clawstash: Skill for Claude Code

.claude/skills/pr/SKILL.md

pr is a skill for Claude Code from fo0/clawstash. It costs 80 tokens per session (3,305 once invoked), scanned A, original, MIT.

A workflow for GitHub pull requests, which are proposed code changes submitted for review before being merged into a project.

In plain words
What is it for?
It helps open or update a pull request, read its status and review feedback, and merge it when the user explicitly asks.
Why use it?
It organizes creating, updating, checking, commenting on, and merging pull requests while checking whether GitHub access is available.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is fo0/clawstash's own configuration. It tells Claude Code how to work on clawstash 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 clawstash configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fo0/clawstash. 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/fo0/clawstash/main/.claude/skills/pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fo0/clawstash

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/skills/fo0/clawstash/pr/github.svg)](https://agentmods.dev/skills/fo0/clawstash/pr)
Your own site
<a href="https://agentmods.dev/skills/fo0/clawstash/pr"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/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 pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/fo0/clawstash/pr"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,305 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 $0.00080 $0.03305
Opus 5.5 $0.00032 $0.01322
Sonnet 5.5 $0.00016 $0.00661
Haiku 4.5 $0.00008 $0.00331

Measured 26d ago against content hash 96c69d9d7931, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 26d 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/pr/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR — Pull Request Workflow

When to Use

  • User says "PR" / "/pr" / "create PR" / "open PR" / "update PR" → auto-route by state
  • User says "PR status" / "/pr status" / "check PR" → status (override)
  • User says "PR comments" / "/pr comments" → read review comments (override)
  • User says "merge PR" / "/pr merge" → merge (explicit only, never automatic; owner-authorized routines count as explicit — see /pr merge)
  • After done-skill push step on a feature branch → suggested, user invokes /pr to trigger

Scope Boundaries

Owns: the pull request as an object — create, update, status, comments, and the explicit merge gate. Does not own: whether the code is good (basic-review), whether the build is green (ci), undoing a merge that already landed (rollback). A PR that should not exist yet is a review finding, not a PR-skill decision.

Prerequisites

gh auth status && gh repo view --json name,owner

If gh is missing or unauthenticated, check for the GitHub MCP server before giving up — Claude Code web/remote sessions ship mcp__github__* tools instead of the CLI, and an unattended routine must not stall there:

Available Do this
gh Use the commands as written below (preferred — least round-trips)
GitHub MCP only Same workflow, MCP equivalents: list_pull_requests / create_pull_request / update_pull_request / pull_request_read (get, get_status, get_comments, get_review_comments) / merge_pull_request. git push still runs over plain git
Neither Print No GitHub access (gh CLI or GitHub MCP required). and stop — do NOT fall back to manual PR creation via web

Dependency-Bot PRs (auto-detect)

Before normal auto-routing, detect dep-bot PRs by head branch pattern (not by author — author can be spoofed):

Read the full file on GitHub · 208 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. 26d ago Changed · +3 lines 96c69d9d7931
  2. 1mo ago Changed 00651183d5ef
  3. 1mo ago Changed · -9 lines e9d0536089ba
  4. 1mo ago Changed · +7 lines 4cca617c8051
  5. 2mo ago First seen · 207 lines · 80 tokens per session scan A 07d3a3ca2122

Subscribe to this mod's changes

pr is a skill published in the GitHub repository fo0/clawstash (1 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 3,305 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

publish-release

Releases a new McpOrchestrator version end to end — version bump PR, tag, and the automated deploy to GitHub Releases, NuGet, and the MCP Registry. Use when asked to release, publish, deploy, ship, or bump the version of McpOrchestrator.

Byggarepop/dotnet-mcp-orchestrator · 63 tokens

feedback-nudge

Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).

zooza-dev/zooza-mcp-server · 38 tokens

release-notes

Writes user-facing release notes from a git commit range. Use when asked to draft release notes, a changelog entry, or "what's new" text for a release.

Byggarepop/dotnet-mcp-orchestrator · 39 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…

cyanheads/pubmed-mcp-server · 155 tokens

git-wrapup

Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…

cyanheads/pubmed-mcp-server · 109 tokens

release-pr-review

Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…

cyanheads/pubmed-mcp-server · 136 tokens