# AGENTS.md — Build guide for Pixelcut ## Project scope Batch-remove product backgrounds, let the editor repair masks, apply a fixed catalogue template and export consistently sized assets. Catalogue verdict: kinda. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Pixelcut, batch-remove backgrounds, resize product images, and apply simple local templates. The hard boundary is mobile polish, hosted models, team assets, and api scale, plus frontier models, compute, and data. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface. - Before starting: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized. ## Stack and architecture - Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface - Data design: Store Batch, SourceAsset, MaskRevision, TemplateVersion and Output; outputs retain their source filename mapping and failed items remain distinguishable from completed ones. - Setup: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized ## Security and data integrity - Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. - Start with local segmentation plus human review. Upscaling cannot guarantee recovered real detail; templates, logos and model weights need licensing review. - 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 Batch, SourceAsset, MaskRevision, TemplateVersion and Output; outputs retain their source filename mapping and failed items remain distinguishable from completed ones. - Project rule — scope and recovery: Start with local segmentation plus human review. Upscaling cannot guarantee recovered real detail; templates, logos and model weights need licensing review. - Project rule — acceptance: Process ten images where one is corrupt and another loses a thin strap; export eight approved results, repair the strap and retry only the two affected items. - 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: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — keep the proposed React work/review views responsive and avoid unnecessary rendering or data-fetch waterfalls. 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: Batch-remove product backgrounds, let the editor repair masks, apply a fixed catalogue template and export consistently sized assets. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Process ten images where one is corrupt and another loses a thin strap; export eight approved results, repair the strap and retry only the two affected items. - State the limits before asking someone to replace their existing tool: Start with local segmentation plus human review. Upscaling cannot guarantee recovered real detail; templates, logos and model weights need licensing review. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Batch-remove product backgrounds, let the editor repair masks, apply a fixed catalogue template and export consistently sized assets. Confirm setup: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized. 2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store Batch, SourceAsset, MaskRevision, TemplateVersion and Output; outputs retain their source filename mapping and failed items remain distinguishable from completed ones. 3. Phase 3 — Connect the working view to real saved state. Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Start with local segmentation plus human review. Upscaling cannot guarantee recovered real detail; templates, logos and model weights need licensing review. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Process ten images where one is corrupt and another loses a thin strap; export eight approved results, repair the strap and retry only the two affected items. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - mobile polish, hosted models, team assets, and API scale - frontier proprietary models - hosted GPU capacity - licensed training data - moderation and fast global delivery ## Implementation prompt Build the following focused alternative to Pixelcut. This is a deliberately limited personal or small-team substitute, not parity with the paid service. WORKING SLICE Batch-remove product backgrounds, let the editor repair masks, apply a fixed catalogue template and export consistently sized assets. SETUP AND ARCHITECTURE Use Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface. Prerequisites: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized. 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 Batch, SourceAsset, MaskRevision, TemplateVersion and Output; outputs retain their source filename mapping and failed items remain distinguishable from completed ones. IMPLEMENTATION CONTRACT Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. 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 local segmentation plus human review. Upscaling cannot guarantee recovered real detail; templates, logos and model weights need licensing review. ACCEPTANCE SCENARIO Process ten images where one is corrupt and another loses a thin strap; export eight approved results, repair the strap and retry only the two affected items. 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.