Skip to complete skill
Free community skill@bcherny

Parallel Claude Code Workflow Based on Boris Cherny’s Setup

Independently compiled by XSkills from public material by Boris Cherny.

Turn parallel Claude Code sessions into reviewable pull requests through plan approval, isolated ownership, reusable commands, shared instructions, and end-to-end verification.

Skill brief

Is this the right skill?

Use it when

  • You have several bounded Claude Code tasks that can run locally or in the cloud.
  • You can isolate concurrent changes through checkouts or worktrees.
  • You can verify results with tests, browser checks, simulators, or other feedback tools.

What you get

  • Approved implementation plan
  • Parallel-session ownership ledger
  • Verified pull-request packet

Workflow

6 moves
  1. 01

    Plan the pull request

  2. 02

    Assign isolated sessions

  3. 03

    Reuse the inner loop

  4. 04

    Verify in the real medium

  5. 05

    Record recurring mistakes

  6. 06

    Return a review packet

Complete instruction set

Complete SKILL.md

Read every instruction below or copy the complete file directly into your agent.

Verification-first parallel session loop

Use parallel sessions to increase useful throughput while making verification, not session count, the definition of progress.

Prepare the repository

Confirm that the repository provides:

  • a shared instruction file such as CLAUDE.md or AGENTS.md;
  • isolation through checkouts, worktrees, branches, or cloud environments;
  • fast build, lint, typecheck, and test commands;
  • browser, simulator, device, or other domain-specific verification where needed;
  • a safe permission policy for every environment.

Do not use unrestricted permissions outside a sandbox whose blast radius the user accepts.

Plan meaningful changes

For any pull-request-sized change, keep the agent in a read-only planning state while it inspects the codebase. Iterate until the plan identifies the outcome, affected areas, approach, non-goals, checks, and important risks. Approve the plan before implementation.

Small mechanical changes may skip a written plan only when their scope and verification are already explicit.

Launch isolated sessions

Give each session one bounded responsibility and its own writable environment. Record:

SessionEnvironmentResponsibilityPlanVerificationStatus

Run only as many sessions as can be reviewed. Do not assign overlapping file ownership without an explicit integration sequence.

Reuse the inner loop

When a procedure repeats throughout the day, encode it as a repository command, skill, or script. Good candidates include:

  • commit, push, and pull-request preparation;
  • code simplification;
  • application verification;
  • formatting and focused checks;
  • collection of a final review packet.

Keep these workflows in version control. Make their output compact and actionable.

Verify in the real medium

Every implementation session must receive a feedback loop that can prove the behavior it changed:

  • run focused and regression tests for logic;
  • exercise web behavior in a browser;
  • exercise native behavior in a simulator or device;
  • inspect generated output when the task changes artifacts;
  • repeat until the checks pass or return a blocker.

A second agent may review or verify, but it does not replace deterministic checks or human product judgment.

Compound stable corrections

When review finds a recurring mistake, add a concise rule or tool reference to the applicable repository instruction file. Do this only for stable guidance that future sessions need. Keep transient facts and one-off debugging history out of global instructions.

Return a review packet

For each session return:

  • the approved plan or scoped assignment;
  • changed files and why;
  • commit or pull-request reference;
  • checks, environments, and results;
  • manual evidence;
  • unresolved risk;
  • any new shared instruction or reusable workflow.

Do not merge unless the user separately authorizes it.

Source attribution

Independently compiled by XSkills from Boris Cherny's thread describing how he uses Claude Code. Cherny did not author or review this skill. Parallel local and web sessions, plan-first pull-request work, shared CLAUDE.md corrections, reusable commands and subagents, safe permission configuration, and strong domain verification come from the source. The ownership ledger, review-capacity limit, and merge boundary are XSkills adaptations. Attribution does not imply endorsement.

Keep exploring

Related agent skills

Browse software engineering skills

Turn an X workflow into your own skill.

Paste a public X post and get a free SKILL.md.

Build one free

Evidence and package

Source, changes, and version

Source

XSkills independently compiled this from public material by Boris Cherny. Attribution does not imply endorsement.

Open source evidence ↗

What XSkills changed

XSkills additions are labeled in the complete SKILL.md.

Limitations

  • Use unrestricted permission modes only inside an environment whose blast radius is explicitly accepted.
  • Do not treat planning, simplification, or a second agent as a substitute for domain verification.
  • Do not add transient or one-off observations to shared instructions.

Version

Package version
Not assigned
Fingerprint
c4fcb4271ee1
Last reviewed
Not recorded
License
Not specified