  1. REPO: Run echo "$HYDRAFLOW_GITHUB_REPO". If the output is empty, run git remote get-url origin and extract the owner/repo slug (strip https://github.com/ prefix and .git suffix).
  2. ASSIGNEE: Run echo "$HYDRAFLOW_GITHUB_ASSIGNEE". If the output is empty, extract the owner from the repo slug (the part before /).
  3. LABEL: Use hydraflow-find (the canonical label for discovery-stage issues).

Phase 0.5: Check for Screenshot

If $ARGUMENTS mentions a screenshot file path (e.g. /tmp/hydraflow-report-*.png):

  1. Read the image with the Read tool to understand what the user saw
  2. Use what you see in the screenshot to inform your understanding of the bug

If $ARGUMENTS includes an uploaded screenshot URL (e.g. https://gist.githubusercontent.com/...):

  • Use ![Screenshot](<URL>) in the issue body with the uploaded URL (NOT the local file path)
  • NEVER embed a local filesystem path like /tmp/... or /var/folders/... in the issue body — it will render as a broken image on GitHub

Phase 1: Understand the Request

Parse $ARGUMENTS to understand what the user wants filed as an issue. Identify:

  • What area of the codebase is involved
  • What the problem or feature request is
  • Any specific services, files, or patterns mentioned

Epic detection: If the user mentions "epic", "break into sub-issues", "multiple parts", or describes a large multi-component feature, treat this as an EPIC:

  • Prefix the title with [Epic]
  • Use the hydraflow-epic label (NOT hydraflow-find — the parent epic is a tracking issue, not implementable)
  • Create sub-issues separately, each WITH the hydraflow-find label
  • Link sub-issues in the epic body with checkboxes: - [ ] #123 — title

Read the full file on GitHub · 230 lines

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. 2d ago First seen · 230 lines · 0 tokens per session scan A a6207e3b74b9

Subscribe to this mod's changes

hf.issue is a command published in the GitHub repository T-rav/hydraflow (5 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,377 tokens. 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.