---
title: "Give each parallel agent its own checkout and a claimed task"
description: "Each agent works in its own container or worktree and claims a task with a lock file before it starts."
url: https://starsling.dev/ci-playbooks/techniques/isolated-agent-checkouts
canonicalUrl: https://starsling.dev/ci-playbooks/techniques/isolated-agent-checkouts
---

# Give each parallel agent its own checkout and a claimed task

Each agent works in its own container or worktree and claims a task with a lock file before it starts.

## How to choose an approach

This technique currently has one documented company example. Validate its prerequisites, tradeoffs and original CI environment against your repository before adapting it.

- **[Anthropic](https://starsling.dev/ci-playbooks/anthropic#isolated-agent-checkouts)**: Use it when Several agents push to one repository, or two agents pick up the same task. Check before adopting: Task locks are plain files in the repository, so merge conflicts are frequent and the agents resolve them. Keep slow shared commands out of the agents' loop.

## Apply this technique

````text
Evaluate and apply this CI technique to my repository: Give each parallel agent its own checkout and a claimed task.

Each agent works in its own container or worktree and claims a task with a lock file before it starts.

Read the technique and its source-backed company examples: https://starsling.dev/ci-playbooks/techniques/isolated-agent-checkouts.md

Inspect this repository’s CI workflows, build and test commands, dependencies, and recent run timings. Identify where this technique applies and explain the expected benefit using this repository’s evidence.
Measure a baseline from recent comparable runs: elapsed time, queue time, runner minutes and failures where available. If data is unavailable, say what cannot be measured.
Compare relevant company approaches, checking prerequisites, platform differences and tradeoffs. Rank applicable options by evidence, fit and measurable opportunity; do not present company results as predictions for this repo.
Recommend the smallest safe change, show what checks and fallback paths remain, and ASK ME WHICH CHANGE TO APPROVE BEFORE EDITING ANY FILES.
Only after approval, work on a new feature branch, make one reversible change, and open a reviewable pull request. Never merge or push to a default or protected branch.
Keep required checks, test coverage, deployment and release behavior intact. Validate the change and compare equivalent runs where possible; report limitations and what should be monitored after merge.
````

## How Anthropic used this technique

Read what Anthropic changed and follow the original sources.

### Anthropic: Give each parallel agent its own checkout and a claimed task

In Anthropic's C compiler project, each agent runs in its own Docker container, clones the shared repository to its own workspace and pushes from there. An agent takes a lock on a task by writing a text file to current_tasks/, so git's synchronization forces a second agent that claims the same task to pick a different one. Bun's Rust port split its work into 4 workflow shards, each in its own worktree and running 16 Claudes, and told the agents to avoid git stash, git reset and any git command beyond committing specific files.

Evidence: Documented technique

Use it when: Several agents push to one repository, or two agents pick up the same task.

Before applying it: Task locks are plain files in the repository, so merge conflicts are frequent and the agents resolve them. Keep slow shared commands out of the agents' loop.

[Read more in the Anthropic playbook](https://starsling.dev/ci-playbooks/anthropic#isolated-agent-checkouts)

[Primary source](https://www.anthropic.com/research/building-c-compiler)

## CI optimization is continuous work.

Apply this technique yourself, or use StarSling Runners for faster GitHub Actions and optional agent-driven optimization PRs, which teams on eligible paid plans can turn on.

[Get self-improving CI](https://starsling.dev/products/runners)

## Company Playbooks

### [Anthropic](https://starsling.dev/ci-playbooks/anthropic)

Run only affected tests

### [DoorDash](https://starsling.dev/ci-playbooks/doordash)

Run build and test in parallel, sharded across CI agents

### [Linear](https://starsling.dev/ci-playbooks/linear)

Benchmark the same job on faster hardware

### [Mastra](https://starsling.dev/ci-playbooks/mastra)

StarSling runners for the slowest test workflow

### [OpenAI](https://starsling.dev/ci-playbooks/openai)

Rank CI fixes by the minutes they save

### [Ramp](https://starsling.dev/ci-playbooks/ramp)

Move a CPU-bound test suite to a faster CPU

### [Shopify](https://starsling.dev/ci-playbooks/shopify)

Let an agent iterate against one CI metric

### [Spotify](https://starsling.dev/ci-playbooks/spotify)

Build arm64 on native arm64 runners

### [Stripe](https://starsling.dev/ci-playbooks/stripe)

Run only the tests a change can reach

### [Uber](https://starsling.dev/ci-playbooks/uber)

Build the merge-queue speculations most likely to be needed