bklit-ui: Skill for Claude Code

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

pr-open is a skill for Claude Code, Codex from bklit/bklit-ui. It costs 88 tokens per session (2,471 once invoked), scanned A, original, MIT.

A repository-specific checklist for turning local code changes into a pull request, a Git-based proposal for merging changes. It covers validation, committing, pushing, and preparing the request.

In plain words
What is it for?
Use it when you need to commit and validate changes, push a branch, and open a structured pull request, including when you say “ship it.”
Why use it?
It reduces the chance of opening a pull request with failed checks, missing generated files, unrelated changes, or accidentally exposed secrets.

Skill for Claude CodeCodex

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

This is bklit/bklit-ui's own configuration. It tells Claude Code and Codex how to work on bklit-ui 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 bklit-ui configures →

About the project

Bklit UI is an open-source collection of customizable interface components and charts for building React applications with shadcn. Developers use it to add data visualizations such as funnels, gauges, maps, financial charts, and other interactive displays. The catalogue add-ons provide workflows for using its components and chart registry.

bklit/bklit-ui · 1,898 stars · on GitHub · bklit.com

Reuse

Borrowing it

Nothing to install: this file belongs to bklit/bklit-ui. 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/bklit/bklit-ui/main/.agents/skills/pr-open/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bklit/bklit-ui

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 pr-open

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/bklit/bklit-ui/pr-open"><img src="https://agentmods.dev/badge/skills/bklit/bklit-ui/pr-open.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,471 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
  • Socket pass 15 Oct 2026
  • Snyk pass 15 Oct 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 84
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 98
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00088 $0.02471
Opus 5.5 $0.00035 $0.00988
Sonnet 5.5 $0.00018 $0.00494
Haiku 4.5 $0.00009 $0.00247

Measured 21d ago against content hash 017777c14a92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-open 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 21d 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.

.agents/skills/pr-open/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Open Skill

End-to-end workflow for committing work and opening a merge-ready PR in bklit-ui.

Read this skill when the user wants to add, commit, validate, push, and open a PR — or references @pr-open.


Before you start

  1. Confirm branch context

    • If the user merged an earlier PR on this branch and there are new changes, branch from latest main instead of stacking on a stale feature branch:
      git fetch origin main
      git checkout -b <new-branch-name> origin/main
      
    • Re-apply or cherry-pick only the intended changes; do not commit unrelated registry:build noise (e.g. reformatted packages/ui/registry/examples/* unless those edits are intentional).
  2. Never commit secrets — skip .env, credentials, API keys, etc. Warn the user if they ask to commit them.

  3. Git safety (required)

    • Do not update git config.
    • Do not run destructive commands (push --force, reset --hard) unless the user explicitly asks.
    • Do not skip hooks (--no-verify) unless the user explicitly asks.
    • Do not git commit --amend unless all amend rules in the user's git rules are satisfied (HEAD commit is yours, not pushed, or user requested amend).
    • If a commit fails due to a hook, fix the issue and create a new commit — do not amend a failed commit.
    • Use HEREDOC for commit messages (see below).
    • Do not push unless the user asked to push or open a PR.

Step 1 — Inspect changes

Run in parallel from the repo root:

git status
git diff
git diff --staged
git log -5 --oneline

If opening a PR, also check divergence from base:

git fetch origin main
git log origin/main..HEAD --oneline
git diff origin/main...HEAD --stat

Draft a commit message that explains why, not just what. Match recent repo style (e.g. feat(charts): …, fix(web): …).


Step 2 — Stage and commit (pre-commit loop)

Stage

git add <paths>   # prefer explicit paths over blind git add -A

Read the full file on GitHub · 302 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. 21d ago Changed · +2 lines 017777c14a92
  2. 2mo ago First seen · 300 lines · 88 tokens per session scan A eccaeb79f003

Subscribe to this mod's changes

pr-open is a skill published in the GitHub repository bklit/bklit-ui (1,898 stars, last pushed 5d ago), licensed MIT. It adds 88 tokens to every session and 2,471 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 2026-08-30.

Related

pr-open compared with skills from other repositories

pr-open next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pr-openbklit/bklit-uiSkill1.9k5d agoMITA88Claude Code, Codex
commitf5/unovisSkill2.9kyesterdayApache-2.0A90Claude Code, Codex
open-prf5/unovisSkill2.9kyesterdayApache-2.0A67Claude Code, Codex
changelogRemocn/remocnSkill1.7kyesterdayMITA70Claude Code
repository-writebacklightdash/lightdashSkill6.2kyesterdaynoneA65Claude Code, Codex
github-readmethatrebeccarae/claude-marketingSkill1925mo agoMITA63Claude Code, Codex
safe-pushthatrebeccarae/claude-marketingSkill1925mo agoMITB63Claude Code, Codex