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 ronaknnathani/relay --skill open-prgit clone --depth 1 https://github.com/ronaknnathani/relayWrote 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/ronaknnathani/relay/open-pr)<a href="https://agentmods.dev/skills/ronaknnathani/relay/open-pr"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/open-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/ronaknnathani/relay/open-pr"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/open-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 | $0.00068 | $0.01216 |
| Opus 5 | $0.00034 | $0.00608 |
| Sonnet 5 | $0.00014 | $0.00243 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
open-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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open PR
Take finished work from working tree to open pull request: stage specific files, commit with a
repo-style message, push, and open the PR in the author's house style. Read <repo>/AGENTS.md and
~/.config/agents/AGENTS.md first (repo-specific rules win) and follow those preferences for commit
messages and PR descriptions. Execute git/gh operations through this skill's bundled
scripts/open-pr.sh helper rather than inlining command sequences in the skill.
Flags
--draft— open the PR as a draft (gh pr create --draft). Default is open (ready for review).--no-review— skip the optional local review before push.
Process
-
Branch-if-on-default gate. Never commit straight onto the default branch. Invoke the helper's
ensure-branch <slug>command. It hard-fails if the default branch cannot be detected and, when a new branch is needed, reads the branch prefix from the first-timerelayconfig (relay config branch-prefix) rather than hardcoding a personal prefix. -
Stage specific files. Invoke the helper's
statuscommand, then itsstage -- <files...>command for exactly what belongs in this change — never stage the whole tree. Confirm the diff carries no secrets and no formatting churn mixed in with behavior. -
Commit in the repo's style. Match the repository's recent commit style and the AGENTS.md preferences. Do not force Conventional Commits unless the repo already uses them. The subject should lead with what changed; include a body only when useful, and make it explain why the change exists rather than restating the diff. Keep refactor commits separate from feature/fix commits (split with separate
stage/commithelper calls if both are present). End every message with aCo-authored-bytrailer for the actual model/agent currently doing the work; never hardcode a model. Use the runtime-provided model identity when available, and the agent's verified no-reply identity for the email. Then invoke the helper'scommit <message-file>command.
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.
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.
- 8d ago First seen · 84 lines · 68 tokens per session scan A 1fdf10c8748f
open-pr is a skill published in the GitHub repository ronaknnathani/relay (3 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 1,216 once invoked, about $0.0003 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.
Other skills, from other repositories
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
git-workflow
Git best practices, branching strategies, commit conventions, and code review patterns.
github-operations
WORKFLOW SKILL — Full GitHub contribution lifecycle: branches, conventional commits, issues, PRs, Actions, releases. gh CLI-first with MCP fallback. WHEN: "commit", "push", "open PR", "create branch", "create issue", "cut release", "GitHub operation". DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code…
conventional-commit
Generer conventional commit-meldinger med Nav-relevante scopes og breaking change-format.
pr-review
Reviews a GitHub pull request and posts inline comments plus one consolidated summary, adapting to any codebase by discovering the project's own test runner, requirement specs, and architecture conventions before running six specialized review agents in parallel. Stack-agnostic across language and framework; targets…
implement-suggestion
Implements review-comment suggestions across one or more PRs. Multi-PR mode (default when $ARGUMENTS contains PR URLs; empty $ARGUMENTS auto-detects the active PR) per PR: resolves a worktree, fetches every actionable comment from both human teammates AND AI code-review bots (claude[bot], coderabbitai[bot], …)…