# AGENTS.md — Build guide for GatherOS

## Project scope
Capture user-selected images, files and URLs into a private inspiration library. Browse a masonry grid, group assets into boards and search tags or extracted colors; semantic tagging is an optional local job.

Catalogue verdict: kinda. GatherOS's solo library is buildable, but a credible replacement is a weekend or multi-day project rather than a one-shot form. The visible grid, collections, tags, palettes, local SQLite files, and a basic board are approachable. The harder gaps are native macOS capture, the browser extension, X/Instagram/Cosmos imports, semantic AI, and interaction polish. A narrow local app is useful; call it a personal substitute, not feature parity.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- Node and the Rust toolchain, a supported desktop build environment and an explicitly selected data folder. Remote sync is outside the initial scope.
- Implementation components: Tauri, React and TypeScript for the desktop interface with a narrowly scoped Rust filesystem bridge. SQLite for structured state and search; user-owned files for original documents and attachments.
- Scope boundary: X, Instagram, and Cosmos bookmark imports with their platform-specific backfill and dedup pipelines; the browser extension and native messaging bridge for one-click capture from any site

## Stack and architecture
- Tauri, React and TypeScript for the desktop interface with a narrowly scoped Rust filesystem bridge.
- SQLite for structured state and search; user-owned files for original documents and attachments.
- Domain model: asset hashes, original files, source URLs, tags, palettes, collections and spatial board positions

## Security and data integrity
- Limit Tauri capabilities to selected folders and commands. Render imported content without executable HTML, and never expose arbitrary shell execution to the webview.
- Correctness boundary: Deduplication references an existing asset without deleting originals; search indexes are disposable and generated tags remain editable.
- Save edits atomically with stable IDs and revision history. Detect external file changes and offer a conflict copy instead of last-write-wins data loss.
- Provide a portable folder export with a JSON manifest and original files. Restore to a separate folder; rebuild disposable indexes from sources.

## Agent implementation rules
- Project rule — data model: asset hashes, original files, source URLs, tags, palettes, collections and spatial board positions
- Project rule — preserve this invariant: Deduplication references an existing asset without deleting originals; search indexes are disposable and generated tags remain editable.
- Project rule — acceptance evidence: Import the same image from two folders and preserve both provenance paths; rebuilding the index retains manual tags and collection positions.

## Optional agent skills and references
- Optional external skill: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — Improve React and Next.js data fetching, rendering, bundle size and server performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- 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 GatherOS-inspired workflow with owned or clearly labeled sample data: Capture user-selected images, files and URLs into a private inspiration library. Browse a masonry grid, group assets into boards and search tags or extracted colors; semantic tagging is an optional local job.
- Publish a reproducible walkthrough with this observable result: Import the same image from two folders and preserve both provenance paths; rebuilding the index retains manual tags and collection positions.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: X, Instagram, and Cosmos bookmark imports with their platform-specific backfill and dedup pipelines; the browser extension and native messaging bridge for one-click capture from any site Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Capture user-selected images, files and URLs into a private inspiration library. Browse a masonry grid, group assets into boards and search tags or extracted colors; semantic tagging is an optional local job. Record prerequisites, select representative user-owned fixtures and document the unsupported features: X, Instagram, and Cosmos bookmark imports with their platform-specific backfill and dedup pipelines; the browser extension and native messaging bridge for one-click capture from any site
2. Phase 2 — Durable model. Model asset hashes, original files, source URLs, tags, palettes, collections and spatial board positions Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Deduplication references an existing asset without deleting originals; search indexes are disposable and generated tags remain editable.
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. Save edits atomically with stable IDs and revision history. Detect external file changes and offer a conflict copy instead of last-write-wins data loss.
4. Phase 4 — Permissions and integration failure. Limit Tauri capabilities to selected folders and commands. Render imported content without executable HTML, and never expose arbitrary shell execution to the webview. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Provide a portable folder export with a JSON manifest and original files. Restore to a separate folder; rebuild disposable indexes from sources. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Import the same image from two folders and preserve both provenance paths; rebuilding the index retains manual tags and collection positions. 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
- X, Instagram, and Cosmos bookmark imports with their platform-specific backfill and dedup pipelines
- the browser extension and native messaging bridge for one-click capture from any site
- the finished AI pipeline's provider maintenance and results without supplying my own OpenAI key
- the mature Spaces canvas, presentation mode, and board export polish
- mobile clients, multi-device sync, and long-term update and support plumbing

## Implementation prompt
WORKING SLICE
Capture user-selected images, files and URLs into a private inspiration library. Browse a masonry grid, group assets into boards and search tags or extracted colors; semantic tagging is an optional local job.

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

Architecture
- Tauri, React and TypeScript for the desktop interface with a narrowly scoped Rust filesystem bridge.
- SQLite for structured state and search; user-owned files for original documents and attachments.

Prerequisites and limits
Node and the Rust toolchain, a supported desktop build environment and an explicitly selected data folder. Remote sync is outside the initial scope.
Outside this release: X, Instagram, and Cosmos bookmark imports with their platform-specific backfill and dedup pipelines; the browser extension and native messaging bridge for one-click capture from any site

Data model and correctness
asset hashes, original files, source URLs, tags, palettes, collections and spatial board positions
Invariant: Deduplication references an existing asset without deleting originals; search indexes are disposable and generated tags remain editable.
Save edits atomically with stable IDs and revision history. Detect external file changes and offer a conflict copy instead of last-write-wins data loss.

Security and privacy
Limit Tauri capabilities to selected folders and commands. Render imported content without executable HTML, and never expose arbitrary shell execution to the webview.

Recovery and export
Provide a portable folder export with a JSON manifest and original files. Restore to a separate folder; rebuild disposable indexes from sources.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Capture user-selected images, files and URLs into a private inspiration library. Browse a masonry grid, group assets into boards and search tags or extracted colors; semantic tagging is an optional local job. Record prerequisites, select representative user-owned fixtures and document the unsupported features: X, Instagram, and Cosmos bookmark imports with their platform-specific backfill and dedup pipelines; the browser extension and native messaging bridge for one-click capture from any site
2. Phase 2 — Durable model. Model asset hashes, original files, source URLs, tags, palettes, collections and spatial board positions Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Deduplication references an existing asset without deleting originals; search indexes are disposable and generated tags remain editable.
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. Save edits atomically with stable IDs and revision history. Detect external file changes and offer a conflict copy instead of last-write-wins data loss.
4. Phase 4 — Permissions and integration failure. Limit Tauri capabilities to selected folders and commands. Render imported content without executable HTML, and never expose arbitrary shell execution to the webview. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Provide a portable folder export with a JSON manifest and original files. Restore to a separate folder; rebuild disposable indexes from sources. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Import the same image from two folders and preserve both provenance paths; rebuilding the index retains manual tags and collection positions. 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 image from two folders and preserve both provenance paths; rebuilding the index retains manual tags and collection positions.
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: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — Improve React and Next.js data fetching, rendering, bundle size and server performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
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: asset hashes, original files, source URLs, tags, palettes, collections and spatial board positions
Project rule — preserve this invariant: Deduplication references an existing asset without deleting originals; search indexes are disposable and generated tags remain editable.
Project rule — acceptance evidence: Import the same image from two folders and preserve both provenance paths; rebuilding the index retains manual tags and collection positions.

## 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.