A workflow for handling a b4 pull request in a separate worktree, reviewing it against project rules, and finishing or taking over the change when requested. A worktree is an additional checked-out copy of a Git repository.

Use it to check out and review contributor pull requests, apply b4's Fix-or-Skip rules, merge main, resolve conflicts, push updates, or take over an abandoned pull request.

It keeps review work separate from the current files and provides project-specific guidance for deciding which review comments require fixes. It also covers merging the latest main branch and resolving conflicts when finishing the request.

How DanielLavrushin/b4 configures Claude Code

About the project

B4 is a Linux network packet-processing service that changes network traffic so deep packet inspection systems cannot identify or block its connections. It is used on routers, servers, and desktops to bypass DPI-based blocking, and a router installation can cover devices across the local network. The catalogue lists 12 skills associated with B4.

DanielLavrushin/b4 · 1,848 stars · on GitHub · docs.b4core.app

Reuse

Borrowing it

Nothing to install: this file belongs to DanielLavrushin/b4. 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/DanielLavrushin/b4/main/.claude/skills/b4-pr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/DanielLavrushin/b4

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/daniellavrushin/b4/b4-pr/github.svg)](https://agentmods.dev/skills/daniellavrushin/b4/b4-pr)

Your own site

<a href="https://agentmods.dev/skills/daniellavrushin/b4/b4-pr"><img src="https://agentmods.dev/badge/skills/daniellavrushin/b4/b4-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/daniellavrushin/b4/b4-pr"><img src="https://agentmods.dev/badge/skills/daniellavrushin/b4/b4-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,503 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 unknown 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.

Model	Per session	Once invoked
Fable 5.1	$0.00119	$0.01503
Opus 5.5	$0.00048	$0.00601
Sonnet 5.5	$0.00024	$0.00301
Haiku 4.5	$0.00012	$0.00150

Measured 6d ago against content hash e1c553d4def5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

b4-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/skills/b4-pr/SKILL.md · 97 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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.

6d ago First seen · 97 lines · 119 tokens per session scan A e1c553d4def5

Subscribe to this mod's changes

b4-pr is a skill published in the GitHub repository DanielLavrushin/b4 (1,848 stars, last pushed 4d ago), licensed GPL-3.0. It adds 119 tokens to every session and 1,503 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 2026-10-31.

Code review Git and workflow asuswrt asuswrt-merlin censorship censorship-free dpi geosite

b4-pr next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
b4-prDanielLavrushin/b4	Skill	1.8k	4d ago	GPL-3.0	A	119	Claude Code
prYeachan-Heo/oh-my-claudecode	Skill	41k	yesterday	MIT	A	47	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	5d ago	MIT	A	46	Claude Code
otto-pr-review-loopomnigent-ai/omnigent	Skill	11k	today	Apache-2.0	A	17	Claude Code, Codex
engram-branch-prGentleman-Programming/engram	Skill	7.8k	today	MIT	A	37	Claude Code, Codex
github-contributordaymade/claude-code-skills	Skill	1.5k	yesterday	MIT	A	105	Claude Code, Codex
revdiffumputun/revdiff	Skill	945	yesterday	MIT	A	250	Claude Code

b4: Skill for Claude Code