unsloth-mcp-server: Command for Claude Code

.claude/commands/pr.md

pr is a command for Claude Code from ScientiaCapital/unsloth-mcp-server. It costs 14 tokens per session (734 once invoked), scanned A, original, Apache-2.0.

A guided workflow for preparing a pull request, which is a proposed code change for review. It creates a branch, implements the change, runs available tests, checks the diff, simplifies the result, and submits it.

In plain words
What is it for?
Use it to develop a feature or fix from the main branch, run project tests, review changed files, and prepare the pull request.
Why use it?
It organizes the steps needed to turn a request into a focused, reviewed change and helps prevent unrelated edits from entering the pull request.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

This is ScientiaCapital/unsloth-mcp-server's own configuration. It tells Claude Code how to work on unsloth-mcp-server 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 unsloth-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ScientiaCapital/unsloth-mcp-server. 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/ScientiaCapital/unsloth-mcp-server/main/.claude/commands/pr.md
Clone the repo
git clone --depth 1 https://github.com/ScientiaCapital/unsloth-mcp-server

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 pr

README.md
[![agentmods](https://agentmods.dev/badge/commands/scientiacapital/unsloth-mcp-server/pr.svg)](https://agentmods.dev/commands/scientiacapital/unsloth-mcp-server/pr)
Your own site
<a href="https://agentmods.dev/commands/scientiacapital/unsloth-mcp-server/pr"><img src="https://agentmods.dev/badge/commands/scientiacapital/unsloth-mcp-server/pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 734 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00734
Opus 5 $0.00007 $0.00367
Sonnet 5 $0.00003 $0.00147
Haiku 4.5 $0.00001 $0.00073

Measured 6d ago against content hash a4a72e23901b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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/commands/pr.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pr — Clean Pull Request Workflow

You are preparing a PR for: $ARGUMENTS

Instructions

Step 1: Sync with upstream

git fetch origin
git checkout main
git pull origin main

Step 2: Create a clean branch

Slugify the description into a branch name:

git checkout -b feat/$ARGUMENTS_SLUG   # or fix/$ARGUMENTS_SLUG

Step 3: Build the feature/fix

Implement what was requested. Follow these rules strictly:

  • Read .claude/rules/coding.md and follow every convention
  • Make the MINIMUM changes needed — no drive-by refactors
  • No unrelated formatting changes, no renaming things "while you're in there"
  • Each file you touch should be directly related to the PR description
  • Run tests: cargo test 2>/dev/null || npm test 2>/dev/null || pytest 2>/dev/null

Step 4: Self-review before simplifying

Check your own work:

  • git diff — read every line you changed
  • Are there files that shouldn't be in this PR? Revert them.
  • Are there debug prints, TODO comments, or commented-out code? Remove them.

Step 5: Simplify

Launch a code-simplifier agent (sonnet) on the changed files:

  • Remove unnecessary complexity, verbose error handling, over-abstraction
  • Keep all functionality intact
  • Make sure the code matches the project's existing style, not "AI style"

Step 6: Final review

Launch a code-reviewer agent (haiku) on the diff:

  • Check for bugs, logic errors, security issues
  • Check conventions match .claude/rules/coding.md
  • Only flag HIGH confidence issues

Step 7: Commit and push

git add -A
git commit -m "feat: $ARGUMENTS"
git push origin HEAD

Step 8: Create PR

Use gh pr create with:

  • Short title (under 70 chars)
  • Body with: what changed, why, how to test
  • Tag the PR for review
gh pr create --title "feat: $ARGUMENTS" --body "$(cat <<'EOF'
## What
[1-2 sentences: what this PR does]

## Why
[1 sentence: why this change is needed]

## Changes
- [bullet list of files/components changed]

## How to test
- [ ] [step-by-step testing checklist]

Co-Authored-By: Claude Opus 4.6 <[email protected]>
EOF
)"

Read the full file on GitHub · 109 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. 6d ago First seen · 109 lines · 14 tokens per session scan A a4a72e23901b

Subscribe to this mod's changes

pr is a command published in the GitHub repository ScientiaCapital/unsloth-mcp-server (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 734 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 2026-08-31.