mcp-mixsearch: Skill for Claude Code

.agents/skills/github-pr/SKILL.md

github-pr is a skill for Claude Code, Codex from geosp/mcp-mixsearch. It costs 94 tokens per session (1,546 once invoked), scanned A, original, MIT.

A workflow for preparing and opening a GitHub pull request, which is a proposed set of code changes for review. It checks the branch and repository, creates a feature branch when needed, prepares a description from the changes, and can push the branch and create the pull request.

In plain words
What is it for?
It helps deliver completed work through clean commits and a documented GitHub pull request, including optional pushing and pull-request creation.
Why use it?
It removes repetitive release and review setup and helps keep the branch, commit, issue link, tests, and manual-check evidence organised.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is geosp/mcp-mixsearch's own configuration. It tells Claude Code and Codex how to work on mcp-mixsearch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-mixsearch configures →

Reuse

Borrowing it

Nothing to install: this file belongs to geosp/mcp-mixsearch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/geosp/mcp-mixsearch/main/.agents/skills/github-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/geosp/mcp-mixsearch

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for github-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/geosp/mcp-mixsearch/github-pr/github.svg)](https://agentmods.dev/skills/geosp/mcp-mixsearch/github-pr)
Your own site
<a href="https://agentmods.dev/skills/geosp/mcp-mixsearch/github-pr"><img src="https://agentmods.dev/badge/skills/geosp/mcp-mixsearch/github-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.

agentmods 80×15 button for github-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/geosp/mcp-mixsearch/github-pr"><img src="https://agentmods.dev/badge/skills/geosp/mcp-mixsearch/github-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00094 $0.01546
Opus 5.5 $0.00038 $0.00618
Sonnet 5.5 $0.00019 $0.00309
Haiku 4.5 $0.00009 $0.00155

Measured today against content hash 72db9284a5bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-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 today.

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.

.agents/skills/github-pr/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub pull request

Work is tracked in GitHub issues and delivered through pull requests into the default branch (main). Follow the branch, commit and attribution rules in AGENTS.md throughout.

Step 1 - Check the repository and the base branch

  1. Find the base branch: gh repo view --json defaultBranchRef -q .defaultBranchRef.name. If that fails (no remote or no gh auth), use main.
  2. Run git remote -v. If there is no remote, say so: you can still prepare the description (Steps 2-6), but pushing and creating the PR in Step 7 are unavailable until the repository exists.

Step 2 - Get to a clean feature branch

Run git status (including untracked files) and check the current branch.

If the current branch is the base branch, the work was done without a feature branch:

  1. If there are unstaged or untracked changes, stash them (git stash --include-untracked).
  2. Update the base branch (git pull) if a remote exists.
  3. Create a feature branch that follows the branch naming in AGENTS.md: <type>/<issue>-<slug>. If you don't know the issue number, go to Step 3 first.
  4. If changes were stashed, pop them (git stash pop).

If there are unstaged or untracked changes (on any branch):

  1. Show the user a summary of the changes and ask whether they belong in this PR. If not, stop and let the user sort them out.
  2. Stage and commit them with clear, descriptive messages. Prefer several small commits when the changes are logically distinct. No attribution: no Co-Authored-By trailers, no "Generated with ..." lines, and no agent as author (AGENTS.md).

Never commit secrets, .env files, pr-description.md, or project data that AGENTS.md keeps out of Git.

Step 3 - Identify the GitHub issue

Look for the issue number, in this order:

  1. The branch name (feat/3-input-validation -> #3).
  2. The commit messages (git log <base>..HEAD).
  3. Ask the user.

When you have a number, read the issue: gh issue view <n> --json number,title,body,labels,milestone,state. Use its acceptance criteria and linked plan as context.

Read the full file on GitHub · 114 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. today First seen · 114 lines · 94 tokens per session scan A 72db9284a5bd

Subscribe to this mod's changes

github-pr is a skill published in the GitHub repository geosp/mcp-mixsearch (0 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,546 once invoked, about $0.0004 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 2026-11-18.

Related

github-pr compared with skills from other repositories

github-pr next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
github-prgeosp/mcp-mixsearchSkill0yesterdayMITA94Claude Code, Codex
prYeachan-Heo/oh-my-claudecodeSkill41ktodayMITA47Claude Code
merge-batchdiegosouzapw/OmniRouteSkill88k3d agoMITA46Claude Code
otto-pr-review-loopomnigent-ai/omnigentSkill11ktodayApache-2.0A17Claude Code, Codex
engram-branch-prGentleman-Programming/engramSkill8.2kyesterdayMITA37Claude Code, Codex
github-contributordaymade/claude-code-skillsSkill1.5ktodayMITA105Claude Code, Codex
revdiffumputun/revdiffSkill961todayMITA253Claude Code