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 runxhq/runx --skill github-issue-to-prgit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/github-issue-to-pr)<a href="https://agentmods.dev/skills/runxhq/runx/github-issue-to-pr"><img src="https://agentmods.dev/badge/skills/runxhq/runx/github-issue-to-pr/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/runxhq/runx/github-issue-to-pr"><img src="https://agentmods.dev/badge/skills/runxhq/runx/github-issue-to-pr.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 | $0.00045 | $0.01177 |
| Opus 5.5 | $0.00018 | $0.00471 |
| Sonnet 5.5 | $0.00009 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00118 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue to PR
Turn one issue into a tested change and, when authorized, a verified pull request. Use the repository's normal development workflow. Runx owns evidence continuity and the consequential publication boundary; it does not replace the host agent's editor, shell, Git, tests, or repository judgment.
Scope
Use this runner for work the repository actually governs with scafld: essential architecture, execution, security, persistence or cross-package contract changes, or work explicitly placed under that lifecycle by the operator. Read the repository's current instructions before choosing it. The receipt-verification wall is part of this skill's executable contract.
For ordinary UI, copy, documentation and routine fixes, use normal host editing and focused checks, then the selected GitHub operation for publication. Do not create a scafld lifecycle merely to satisfy this package, and do not invent a finalization receipt. Task size or file count alone does not make work governed.
Direct operator flow
- Name the repository as an exact
owner/name. Never infer the target from an available grant. - Read through the GitHub instance selected here: the signed-in
ghsession (runx connector use github --session) or a stored token. - Run one preflight before work: issue identity, repository permission, branch state, required tools, requested outcome, and publication authority.
- Investigate, edit, and test with the host agent's ordinary tools. Do not manufacture Runx answer files between normal coding steps.
- Complete the repository-required independent review and call
scafld finalizeexactly once after the change and tests are ready. Preserve its workspace-scoped receipt path, exact target commit, and contract digest inhost_result. Runx verifies that receipt with the scafld CLI on this host (scafld/receipt.verify) and checks its verdict, commit, contract and open blockers; host-authored status strings are not proof. - If PR publication is not authorized, return the tested/finalized result and stop. Do not silently downgrade the work to a plan.
- If publication is authorized, pass the exact
host_resulttopublish. Runx pushes the exact commit to the requested branch (github/branch.push, never forced, read back from GitHub), reuses the one open pull request for that branch or opens one (github/pullrequest.open, read back), and completes only when the pull request's head is the tested commit. Notifications, feeds, issue comments, and documentation sync are optional downstream skills.
What ships with it
14 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.
- fixtures/bin/gh 205 B
- fixtures/bin/git 758 B
- fixtures/bin/scafld 174 B
- fixtures/composed-pr-flow.yaml 2.6 KB
- fixtures/composes-in-graph.yaml 228 B
- fixtures/receipt-for-another-contract.yaml 1.9 KB
- fixtures/resume-after-provider-failure.yaml 4.0 KB
- fixtures/resume-reuses-open-pull-request.yaml 3.1 KB
- fixtures/scafld-pass.json 267 B
- fixtures/standalone-host-flow.yaml 2.8 KB
- fixtures/support/composed.graph 1.6 KB
- github-issue-to-pr.mjs 9.0 KB runs code
- references/catalog.md 170 B
- run.yaml 14 KB
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.
- yesterday First seen · 118 lines · 45 tokens per session scan A 1e2d15f4580a
github-issue-to-pr is a skill published in the GitHub repository runxhq/runx (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,177 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
test-then-commit
Implements a small change and commits it. Use when the user asks for a quick fix with a commit.
aigon-research-spec-revise
Revise research spec after pending spec reviews — decide and acknowledge in one pass.