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 agentmods add commands/t-rav/hydraflow/hf.issuegit clone --depth 1 https://github.com/T-rav/hydraflowWhat 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 | $0.00000 | $0.02377 |
| Opus 5 | $0.00000 | $0.01189 |
| Sonnet 5 | $0.00000 | $0.00475 |
| Haiku 4.5 | $0.00000 | $0.00238 |
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.
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 $ARGUMENTS is empty, ask the user to describe the issue.
Instructions
Phase 0: Resolve Configuration
Before doing anything else, resolve these three values. Use the EXACT fallback logic below — do NOT pass empty strings to gh issue create:
- REPO: Run
echo "$HYDRAFLOW_GITHUB_REPO". If the output is empty, rungit remote get-url originand extract theowner/reposlug (striphttps://github.com/prefix and.gitsuffix). - ASSIGNEE: Run
echo "$HYDRAFLOW_GITHUB_ASSIGNEE". If the output is empty, extract the owner from the repo slug (the part before/). - 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):
- Read the image with the Read tool to understand what the user saw
- 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
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-epiclabel (NOThydraflow-find— the parent epic is a tracking issue, not implementable) - Create sub-issues separately, each WITH the
hydraflow-findlabel - Link sub-issues in the epic body with checkboxes:
- [ ] #123 — title
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.
- 2d ago First seen · 230 lines · 0 tokens per session scan A a6207e3b74b9
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.
Other commands, from other repositories
gh-issue
Create a new GitHub issue following solution-agnostic principles.
gh-release
Create a new release for the marketplace or a specific plugin.
verify
Verify factual claims in content using deep research methodology - fact-checks key assertions and updates NCI scores.
gh-merge
Merge an approved pull request with standardized settings.
gh-plugin
Validate plugin structure and configuration before committing changes.
gh-review
Review a pull request with proper branch checkout and convention checks.