Bolt.new

Build me a focused AI coding agents and developer workspaces workflow for the personal core of Bolt.new. Requirements:

- Use TypeScript, Node.js 22, a VS Code extension, SQLite, and one user-supplied model API. Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
- Paid product context: Generate and edit a small web project in a local sandbox from structured prompts. Build only this DIY scope: Generate and edit a small web project in a local sandbox from structured prompts, index the repository, propose patches, run approved commands, and preserve an auditable session log.
- For AI coding agents and developer workspaces, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
- Make changes on a branch with an inspectable diff and record each command, result, and approval.
- Run the project’s verification command and show the diff plus final status before merge or export.
- Use a browser popup or toolbar action with a saved-items view. Required input or access: VS Code; OpenAI or Anthropic API key. Keep credentials in .env.
- Recovery: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.
- Out of scope: browser sandbox, model orchestration, package execution, deployment, and hosted compute; frontier proprietary model. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for Bolt.new

## Project scope
Generate and edit a small web project in a local sandbox from structured prompts, index the repository, propose patches, run approved commands, and preserve an auditable session log.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Bolt.new, generate and edit a small web project in a local sandbox from structured prompts. The hard boundary is browser sandbox, model orchestration, package execution, deployment, and hosted compute, plus frontier models, context infrastructure, and execution safety.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- VS Code
- OpenAI or Anthropic API key
- Git repository
- local command sandbox

## Stack and architecture
- Use TypeScript, Node.js 22, a VS Code extension, SQLite, and one user-supplied model API.
- Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
- Interface for this AI coding agents and developer workspaces workflow: a browser popup or toolbar action with a saved-items view.

## Security and data integrity
- A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: browser sandbox, model orchestration, package execution, deployment, and hosted compute.

## Agent implementation rules
- Project rule, data: Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
- Project rule, behavior: For AI coding agents and developer workspaces, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
- Project rule, recovery: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this AI coding agents and developer workspaces operation with sample or user-owned data: For AI coding agents and developer workspaces, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
- Show a concrete result or export: Run the project’s verification command and show the diff plus final status before merge or export.
- State the practical limit: browser sandbox, model orchestration, package execution, deployment, and hosted compute.

## Engineering roadmap
1. Phase 1, architecture and data: Use TypeScript, Node.js 22, a VS Code extension, SQLite, and one user-supplied model API. Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
2. Phase 2, implement: For AI coding agents and developer workspaces, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
3. Phase 3, implement: Make changes on a branch with an inspectable diff and record each command, result, and approval.
4. Phase 4, review and output: Run the project’s verification command and show the diff plus final status before merge or export.
5. Phase 5, recovery and acceptance: Verify this invariant with a saved fixture: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change. State the practical limit: browser sandbox, model orchestration, package execution, deployment, and hosted compute.

## Paid-product capabilities outside this build
- browser sandbox, model orchestration, package execution, deployment, and hosted compute
- frontier proprietary model
- large-scale code retrieval
- cloud sandbox fleet
- enterprise policy and support

## Implementation prompt
Build me a focused AI coding agents and developer workspaces workflow for the personal core of Bolt.new. Requirements:

- Use TypeScript, Node.js 22, a VS Code extension, SQLite, and one user-supplied model API. Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
- Paid product context: Generate and edit a small web project in a local sandbox from structured prompts. Build only this DIY scope: Generate and edit a small web project in a local sandbox from structured prompts, index the repository, propose patches, run approved commands, and preserve an auditable session log.
- For AI coding agents and developer workspaces, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
- Make changes on a branch with an inspectable diff and record each command, result, and approval.
- Run the project’s verification command and show the diff plus final status before merge or export.
- Use a browser popup or toolbar action with a saved-items view. Required input or access: VS Code; OpenAI or Anthropic API key. Keep credentials in .env.
- Recovery: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.
- Out of scope: browser sandbox, model orchestration, package execution, deployment, and hosted compute; frontier proprietary model. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.