# AGENTS.md — Build guide for Raycast Pro

## Project scope
Build a macOS command palette for the owner's chosen actions, with fuzzy search, safe snippets and opt-in local history. Add a model shortcut that previews the selected text before sending it remotely.

Catalogue verdict: kinda. A personal launcher command or menubar utility is buildable, but Raycast's native polish, extension ecosystem, sync, AI, and Mac integration take serious product work.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- macOS, Xcode and a selected deployment target. Ask for each OS permission only when its feature is enabled; code signing and distribution are separate release tasks.
- Implementation components: Swift, SwiftUI and focused AppKit integrations for a macOS utility. SQLite or Codable files for local settings and history; macOS Keychain for credentials.
- Scope boundary: extension ecosystem; store/discovery

## Stack and architecture
- Swift, SwiftUI and focused AppKit integrations for a macOS utility.
- SQLite or Codable files for local settings and history; macOS Keychain for credentials.
- Domain model: allowlisted commands, command arguments, snippet templates, clipboard preferences and optional AI request receipts

## Security and data integrity
- Start capture or automation paused. Respect denied permissions, exclude secure fields and sensitive applications, and expose a visible pause/stop control.
- Correctness boundary: Commands require typed argument validation and a fixed executable policy; clipboard secrets and arbitrary downloaded extensions are excluded.
- Keep UI state on the main actor, cancel obsolete background tasks, and avoid blocking system callbacks. Record only the selected feature scope, with clear retention controls.
- Export settings and explicitly selected history without secrets. Preserve the last working configuration and provide a reset that does not delete user source files.

## Agent implementation rules
- Project rule — data model: allowlisted commands, command arguments, snippet templates, clipboard preferences and optional AI request receipts
- Project rule — preserve this invariant: Commands require typed argument validation and a fixed executable policy; clipboard secrets and arbitrary downloaded extensions are excluded.
- Project rule — acceptance evidence: A command with malicious shell characters is passed as data or rejected; cancelling the AI preview sends no request and leaves the clipboard intact.

## Optional agent skills and references
- Optional external skill: [swiftui-expert-skill](https://github.com/AvdLee/SwiftUI-Agent-Skill/blob/main/skills/swiftui-expert-skill/SKILL.md) — Build and review native SwiftUI views, state management, navigation, accessibility and rendering performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [swift-concurrency](https://github.com/AvdLee/Swift-Concurrency-Agent-Skill/blob/main/skills/swift-concurrency/SKILL.md) — Design Swift async tasks, actors, isolation, cancellation and safe data sharing, including Swift 6 migration. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.

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 the actual Raycast Pro-inspired workflow with owned or clearly labeled sample data: Build a macOS command palette for the owner's chosen actions, with fuzzy search, safe snippets and opt-in local history. Add a model shortcut that previews the selected text before sending it remotely.
- Publish a reproducible walkthrough with this observable result: A command with malicious shell characters is passed as data or rejected; cancelling the AI preview sends no request and leaves the clipboard intact.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: extension ecosystem; store/discovery Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Build a macOS command palette for the owner's chosen actions, with fuzzy search, safe snippets and opt-in local history. Add a model shortcut that previews the selected text before sending it remotely. Record prerequisites, select representative user-owned fixtures and document the unsupported features: extension ecosystem; store/discovery
2. Phase 2 — Durable model. Model allowlisted commands, command arguments, snippet templates, clipboard preferences and optional AI request receipts Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Commands require typed argument validation and a fixed executable policy; clipboard secrets and arbitrary downloaded extensions are excluded.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Keep UI state on the main actor, cancel obsolete background tasks, and avoid blocking system callbacks. Record only the selected feature scope, with clear retention controls.
4. Phase 4 — Permissions and integration failure. Start capture or automation paused. Respect denied permissions, exclude secure fields and sensitive applications, and expose a visible pause/stop control. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export settings and explicitly selected history without secrets. Preserve the last working configuration and provide a reset that does not delete user source files. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. A command with malicious shell characters is passed as data or rejected; cancelling the AI preview sends no request and leaves the clipboard intact. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

## Paid-product capabilities outside this build
- extension ecosystem
- store/discovery
- native speed
- cloud sync
- team/shared snippets
- polished AI commands

## Implementation prompt
WORKING SLICE
Build a macOS command palette for the owner's chosen actions, with fuzzy search, safe snippets and opt-in local history. Add a model shortcut that previews the selected text before sending it remotely.

Build this scoped Raycast Pro-inspired workflow with a documented data model and visible failure states.

Architecture
- Swift, SwiftUI and focused AppKit integrations for a macOS utility.
- SQLite or Codable files for local settings and history; macOS Keychain for credentials.

Prerequisites and limits
macOS, Xcode and a selected deployment target. Ask for each OS permission only when its feature is enabled; code signing and distribution are separate release tasks.
Outside this release: extension ecosystem; store/discovery

Data model and correctness
allowlisted commands, command arguments, snippet templates, clipboard preferences and optional AI request receipts
Invariant: Commands require typed argument validation and a fixed executable policy; clipboard secrets and arbitrary downloaded extensions are excluded.
Keep UI state on the main actor, cancel obsolete background tasks, and avoid blocking system callbacks. Record only the selected feature scope, with clear retention controls.

Security and privacy
Start capture or automation paused. Respect denied permissions, exclude secure fields and sensitive applications, and expose a visible pause/stop control.

Recovery and export
Export settings and explicitly selected history without secrets. Preserve the last working configuration and provide a reset that does not delete user source files.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Build a macOS command palette for the owner's chosen actions, with fuzzy search, safe snippets and opt-in local history. Add a model shortcut that previews the selected text before sending it remotely. Record prerequisites, select representative user-owned fixtures and document the unsupported features: extension ecosystem; store/discovery
2. Phase 2 — Durable model. Model allowlisted commands, command arguments, snippet templates, clipboard preferences and optional AI request receipts Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Commands require typed argument validation and a fixed executable policy; clipboard secrets and arbitrary downloaded extensions are excluded.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Keep UI state on the main actor, cancel obsolete background tasks, and avoid blocking system callbacks. Record only the selected feature scope, with clear retention controls.
4. Phase 4 — Permissions and integration failure. Start capture or automation paused. Respect denied permissions, exclude secure fields and sensitive applications, and expose a visible pause/stop control. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export settings and explicitly selected history without secrets. Preserve the last working configuration and provide a reset that does not delete user source files. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. A command with malicious shell characters is passed as data or rejected; cancelling the AI preview sends no request and leaves the clipboard intact. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
A command with malicious shell characters is passed as data or rejected; cancelling the AI preview sends no request and leaves the clipboard intact.
Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees.

Optional agent guidance
Optional external skill: [swiftui-expert-skill](https://github.com/AvdLee/SwiftUI-Agent-Skill/blob/main/skills/swiftui-expert-skill/SKILL.md) — Build and review native SwiftUI views, state management, navigation, accessibility and rendering performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [swift-concurrency](https://github.com/AvdLee/Swift-Concurrency-Agent-Skill/blob/main/skills/swift-concurrency/SKILL.md) — Design Swift async tasks, actors, isolation, cancellation and safe data sharing, including Swift 6 migration. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: allowlisted commands, command arguments, snippet templates, clipboard preferences and optional AI request receipts
Project rule — preserve this invariant: Commands require typed argument validation and a fixed executable policy; clipboard secrets and arbitrary downloaded extensions are excluded.
Project rule — acceptance evidence: A command with malicious shell characters is passed as data or rejected; cancelling the AI preview sends no request and leaves the clipboard intact.

## 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.