# AGENTS.md — Build guide for Mymind

## Project scope
Capture an image, URL or note into a visual library, extract available text and suggest editable tags while retaining the source.

Catalogue verdict: kinda. The mechanic is honestly simple: capture a thing, extract text and metadata, ask a model for tags, embed it, then search across everything. An agent can build that in a weekend with SQLite, a headless browser for page snapshots and one model API call per item. What you cannot one-shot is the capture surface, which is the entire product in practice: browser extensions for three browsers, an iOS and Android share sheet, and the reliability that makes you trust it with the thought you had in a queue. The taste also matters more than it should here, because the pitch is that you never organize anything, and a DIY version that mis-tags half your library quietly becomes a junk drawer. Fine build, real gaps.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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: Python, SQLite FTS5, a PDF/text extraction worker and a React evidence notebook.
- Before starting: User-owned or licensed source documents, a local data folder and an optional explicitly configured model provider.

## Stack and architecture
- Python, SQLite FTS5, a PDF/text extraction worker and a React evidence notebook
- Data design: Store Capture, ContentHash, ExtractedText, SuggestedTag and UserTag; rejecting a tag persists across later model runs and duplicate captures preserve original provenance.
- Setup: User-owned or licensed source documents, a local data folder and an optional explicitly configured model provider

## Security and data integrity
- Preserve source hashes, page/section anchors and exact quotations. OCR and optional generated summaries are derived views, never replacements for originals; label missing text and unsupported claims.
- Start with keyword search and local assets. Optional vision/embedding services require explicit disclosure, and generated tags must not infer sensitive personal traits.
- 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 Capture, ContentHash, ExtractedText, SuggestedTag and UserTag; rejecting a tag persists across later model runs and duplicate captures preserve original provenance.
- Project rule — scope and recovery: Start with keyword search and local assets. Optional vision/embedding services require explicit disclosure, and generated tags must not infer sensitive personal traits.
- Project rule — acceptance: Save the same image twice, reject an incorrect model tag and search by exact text; deduplicate the asset and keep the rejected tag out of future suggestions.
- 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: [modern-python](https://github.com/trailofbits/skills/blob/main/plugins/modern-python/skills/modern-python/SKILL.md) — structure the Python worker or explicitly optional read-only utility with pinned dependencies, typed boundaries and clear failure handling. Follow the maintainer's installation instructions and match its requirements to the chosen runtime.
- Recommended skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — review keyboard access, focus, validation, error recovery and the readable work/review interface or HTML report. 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: Capture an image, URL or note into a visual library, extract available text and suggest editable tags while retaining the source.
- Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Save the same image twice, reject an incorrect model tag and search by exact text; deduplicate the asset and keep the rejected tag out of future suggestions.
- State the limits before asking someone to replace their existing tool: Start with keyword search and local assets. Optional vision/embedding services require explicit disclosure, and generated tags must not infer sensitive personal traits.

## Engineering roadmap
1. Phase 1 — Pin the working slice and create its example input: Capture an image, URL or note into a visual library, extract available text and suggest editable tags while retaining the source. Confirm setup: User-owned or licensed source documents, a local data folder and an optional explicitly configured model provider.
2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store Capture, ContentHash, ExtractedText, SuggestedTag and UserTag; rejecting a tag persists across later model runs and duplicate captures preserve original provenance.
3. Phase 3 — Connect the working view to real saved state. Preserve source hashes, page/section anchors and exact quotations. OCR and optional generated summaries are derived views, never replacements for originals; label missing text and unsupported claims.
4. Phase 4 — Expose the app-specific limits and recovery path in context: Start with keyword search and local assets. Optional vision/embedding services require explicit disclosure, and generated tags must not infer sensitive personal traits.
5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Save the same image twice, reject an incorrect model tag and search by exact text; deduplicate the asset and keep the rejected tag out of future suggestions. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

## Paid-product capabilities outside this build
- Real browser extensions and a mobile share sheet, so capture friction goes way up
- Image understanding that recognizes objects, art, color palettes and text in photos at Mymind's quality
- Sync across devices, plus offline capable native apps
- Serendipity features: the everything-search, the surfacing of old cards, spaced resurfacing
- Someone else's ongoing judgment about what a good tag actually is

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

WORKING SLICE
Capture an image, URL or note into a visual library, extract available text and suggest editable tags while retaining the source.

SETUP AND ARCHITECTURE
Use Python, SQLite FTS5, a PDF/text extraction worker and a React evidence notebook. Prerequisites: User-owned or licensed source documents, a local data folder and an optional explicitly configured model provider. 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 Capture, ContentHash, ExtractedText, SuggestedTag and UserTag; rejecting a tag persists across later model runs and duplicate captures preserve original provenance.

IMPLEMENTATION CONTRACT
Preserve source hashes, page/section anchors and exact quotations. OCR and optional generated summaries are derived views, never replacements for originals; label missing text and unsupported claims. 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
Start with keyword search and local assets. Optional vision/embedding services require explicit disclosure, and generated tags must not infer sensitive personal traits.

ACCEPTANCE SCENARIO
Save the same image twice, reject an incorrect model tag and search by exact text; deduplicate the asset and keep the rejected tag out of future suggestions. 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.