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 aivrar/portable-hermes-agent --skill github-issue-to-prgit clone --depth 1 https://github.com/aivrar/portable-hermes-agentWrote 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/aivrar/portable-hermes-agent/github-issue-to-pr)<a href="https://agentmods.dev/skills/aivrar/portable-hermes-agent/github-issue-to-pr"><img src="https://agentmods.dev/badge/skills/aivrar/portable-hermes-agent/github-issue-to-pr.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.01324 |
| Opus 5 | $0.00010 | $0.00662 |
| Sonnet 5 | $0.00004 | $0.00265 |
| Haiku 4.5 | $0.00002 | $0.00132 |
Grade A, and why
github-issue-to-pr 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 4d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- github-issue-to-pr — 100% identical, 0 lines differ
- github-issue-to-pr — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue to Pull Request
Turn a GitHub issue into a tested, verified PR. This skill owns the end-to-end discipline — premise validation, duplicate sweeps, class-level fixes, and honest CI reporting; the sibling GitHub and development skills own their own mechanics.
When to Use
- "Fix issue #123 and open a PR."
- "Implement this GitHub feature request."
- "Take this bug from issue to green CI."
Don't use for: reviewing an existing PR, or answering a code question with no requested change.
Procedure
1. Read the live issue — body AND full thread
Use terminal to run gh issue view <N> --comments. The body is a snapshot from filing time; the newest comments carry the live state: partial fixes already merged, new root-cause analyses, maintainer decisions, or questions directed at you that change the task. Also read repository instructions (AGENTS.md, contribution docs) with read_file. Done when the currently requested behavior, non-goals, and any unanswered thread questions are known.
2. Sweep for existing and duplicate work
Before writing anything, run gh pr list --search "#<N>" --state all plus at least two keyword/synonym variants of the symptom (gh pr list --search "<subsystem> <symptom>" --state open). Popular issues attract multiple independent fixes; building a duplicate wastes the work and the credit. Also check whether a recent commit already fixed it: git log --oneline -20 -- <relevant files>. Done when you know every open PR and recent commit touching this issue, or that none exist.
3. Validate the premise against current code — and against design intent
Reproduce the bug or demonstrate the missing behavior on the current default branch with a failing test or fixture, using search_files and read_file to trace the reported path. Then check the second question: is the "bug" actually deliberate design? Run git log -p -S "<symbol>" on the code the issue wants changed and read the original commit's intent — a missing link or restriction is often the feature. Challenge stale or flawed issue prose instead of implementing it blindly. Done when the root cause or feature gap is demonstrated in current code AND the change doesn't fight an intentional design.
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.
- 4d ago First seen · 78 lines · 20 tokens per session scan A d422963778ee
github-issue-to-pr is a skill published in the GitHub repository aivrar/portable-hermes-agent (215 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,324 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
release-nyx
Ship a new nyx-local-ai release end to end — bump versions consistently, run the quality gates (typecheck, smoke tests, package), install locally, tag and push so CI publishes the installer artifacts. Use when the user asks to release, ship, publish, bump the version, or cut a new build of the extension.
nyx-ui-screenshots
Regenerate the README UI screenshots for nyx-local-ai from the browser harness — build the webview, serve the harness scenes, capture and crop the images into docs/. Use when the UI changed visibly, when the user asks to update screenshots, or before a release with UI changes.
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.
develop-small-feature
Implement a small, well-scoped feature or fix end-to-end from spec to PR — reuse or create a feature branch, implement test-first, run static checks, get user verification, commit, then open a PR to main.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.