# AGENTS.md — Build guide for Readwise

## Project scope
Import user-exported highlights, preserve their source locations and schedule a modest daily review. Let the reader annotate or archive a highlight and export selected notes to Markdown.

Catalogue verdict: kinda. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Readwise, import highlights from user-exported files, review them with spaced repetition, and export notes. The hard boundary is broad source integrations, sync, daily review polish, and knowledge-tool exports, plus capture polish, sync, and content partnerships.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first.
- Implementation components: Node.js, TypeScript and Express with server-rendered HTML and small browser modules. SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.
- Scope boundary: broad source integrations, sync, daily review polish, and knowledge-tool exports; publisher bypasses

## Stack and architecture
- Node.js, TypeScript and Express with server-rendered HTML and small browser modules.
- SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.
- Domain model: import batches, books/articles, highlight IDs, source locations, review schedules and note exports

## Security and data integrity
- Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs.
- Correctness boundary: Repeated imports are deduplicated by source identity and content; a review schedule cannot manufacture reading progress.
- Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
- Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data.

## Agent implementation rules
- Project rule — data model: import batches, books/articles, highlight IDs, source locations, review schedules and note exports
- Project rule — preserve this invariant: Repeated imports are deduplicated by source identity and content; a review schedule cannot manufacture reading progress.
- Project rule — acceptance evidence: Import the same book export twice and retain one copy of each highlight; correcting a source location updates future exports without resetting review history.

## Optional agent skills and references
- Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. 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 Readwise-inspired workflow with owned or clearly labeled sample data: Import user-exported highlights, preserve their source locations and schedule a modest daily review. Let the reader annotate or archive a highlight and export selected notes to Markdown.
- Publish a reproducible walkthrough with this observable result: Import the same book export twice and retain one copy of each highlight; correcting a source location updates future exports without resetting review history.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: broad source integrations, sync, daily review polish, and knowledge-tool exports; publisher bypasses Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Import user-exported highlights, preserve their source locations and schedule a modest daily review. Let the reader annotate or archive a highlight and export selected notes to Markdown. Record prerequisites, select representative user-owned fixtures and document the unsupported features: broad source integrations, sync, daily review polish, and knowledge-tool exports; publisher bypasses
2. Phase 2 — Durable model. Model import batches, books/articles, highlight IDs, source locations, review schedules and note exports Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Repeated imports are deduplicated by source identity and content; a review schedule cannot manufacture reading progress.
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. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Import the same book export twice and retain one copy of each highlight; correcting a source location updates future exports without resetting review history. 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
- broad source integrations, sync, daily review polish, and knowledge-tool exports
- publisher bypasses
- cross-device mobile capture
- high-quality recommendation graph
- licensed full-text feeds

## Implementation prompt
WORKING SLICE
Import user-exported highlights, preserve their source locations and schedule a modest daily review. Let the reader annotate or archive a highlight and export selected notes to Markdown.

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

Architecture
- Node.js, TypeScript and Express with server-rendered HTML and small browser modules.
- SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.

Prerequisites and limits
A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first.
Outside this release: broad source integrations, sync, daily review polish, and knowledge-tool exports; publisher bypasses

Data model and correctness
import batches, books/articles, highlight IDs, source locations, review schedules and note exports
Invariant: Repeated imports are deduplicated by source identity and content; a review schedule cannot manufacture reading progress.
Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.

Security and privacy
Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs.

Recovery and export
Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Import user-exported highlights, preserve their source locations and schedule a modest daily review. Let the reader annotate or archive a highlight and export selected notes to Markdown. Record prerequisites, select representative user-owned fixtures and document the unsupported features: broad source integrations, sync, daily review polish, and knowledge-tool exports; publisher bypasses
2. Phase 2 — Durable model. Model import batches, books/articles, highlight IDs, source locations, review schedules and note exports Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Repeated imports are deduplicated by source identity and content; a review schedule cannot manufacture reading progress.
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. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Import the same book export twice and retain one copy of each highlight; correcting a source location updates future exports without resetting review history. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Import the same book export twice and retain one copy of each highlight; correcting a source location updates future exports without resetting review history.
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: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. 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: import batches, books/articles, highlight IDs, source locations, review schedules and note exports
Project rule — preserve this invariant: Repeated imports are deduplicated by source identity and content; a review schedule cannot manufacture reading progress.
Project rule — acceptance evidence: Import the same book export twice and retain one copy of each highlight; correcting a source location updates future exports without resetting review history.

## 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.