# AGENTS.md — Build guide for Superscribe

## Project scope
Hold a hotkey to dictate, inspect a transcript, optionally review a cleanup diff and insert text into the intended app.

Catalogue verdict: kinda. The desktop dictation half is a solved one-sitting build with complete open-source clones to fork. The hero product is not that: live-transcribing calls on your existing iPhone number takes carrier call forwarding, a pooled Twilio number, a CallKit/PushKit softphone, and a dual-track media-stream pipeline that can only be debugged against live phone calls. And a clone gets you a transcript file, not the workspace around it: roughly 45k lines of API and web app that embed every recording, time block, and project (with synced GitHub repo context), auto-file notes and billable time to the right client, and expose it all as reports, semantic search, a public API, and an MCP server. Each piece is a documented recipe; shipping all of them integrated is the multi-week part even before telephony.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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: Swift, SwiftUI/AppKit and SQLite on macOS, with secrets in Keychain where needed.
- Before starting: A Mac, the current Xcode toolchain and a documented permission checklist; distribution signing is a separate delivery task.

## Stack and architecture
- Swift, SwiftUI/AppKit and SQLite on macOS, with secrets in Keychain where needed
- Data design: Store DictationSession, CapturedApp, TranscriptRevision and InsertAttempt; cancellation invalidates late callbacks and clipboard restoration happens only if no newer user copy occurred.
- Setup: A Mac, the current Xcode toolchain and a documented permission checklist; distribution signing is a separate delivery task

## Security and data integrity
- Ask for each operating-system permission when its feature is used. Handle denial and revocation without a loop; show permission status and keep local history deletable.
- Choose either a documented streaming provider or pinned local transcriber explicitly; never switch providers silently. Store keys in Keychain and preserve raw wording before optional model cleanup.
- 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 DictationSession, CapturedApp, TranscriptRevision and InsertAttempt; cancellation invalidates late callbacks and clipboard restoration happens only if no newer user copy occurred.
- Project rule — scope and recovery: Choose either a documented streaming provider or pinned local transcriber explicitly; never switch providers silently. Store keys in Keychain and preserve raw wording before optional model cleanup.
- Project rule — acceptance: Release the hotkey, switch apps and cancel during cleanup; do not paste into the new app or overwrite a fresh clipboard value.
- 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: Hold a hotkey to dictate, inspect a transcript, optionally review a cleanup diff and insert text into the intended app.
- Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Release the hotkey, switch apps and cancel during cleanup; do not paste into the new app or overwrite a fresh clipboard value.
- State the limits before asking someone to replace their existing tool: Choose either a documented streaming provider or pinned local transcriber explicitly; never switch providers silently. Store keys in Keychain and preserve raw wording before optional model cleanup.

## Engineering roadmap
1. Phase 1 — Pin the working slice and create its example input: Hold a hotkey to dictate, inspect a transcript, optionally review a cleanup diff and insert text into the intended app. Confirm setup: A Mac, the current Xcode toolchain and a documented permission checklist; distribution signing is a separate delivery task.
2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store DictationSession, CapturedApp, TranscriptRevision and InsertAttempt; cancellation invalidates late callbacks and clipboard restoration happens only if no newer user copy occurred.
3. Phase 3 — Connect the working view to real saved state. Ask for each operating-system permission when its feature is used. Handle denial and revocation without a loop; show permission status and keep local history deletable.
4. Phase 4 — Expose the app-specific limits and recovery path in context: Choose either a documented streaming provider or pinned local transcriber explicitly; never switch providers silently. Store keys in Keychain and preserve raw wording before optional model cleanup.
5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Release the hotkey, switch apps and cancel during cleanup; do not paste into the new app or overwrite a fresh clipboard value. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

## Paid-product capabilities outside this build
- call capture on your existing number (carrier forwarding into a CallKit softphone)
- glitch-free live word-by-word insertion tuned per app: terminals, Electron editors, browser contenteditables
- auto-filing: dictations and calls alike are matched to the right project via embeddings (enriched with GitHub repo context) plus live commit activity during the work block, so billable time lands on the right client without tagging
- the workspace around the transcripts: semantic search, invoice-ready PDF reports, CRM note drafts, a public API, and an MCP server
- Windows parity and signed, notarized auto-updating installers

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

WORKING SLICE
Hold a hotkey to dictate, inspect a transcript, optionally review a cleanup diff and insert text into the intended app.

SETUP AND ARCHITECTURE
Use Swift, SwiftUI/AppKit and SQLite on macOS, with secrets in Keychain where needed. Prerequisites: A Mac, the current Xcode toolchain and a documented permission checklist; distribution signing is a separate delivery task. 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 DictationSession, CapturedApp, TranscriptRevision and InsertAttempt; cancellation invalidates late callbacks and clipboard restoration happens only if no newer user copy occurred.

IMPLEMENTATION CONTRACT
Ask for each operating-system permission when its feature is used. Handle denial and revocation without a loop; show permission status and keep local history deletable. 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
Choose either a documented streaming provider or pinned local transcriber explicitly; never switch providers silently. Store keys in Keychain and preserve raw wording before optional model cleanup.

ACCEPTANCE SCENARIO
Release the hotkey, switch apps and cancel during cleanup; do not paste into the new app or overwrite a fresh clipboard value. 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.