# AGENTS.md — Build guide for Timing ## Project scope Track app-level activity locally with a visible pause control, detect idle periods and let the user classify blocks into projects. Keep detailed titles opt-in and export reviewed time totals. Catalogue verdict: yes. The core loop is small enough for a capable coding agent to produce a useful local version in one sitting. For Timing, track Mac application activity privately and assign blocks to projects. The hard boundary is deep macos automation, rules, sync, calendar integration, and reporting polish, plus ubiquitous capture, coaching, and team workflow. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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: deep macOS automation, rules, sync, calendar integration, and reporting polish; cross-device history ## 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: foreground-app observations, optional selected window titles, idle intervals, classification rules and reviewed time blocks ## Security and data integrity - Keep observation local and visibly pausable. Record app identity only by default; selected window titles are opt-in and sensitive apps can be excluded. Never capture keystrokes or screen pixels, and make retention/deletion remove derived search and report data as well as raw observations. - Correctness boundary: No keystroke or screen capture is needed; idle time and overlapping observations cannot inflate billable time. - 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: foreground-app observations, optional selected window titles, idle intervals, classification rules and reviewed time blocks - Project rule — preserve this invariant: No keystroke or screen capture is needed; idle time and overlapping observations cannot inflate billable time. - Project rule — acceptance evidence: Lock the Mac during a running observation and mark the interval idle; delete a sensitive block and remove its title from search and exports. ## 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 Timing-inspired workflow with owned or clearly labeled sample data: Track app-level activity locally with a visible pause control, detect idle periods and let the user classify blocks into projects. Keep detailed titles opt-in and export reviewed time totals. - Publish a reproducible walkthrough with this observable result: Lock the Mac during a running observation and mark the interval idle; delete a sensitive block and remove its title from search and exports. - Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: deep macOS automation, rules, sync, calendar integration, and reporting polish; cross-device history Avoid guaranteed savings, performance scores or implied endorsement. ## Engineering roadmap 1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Track app-level activity locally with a visible pause control, detect idle periods and let the user classify blocks into projects. Keep detailed titles opt-in and export reviewed time totals. Record prerequisites, select representative user-owned fixtures and document the unsupported features: deep macOS automation, rules, sync, calendar integration, and reporting polish; cross-device history 2. Phase 2 — Durable model. Model foreground-app observations, optional selected window titles, idle intervals, classification rules and reviewed time blocks Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: No keystroke or screen capture is needed; idle time and overlapping observations cannot inflate billable time. 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. Keep observation local and visibly pausable. Record app identity only by default; selected window titles are opt-in and sensitive apps can be excluded. Never capture keystrokes or screen pixels, and make retention/deletion remove derived search and report data as well as raw observations. 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. Lock the Mac during a running observation and mark the interval idle; delete a sensitive block and remove its title from search and exports. 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 - deep macOS automation, rules, sync, calendar integration, and reporting polish - cross-device history - team timesheets and payroll - behavioral datasets - blocking across every platform ## Implementation prompt WORKING SLICE Track app-level activity locally with a visible pause control, detect idle periods and let the user classify blocks into projects. Keep detailed titles opt-in and export reviewed time totals. Build this scoped Timing-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: deep macOS automation, rules, sync, calendar integration, and reporting polish; cross-device history Data model and correctness foreground-app observations, optional selected window titles, idle intervals, classification rules and reviewed time blocks Invariant: No keystroke or screen capture is needed; idle time and overlapping observations cannot inflate billable time. 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 Keep observation local and visibly pausable. Record app identity only by default; selected window titles are opt-in and sensitive apps can be excluded. Never capture keystrokes or screen pixels, and make retention/deletion remove derived search and report data as well as raw observations. 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: Track app-level activity locally with a visible pause control, detect idle periods and let the user classify blocks into projects. Keep detailed titles opt-in and export reviewed time totals. Record prerequisites, select representative user-owned fixtures and document the unsupported features: deep macOS automation, rules, sync, calendar integration, and reporting polish; cross-device history 2. Phase 2 — Durable model. Model foreground-app observations, optional selected window titles, idle intervals, classification rules and reviewed time blocks Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: No keystroke or screen capture is needed; idle time and overlapping observations cannot inflate billable time. 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. Keep observation local and visibly pausable. Record app identity only by default; selected window titles are opt-in and sensitive apps can be excluded. Never capture keystrokes or screen pixels, and make retention/deletion remove derived search and report data as well as raw observations. 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. Lock the Mac during a running observation and mark the interval idle; delete a sensitive block and remove its title from search and exports. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder. Acceptance Lock the Mac during a running observation and mark the interval idle; delete a sensitive block and remove its title from search and exports. 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: foreground-app observations, optional selected window titles, idle intervals, classification rules and reviewed time blocks Project rule — preserve this invariant: No keystroke or screen capture is needed; idle time and overlapping observations cannot inflate billable time. Project rule — acceptance evidence: Lock the Mac during a running observation and mark the interval idle; delete a sensitive block and remove its title from search and exports. ## 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.