Hamster vs BMAD Method
BMAD Method gives your coding agent product, architecture and dev roles and sizes the planning to the change, and it’s very good at that. Hamster gives you a Brief and a Plan your agents build from, and it still works when your head of product, your designer and a second engineer all have a say.
Free for 10 Briefs a month, and viewers are always free.
The short version
BMAD Method gives you named roles for your coding agent and a planning path sized to the change, from a quick fix to a PRD with a spec per epic. Every document is markdown in your repo, and it’s free and MIT licensed.
Hamster gives you a Brief, a Plan with acceptance criteria on every task, owners who get notified, and a tracker that matches the Plan. It works when you build alone, and it keeps working when the people who have to agree don’t all have the repo checked out.
You can also run both. Hamster takes BMAD’s skills in as a Method your whole team shares.
What BMAD is good at
BMAD gives your agent a role for each part of the job. There are product, architecture, UX, dev and test perspectives, and each one writes its own document. It also sizes the planning to the change, so a small fix goes straight to build and a large initiative gets a PRD, a spec per epic and stories. Everything it writes is markdown in your repo, where the PRD and the architecture decisions sit next to the code. It installs with npx skills add bmad-code-org/BMAD-METHOD or as a Claude Code or Codex plugin, the README lists 45 or more supported coding tools, and it’s MIT licensed and free.
BMAD sizes the planning to the change, from the BMAD docs. docs.bmad-method.org, September 16, 2026
Where it gets hard with a team
Say your team is moving the API to usage-based billing. Your head of product wants metered pricing, your designer owns the billing screens, and two engineers will build it across the metering service and the web app.
Someone runs bmad-prd, and prd.md gets a section for metered pricing, with an [ASSUMPTION] tag where the skill guessed at the tiers. BMAD’s guide to planning inside an organization has reviewers read copies of the documents, while edits go into the source file and everything downstream gets regenerated from it. So your head of product and your designer review a rendering of prd.md, and their comments live wherever they left them.
The tiers get settled with finance in a Slack thread, which none of the files know about. Meanwhile sprint-status.yaml holds the sprint state, and updating Linear or Jira is a hook your team wires up. The first week someone updates the board and not the yaml, you have two versions of where the work stands.
What Hamster does instead
Your team agrees on the Brief itself
Your head of product describes metered pricing in chat, and Hamster drafts one Brief from the Slack thread with finance, the metering code and the support tickets behind it. Your designer, both engineers and finance edit that same Brief and mark it ready. Nobody reviews a copy, and the thread that settled the tiers stays attached.
Owners and a tracker that match the Plan
Hamster turns the agreed Brief into one Plan, with tasks across the metering service and the web app and acceptance criteria on every task. Each task has an owner, and a hand-off notifies the next person. The tasks sync to Linear or Jira, so your tracker and the Plan are the same list.
Every agent starts from what you agreed
Each engineer runs hamster sync, and the Brief, the Plan and your Blueprints land in .hamster/ in both repos. Claude Code, Cursor or Codex picks them up from there, and BMAD’s skills run on top of that context. When the pull request comes back, you review it against the acceptance criteria on its task.
Keep using BMAD
Nothing you’ve built gets thrown away. BMAD’s skills are SKILL.md files, and Hamster keeps skills in a library your team shares. The setup prompt pushes them into your workspace, where you group them under a Method, so everyone runs bmad-prd, bmad-spec and the rest with the same wording.
Your documents stay in the repo, and your agent runs the same skills it runs today. What changes is that they run against a Brief and a Plan you agreed on, which hamster sync puts in the repo. The facts you keep in a toml file can live in a Blueprint every agent loads.
Set up Hamster and bring BMAD along
Paste this into Claude Code, Cursor or Codex in your repo. You sign in once in the browser, and your agent does the rest.
Set up Hamster in this repo: follow https://tryhamster.com/plugin/install, then run hamster init and hamster sync. Then install BMAD Method with `npx skills add bmad-code-org/BMAD-METHOD`, make sure its skills are under .agents/skills/, and run `hamster skills sync --push-only` so they appear in my Hamster workspace. Stop when you need me to sign in.
BMAD is free. Why pay for Hamster?
BMAD is free and open source under the MIT license, and you pay only for your coding agent.
Hamster is free too, for 10 Briefs a month, and viewers are always free. After that it’s $40 per creator a month, so your head of product and your designer can read a Brief and mark it ready without a paid seat.
The $40 pays for the part BMAD leaves to convention. Owners get notified, the tracker matches the Plan, and the people who have to agree can do it without a git checkout.
| What is compared | BMAD Method | Hamster |
|---|---|---|
| Price | Free, MIT licensed. You pay for your coding agent. license | Free for 10 Briefs a month with viewers free, then $40 per creator a month. |
| Account | None. It runs from your repo. | You sign in once in the browser. |
| Where decisions live | Markdown in the repo: prd.md, ARCHITECTURE-SPINE.md and one SPEC.md per epic. | A Brief and a Plan in your workspace, synced into every clone. |
| Issue tracker | sprint-status.yaml, with Linear or Jira updated by hooks you configure. adopt BMad across a team | Tasks sync with Linear or Jira. |
Questions
- Can we use BMAD and Hamster together?
- Yes. Your agent keeps running bmad-spec, bmad-build and the rest from your repo, and the documents you already have stay where they are. Hamster supplies the Brief and the Plan those skills run against.
- I work alone. Is Hamster for me?
- Yes. Hamster drafts the Brief from your code and your tickets, and the Plan gives your agent tasks with acceptance criteria. What you decide stays on the record for the next Brief, a Cloud Agent can work the Plan for you, and it’s free for 10 Briefs a month.
- Our PM doesn’t use git. Can they still sign off?
- Yes. The Brief lives in your Hamster workspace, so your PM, your designer or a founder reads it in the browser, suggests edits and marks it ready. Viewers are free. hamster sync then puts the agreed version in the repo for your engineers and their agents.
- Does it work with the coding tools BMAD supports?
- Yes, for any agent that reads your repo. hamster sync writes the Brief and the Plan into .hamster/ as markdown, and there’s an MCP server too. BMAD’s README lists 45 or more coding tools, including Claude Code, Codex, Cursor and Copilot. BMAD-METHOD README
- Do we still need sprint-status.yaml?
- No, not to track the work. The Plan holds the tasks and syncs them to Linear or Jira, so your tracker and the Plan are the same list. Nothing in Hamster depends on the yaml file.
Agree on what to build before anyone’s agent builds it
Free for 10 Briefs a month, and viewers are always free. You set it up with one prompt in your repo.
More reading: spec-driven development for a team, GitHub Spec Kit vs Hamster and Hamster for Claude Code.
Sources, checked September 16, 2026: BMAD-METHOD README, license, choose a planning path, plan inside an organization, adopt BMad across a team. Seen something out of date? Tell us at hello@tryhamster.com.