grouter: Skill for Claude Code

.claude/skills/contribute/SKILL.md

contribute is a skill for Claude Code from GXDEVS/grouter. It costs 135 tokens per session (2,919 once invoked), scanned A, original, MIT.

A guided contribution workflow for grouter, a GitHub software project. It takes a developer from local changes through branch creation, commits, pushing, and opening a pull request.

In plain words
What is it for?
Use it when preparing a grouter contribution: create a correctly named branch, make Conventional Commits, push the branch, and open a pull request with the GitHub CLI.
Why use it?
It removes guesswork from the project’s contribution rules and helps keep each change separate and clearly described. It also checks the developer’s Git identity and requires approval for shared repository actions.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is GXDEVS/grouter's own configuration. It tells Claude Code how to work on grouter 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 grouter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GXDEVS/grouter. 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/GXDEVS/grouter/main/.claude/skills/contribute/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GXDEVS/grouter

Made for: Claude Code.

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 contribute

README.md
[![agentmods](https://agentmods.dev/badge/skills/gxdevs/grouter/contribute/github.svg)](https://agentmods.dev/skills/gxdevs/grouter/contribute)
Your own site
<a href="https://agentmods.dev/skills/gxdevs/grouter/contribute"><img src="https://agentmods.dev/badge/skills/gxdevs/grouter/contribute/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 contribute

Your own site · 80×15
<a href="https://agentmods.dev/skills/gxdevs/grouter/contribute"><img src="https://agentmods.dev/badge/skills/gxdevs/grouter/contribute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,919 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00135 $0.02919
Opus 5.5 $0.00054 $0.01168
Sonnet 5.5 $0.00027 $0.00584
Haiku 4.5 $0.00014 $0.00292

Measured 2mo ago against content hash cc0182a4780d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

contribute 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 2mo 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.

.claude/skills/contribute/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grouter — Contribution Flow

End-to-end helper for contributing to grouter (GXDEVS/grouter). Take the user from "I have changes" to "PR open on GitHub" with zero guesswork.

Ground rules — non-negotiable

  1. Use the developer's git identity. Read git config user.name and git config user.email. Never run git config --global user.* or override the identity. If unset, stop and tell the user to configure it (see step 0).
  2. No emojis. Not in branch names, commit messages, PR titles, PR bodies, or terminal output. None.
  3. No Claude attribution. Do not append Co-Authored-By: Claude …, "Generated with Claude Code", or any similar footer to commits or PRs. Leave the message ending with the body/footer the user approved.
  4. Never force-push, never --no-verify, never amend a commit that was already pushed. If a hook fails, fix the underlying issue and create a new commit.
  5. Commit scope matches the user's intent. Ask per logical change — one feature/fix per commit. Do not silently bundle unrelated files.
  6. Confirm before destructive or shared-state actions. Branch deletion, rebases, PR creation, and git push always get an explicit "yes" from the user.

Step 0 — Verify the developer is logged in

Run these checks in parallel before anything else:

git config user.name
git config user.email
git -C . remote get-url origin
gh auth status 2>&1 || true

Decision table:

Check Missing → do this
user.name / user.email empty Stop. Tell the user to run git config --global user.name "Your Name" and git config --global user.email "[email protected]" themselves, then retry.
gh auth status not logged in Tell the user to run gh auth login in the prompt as ! gh auth login (interactive). PR step needs it. Commits/branch work can still proceed.
origin points to a fork Fine — PRs will target GXDEVS/grouter:main via gh pr create --repo GXDEVS/grouter. Confirm the fork URL with the user.

Read the full file on GitHub · 259 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. 2mo ago First seen · 259 lines · 0 tokens per session scan A cc0182a4780d

Subscribe to this mod's changes

contribute is a skill published in the GitHub repository GXDEVS/grouter (54 stars, last pushed 2mo ago), licensed MIT. It adds 135 tokens to every session and 2,919 once invoked, about $0.0005 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 2026-08-30.

Related

contribute compared with skills from other repositories

contribute next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
contributeGXDEVS/grouterSkill542mo agoMITA135Claude Code
github-automationruvnet/rufloSkill81kyesterdayMITA61Claude Code
changelogDonchitos/Claude-Code-Game-StudiosSkill36k19d agoMITA22Claude Code
comet-safe-deliveryrpamis/cometSkill3.3kyesterdayMITA78Claude Code, Codex
coco-shipcoco-research/cocoSkill785yesterdayApache-2.0A69Claude Code
close-task-commit-push-prdevoxx/DevoxxGenieIDEAPluginSkill687yesterdayMITA64Claude Code
git-workflowjezweb/claude-skillsSkill1.1k28d agoMITA52Claude Code