The spec layer for OpenAI Codex.
Hamster prepares scoped Tasks with the Brief and acceptance criteria that Codex needs, so you can review the resulting pull requests against the agreed requirements.
Free for 10 briefs a month.
Codex needs more than a prompt.
Async execution demands upfront clarity
An asynchronous coding run depends on the requirements supplied before it starts, so ambiguity in the Brief can become a review comment or a request to redo the work.
Feature-level work does not fit in one task
A full feature can produce a pull request that is difficult to review unless someone first breaks the work into focused Tasks.
AI output drifts from team priorities
Without a clear link between product goals and Codex tasks, AI-generated PRs solve the wrong problems or implement features nobody prioritized.
Hamster structures work for Codex.
Hamster turns your intent into a Brief and a Plan with scoped Tasks. The CLI syncs them into .hamster/ so Codex can read the reasoning and acceptance criteria alongside the code.
Self-contained specs via the CLI
The CLI syncs Briefs, Tasks, and Plans into .hamster/ as Markdown, giving an asynchronous Codex run the requirements it needs without manual copying.
Atomic task decomposition
Hamster breaks larger features into scoped Tasks with acceptance criteria, giving Codex work that can be implemented and reviewed separately.
Brief-to-PR pipeline
Hamster dispatches tasks to Codex with structured specs attached, turning the brief-to-PR pipeline into a queue that Codex processes autonomously while you focus on higher-leverage work.
How teams use Hamster with Codex
Async feature pipeline
Before
A prompt that misses edge cases can send a Codex run through another cycle of implementation and review after the missing requirements surface.
After
Hamster generates scoped Tasks from the Brief, so you can give Codex the acceptance criteria before it starts and use them to review the pull request.
Preparing a batch of Codex Tasks
Before
Preparing a batch of Codex Tasks separately repeats the context gathering and specification work for each run.
After
Hamster derives the Tasks from a shared Brief, giving each Codex run its own scope and acceptance criteria for later review.
API development
Before
An endpoint description alone can leave validation rules and edge cases out of the implementation.
After
The Brief records endpoint requirements, schemas, and validation rules so Codex can build from task-level acceptance criteria.
Give Codex a Brief your team can review against.
Use the Brief to prepare Tasks for Codex, then review its changes against the scope and acceptance criteria before shipping.
The Free plan includes 10 Briefs a month for you and your team.
Related pages
Hamster CLI
Install the CLI, sync briefs and plans into your repo, and give your coding agent full project context.
Hamster for Developers
Implementation-ready task specs for developers who ship with AI agents.
Hamster for Founders
Turn product vision into shipped features with a lean team and AI execution.
Hamster for Claude Code
Give Claude Code structured context for every agentic coding session.