{"slug": "show-hn-mob-programming-with-ai-agents-built-on-openspec-and-opencode", "title": "Show HN: Mob programming with AI agents, built on OpenSpec and OpenCode", "summary": "Griyd launched as a spec-first development tool that turns each feature written as a spec into code and a pull request using AI agents built on OpenSpec and OpenCode. Agents read the repository and every open story on the board before writing a spec, and nothing runs until a team member presses Run; fresh agents then work through tasks on the story's own branch, writing tests alongside the code. Billing is measured in agent-hours of sandbox runtime, with model usage billed directly by the provider on the user's own keys, and the tool requires a git repository with a personal access token plus a model API key or ChatGPT subscription to start.", "body_md": "Click a story for its spec and activity or pick a goal\n\nSpec400123456789\n\nApple Pay and Google Pay buttons on the cart pageChrisSpec ready\n\nWelcome email with a 3-step setup checklistEmilySpec ready\n\nRate limit the login endpointMarcusSpec ready\n\nDark mode for the order history pageSarah\n\nWriting spec\n\nBuild300123456789\n\nChrisSave addresses for returning customersChris\n\nAddress picker in checkout\n\nEmilyInvite teammates from the empty dashboardEmily\n\nInvite form with email chips\n\nMarcusAudit log for admin actionsMarcus\n\nAudit log page for admins\n\nReview300123456789\n\nShow shipping costs before the payment stepSarah\n\nProduct tour for first-time sellersChris\n\nExport orders to CSV without breaking on accentsEmily\n\nShip400123456789\n\nGuest checkout without an accountMarcus\n\nFix the typo in the footerSarah\n\nSign in with GoogleChris\n\nOrder confirmation email redesignEmily\n\nFrom intent to pull request on one board\n\nAgents that know the whole board\n\nEach card is a story. Agents read every open story before they plan. They skip work another story already covers.\n\nWrite the story\n\nDescribe the change the way you would brief a colleague and @mention whoever should weigh in. Got a bigger goal? An agent can break it into stories. You can also send them in from any tool through the project webhook.\n\nRead more\n\nChrisSave addresses for returning customersChris\n\nAddress picker in checkout\n\nEmilyInvite teammates from the empty dashboardEmily\n\nInvite form with email chips\n\nMarcusAudit log for admin actionsMarcus\n\nAudit log page for admins\n\nApple Pay and Google Pay buttons on the cart pageChrisSpec ready\n\nRate limit the login endpointMarcusSpec ready\n\nDark mode for the order history pageSarah\n\nWriting spec\n\nShow shipping costs before the payment stepSarah\n\nExport orders to CSV without breaking on accentsEmily\n\nGuest checkout without an accountMarcus\n\nFix the typo in the footerSarah\n\nSign in with GoogleChris\n\nOrder confirmation email redesignEmily\n\nShip features by writing specs\n\nGriyd is spec-first. Your whole team writes each feature as a spec. Agents turn the spec into code and a pull request.\n\nAn agent writes the spec\n\nYour agent reads the repository and every open story on the board. Then your agent writes the spec with OpenSpec. It covers what will change, the scenarios that prove it works and the tasks to get there. Not quite right? “Keep the old checkout behind a flag.” Your agent revises the spec.\n\nAgree on it, then Run\n\nNothing runs until someone on the team presses Run. Fresh agents work through the tasks on the story's own branch, writing tests alongside the code. Watch the terminal and steer while they work.\n\nRead more\n\nReview with the full story\n\nEvery task is checked off. Open the pull request with the whole history attached.\n\nReview the pull request\n\nBefore the story reaches Review, every scenario in the spec is checked for code and tests. The branch is pushed, with the whole record on the story. Your automatic tests have to pass too. When a test fails, your agent fixes it.\n\nAn agent-hour is an hour of sandbox runtime while an agent writes a spec, works through tasks or checks the result. Model usage is still billed directly by your provider on the keys you add.\n\nYour code stays yours\n\nYour keys\n\nPlain git\n\nThrowaway sandboxes\n\nRuns on Cloudflare\n\nFrequently asked questions\n\nWhat do we need to get started?\n\nA git repository with a personal access token, plus a model API key or a ChatGPT subscription. Add the repository as a project and write a story. The first spec arrives within minutes.\n\nDo we have to move our backlog into Griyd?\n\nNo. Your tracker stays the source of truth. Send only the work you want agents to take through the project webhook. Each request becomes a story that gets its spec right away.\n\nWhich languages and frameworks does it support?\n\nAny. Your agent reads the repository first so the changes follow your structure and conventions. Your CI checks the result the same way it checks your team's work.\n\nCan one goal span several repositories?\n\nYes. Add each repository as a project and include them in the goal. An agent drafts stories for each repository in turn. Related stories see each other's specs so the pieces fit together.\n\nDo agents know about the other stories on the board?\n\nYes. Agents read every open story before they write a spec. They leave out work that another story covers. When a story needs another one first, your agent names that story as a dependency. You can still run the story sooner.\n\nCan an agent merge or push to main?\n\nNo. Agents can only push to their own story branch. Any other push is blocked before it reaches your git host. Merging always stays with a person.\n\nWhat if the agent gets it wrong?\n\nYou review the spec before anything runs. While your agent works you can send a message or stop the run. If the pull request needs work, ask for changes on the story and run it again. Nothing merges until you merge it.\n\nDoes the agent run our tests?\n\nYour tests run on your git host like they always do. Griyd waits for the result. When a test fails, your agent reads what went wrong and fixes it. Your agent tries up to three times. The story moves to Review only once all tests pass. If a test still fails, the story shows the error.\n\nDoes Griyd keep our code or train on it?\n\nNo. Each run clones into a sandbox that is deleted when the run ends. Griyd does not train models. Your code is processed by the model provider you pick under your own key.\n\nWho on the team can do what?\n\nAdmins manage members and project settings. Members write stories, approve specs and run agents. Viewers can follow every story without changing anything.\n\nHow much does a story cost?\n\nModel tokens are billed by your provider on the key of whoever presses Run. Sandbox time is free for five hours a month per person. After that your new runs wait for next month unless you upgrade to Pro at $0.75 per agent-hour. A single run stops after an hour.", "url": "https://wpnews.pro/news/show-hn-mob-programming-with-ai-agents-built-on-openspec-and-opencode", "canonical_source": "https://griyd.com", "published_at": "2026-10-26 10:46:16+00:00", "updated_at": "2026-10-26 11:14:37.406586+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "generative-ai"], "entities": ["Griyd", "OpenSpec", "OpenCode", "Cloudflare", "ChatGPT"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-mob-programming-with-ai-agents-built-on-openspec-and-opencode", "markdown": "https://wpnews.pro/news/show-hn-mob-programming-with-ai-agents-built-on-openspec-and-opencode.md", "text": "https://wpnews.pro/news/show-hn-mob-programming-with-ai-agents-built-on-openspec-and-opencode.txt", "jsonld": "https://wpnews.pro/news/show-hn-mob-programming-with-ai-agents-built-on-openspec-and-opencode.jsonld"}}