Warp

Build the following focused alternative to Warp. This is a deliberately limited personal or small-team substitute, not parity with the paid service.

WORKING SLICE
Build a small terminal companion that groups commands/output into blocks, searches local history and offers optional command explanations before execution.

SETUP AND ARCHITECTURE
Use SwiftUI/AppKit, a system PTY bridge to one installed shell and SQLite for explicitly retained redacted command history. Prerequisites: A Mac with Xcode, one supported shell, a documented PTY integration and an optional model key only if explanations are enabled. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success.

DOMAIN MODEL AND INVARIANTS
Store TerminalSession, CommandBlock, ExitStatus and RedactedHistory; the shell remains authoritative, and proposed commands never execute merely because a model suggested them.

IMPLEMENTATION CONTRACT
Treat pasted text and model-proposed commands as untrusted until reviewed. Keep process cancellation separate from successful completion and never replay a command automatically after reconnect. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content.

APP-SPECIFIC BOUNDARY AND RECOVERY
Correct the prior repository-agent framing: start with one shell/platform and explicit execution controls. Terminal output can contain secrets; redact history and request consent before sending any context to a model.

ACCEPTANCE SCENARIO
Suggest a command containing a destructive option, cancel it and interrupt a long-running process; record the cancellation/status without claiming completion or replaying the command. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested.

DELIVERY
Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product.

PROJECT RULES FOR AGENTS.md
Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication.

# AGENTS.md — Build guide for Warp

## Project scope
Build a small terminal companion that groups commands/output into blocks, searches local history and offers optional command explanations before execution.

Catalogue verdict: kinda. The visible AI terminal loop is buildable, but a credible replacement needs more than the first screen. Warp earns its keep through model, context, integration, so expect a weekend or multi-day build and a narrower personal scope.
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
- Runtime and tools: SwiftUI/AppKit, a system PTY bridge to one installed shell and SQLite for explicitly retained redacted command history.
- Before starting: A Mac with Xcode, one supported shell, a documented PTY integration and an optional model key only if explanations are enabled.

## Stack and architecture
- SwiftUI/AppKit, a system PTY bridge to one installed shell and SQLite for explicitly retained redacted command history
- Data design: Store TerminalSession, CommandBlock, ExitStatus and RedactedHistory; the shell remains authoritative, and proposed commands never execute merely because a model suggested them.
- Setup: A Mac with Xcode, one supported shell, a documented PTY integration and an optional model key only if explanations are enabled

## Security and data integrity
- Treat pasted text and model-proposed commands as untrusted until reviewed. Keep process cancellation separate from successful completion and never replay a command automatically after reconnect.
- Correct the prior repository-agent framing: start with one shell/platform and explicit execution controls. Terminal output can contain secrets; redact history and request consent before sending any context to a model.
- Keep secrets outside client bundles and exported projects; document what leaves the device and make retention/deletion controls visible.

## Agent implementation rules
- Project rule — domain: Store TerminalSession, CommandBlock, ExitStatus and RedactedHistory; the shell remains authoritative, and proposed commands never execute merely because a model suggested them.
- Project rule — scope and recovery: Correct the prior repository-agent framing: start with one shell/platform and explicit execution controls. Terminal output can contain secrets; redact history and request consent before sending any context to a model.
- Project rule — acceptance: Suggest a command containing a destructive option, cancel it and interrupt a long-running process; record the cancellation/status without claiming completion or replaying the command.
- Project rule — delivery: document real setup commands and permissions; do not claim a build, accuracy level, performance result or security certification that has not been demonstrated.

## Optional agent skills and references
- Recommended skill: [swiftui-expert-skill](https://github.com/AvdLee/SwiftUI-Agent-Skill/blob/main/skills/swiftui-expert-skill/SKILL.md) — design native SwiftUI state, accessible controls and permission/error views for the proposed Apple-platform interface. Follow the maintainer's installation instructions and match its requirements to the chosen runtime.
- Recommended skill: [swift-concurrency](https://github.com/AvdLee/Swift-Concurrency-Agent-Skill/blob/main/skills/swift-concurrency/SKILL.md) — isolate capture, background work and UI updates, and make cancellation invalidate late callbacks. Follow the maintainer's installation instructions and match its requirements to the chosen runtime.

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 working slice using synthetic or explicitly authorized non-sensitive examples: Build a small terminal companion that groups commands/output into blocks, searches local history and offers optional command explanations before execution.
- Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Suggest a command containing a destructive option, cancel it and interrupt a long-running process; record the cancellation/status without claiming completion or replaying the command.
- State the limits before asking someone to replace their existing tool: Correct the prior repository-agent framing: start with one shell/platform and explicit execution controls. Terminal output can contain secrets; redact history and request consent before sending any context to a model.

## Engineering roadmap
1. Phase 1 — Pin the working slice and create its example input: Build a small terminal companion that groups commands/output into blocks, searches local history and offers optional command explanations before execution. Confirm setup: A Mac with Xcode, one supported shell, a documented PTY integration and an optional model key only if explanations are enabled.
2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store TerminalSession, CommandBlock, ExitStatus and RedactedHistory; the shell remains authoritative, and proposed commands never execute merely because a model suggested them.
3. Phase 3 — Connect the working view to real saved state. Treat pasted text and model-proposed commands as untrusted until reviewed. Keep process cancellation separate from successful completion and never replay a command automatically after reconnect.
4. Phase 4 — Expose the app-specific limits and recovery path in context: Correct the prior repository-agent framing: start with one shell/platform and explicit execution controls. Terminal output can contain secrets; redact history and request consent before sending any context to a model.
5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Suggest a command containing a destructive option, cancel it and interrupt a long-running process; record the cancellation/status without claiming completion or replaying the command. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

## Paid-product capabilities outside this build
- IDE-wide polish and latency
- enterprise policy, telemetry, and support
- frontier coding model quality
- large-context infrastructure

## Implementation prompt
Build the following focused alternative to Warp. This is a deliberately limited personal or small-team substitute, not parity with the paid service.

WORKING SLICE
Build a small terminal companion that groups commands/output into blocks, searches local history and offers optional command explanations before execution.

SETUP AND ARCHITECTURE
Use SwiftUI/AppKit, a system PTY bridge to one installed shell and SQLite for explicitly retained redacted command history. Prerequisites: A Mac with Xcode, one supported shell, a documented PTY integration and an optional model key only if explanations are enabled. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success.

DOMAIN MODEL AND INVARIANTS
Store TerminalSession, CommandBlock, ExitStatus and RedactedHistory; the shell remains authoritative, and proposed commands never execute merely because a model suggested them.

IMPLEMENTATION CONTRACT
Treat pasted text and model-proposed commands as untrusted until reviewed. Keep process cancellation separate from successful completion and never replay a command automatically after reconnect. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content.

APP-SPECIFIC BOUNDARY AND RECOVERY
Correct the prior repository-agent framing: start with one shell/platform and explicit execution controls. Terminal output can contain secrets; redact history and request consent before sending any context to a model.

ACCEPTANCE SCENARIO
Suggest a command containing a destructive option, cancel it and interrupt a long-running process; record the cancellation/status without claiming completion or replaying the command. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested.

DELIVERY
Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product.

PROJECT RULES FOR AGENTS.md
Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication.

## 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.