asana-clone-app: Skill for Claude Code

.claude/skills/pr/SKILL.md

pr is a skill for Claude Code from manakuro/asana-clone-app. It costs 24 tokens per session (798 once invoked), scanned A, original, MIT.

A workflow for pushing the current Git branch and opening a GitHub pull request, a request for others to review and merge changes. It follows the repository's pull-request template and checks the branch and remotes first.

In plain words
What is it for?
Use it to inspect branch differences, identify the source and target repositories, push a feature branch, and create a templated pull request.
Why use it?
It avoids pushing directly to the main branch, sending changes to the wrong repository, or opening a pull request without the required information.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

This is manakuro/asana-clone-app's own configuration. It tells Claude Code how to work on asana-clone-app 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 asana-clone-app configures →

Reuse

Borrowing it

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

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/manakuro/asana-clone-app/pr/github.svg)](https://agentmods.dev/skills/manakuro/asana-clone-app/pr)
Your own site
<a href="https://agentmods.dev/skills/manakuro/asana-clone-app/pr"><img src="https://agentmods.dev/badge/skills/manakuro/asana-clone-app/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/manakuro/asana-clone-app/pr"><img src="https://agentmods.dev/badge/skills/manakuro/asana-clone-app/pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 798 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 $0.00024 $0.00798
Opus 5.5 $0.00010 $0.00319
Sonnet 5.5 $0.00005 $0.00160
Haiku 4.5 $0.00002 $0.00080

Measured 22d ago against content hash ca8c6b3c8cc2, 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 22d 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a pull request

Push the current branch to origin (the maintainer's clone or a contributor's fork) and open a PR against main of the upstream repository, with a description that follows .github/PULL_REQUEST_TEMPLATE.md.

Extra notes from the user (may be empty): $ARGUMENTS

1. Find the repositories

git remote -v
  • Head (where the branch is pushed): the origin remote, <head-owner>/<head-repo>.
  • Base (where the PR is opened): the upstream remote if there is one (a fork), otherwise origin. Call it <base-owner>/<base-repo> and use <base> below for that remote's name.

Read the owners and repo names from the remote URLs ([email protected]:<owner>/<repo>.git or https://github.com/<owner>/<repo>.git). Don't assume a fixed owner.

2. Check the branch

git branch --show-current
git status --short
git fetch <base> main --quiet
git log --oneline <base>/main..HEAD
git diff --stat <base>/main...HEAD
  • If the current branch is main, stop and ask the user for a branch name. Don't push to main.
  • If there are uncommitted changes, ask the user whether to commit them first or leave them out.
  • If there are no commits ahead of <base>/main, stop: there is nothing to open a PR for.

3. Write the title and description

Read the branch name, the commit messages and the diff to understand the change.

  • Title: Conventional Commits, like the commits in this repo (feat(core): …, fix(cli): …, docs: …, build: …, ci: …). For a single-commit branch, reuse the commit subject.
  • Description: fill in every section of .github/PULL_REQUEST_TEMPLATE.md, keeping its headings and order:
    • Summary: the purpose of the change in one or two sentences, then a bullet list of the main changes
    • Related Issues: Closes #<n> for issues the branch fixes (from the branch name, commits or the user's notes), otherwise None
    • Testing: what was run (pnpm lint, pnpm tsc, pnpm test:ci, the playground app, …) and what was checked by hand
    • Add anything reviewers should know (breaking changes, follow-ups, generated files to skip) at the end of Summary
  • Screenshots are not required.
  • Don't add the 🤖 Generated with Claude Code footer or any link to Claude at the end of the description.

Read the full file on GitHub · 70 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. 22d ago First seen · 70 lines · 24 tokens per session scan A ca8c6b3c8cc2

Subscribe to this mod's changes

pr is a skill published in the GitHub repository manakuro/asana-clone-app (22 stars, last pushed 22d ago), licensed MIT. It adds 24 tokens to every session and 798 once invoked, about $0.0001 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 2026-10-08.