# AGENTS.md — Build guide for Aurelius ## Project scope Import interview notes, highlight exact evidence, apply a small codebook, group highlights into themes and publish an internal insight report with source links. Catalogue verdict: kinda. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Aurelius, organize interview notes, code excerpts, and synthesize themes into findings. The hard boundary is research-specific tagging, collaboration, reporting, and import workflows, plus participant network, synthesis workflow, and collaboration. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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 Study, ParticipantAlias, SourceRevision, HighlightRange, Code and Insight; every insight links to supporting and contradictory excerpts, with source revisions retained when text changes. - 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. - Keep participant identity separate from report aliases and require redaction review before sharing. Frequency counts describe this study's sample, not population prevalence. - 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 Study, ParticipantAlias, SourceRevision, HighlightRange, Code and Insight; every insight links to supporting and contradictory excerpts, with source revisions retained when text changes. - Project rule — scope and recovery: Keep participant identity separate from report aliases and require redaction review before sharing. Frequency counts describe this study's sample, not population prevalence. - Project rule — acceptance: Edit an interview after coding it; old highlights retain their quoted evidence and are marked stale rather than shifting silently onto different sentences. - 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: Import interview notes, highlight exact evidence, apply a small codebook, group highlights into themes and publish an internal insight report with source links. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Edit an interview after coding it; old highlights retain their quoted evidence and are marked stale rather than shifting silently onto different sentences. - State the limits before asking someone to replace their existing tool: Keep participant identity separate from report aliases and require redaction review before sharing. Frequency counts describe this study's sample, not population prevalence. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Import interview notes, highlight exact evidence, apply a small codebook, group highlights into themes and publish an internal insight report with source links. 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 Study, ParticipantAlias, SourceRevision, HighlightRange, Code and Insight; every insight links to supporting and contradictory excerpts, with source revisions retained when text changes. 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: Keep participant identity separate from report aliases and require redaction review before sharing. Frequency counts describe this study's sample, not population prevalence. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Edit an interview after coding it; old highlights retain their quoted evidence and are marked stale rather than shifting silently onto different sentences. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - research-specific tagging, collaboration, reporting, and import workflows - large participant panel - recording and transcription infrastructure - advanced research repository - enterprise governance ## Implementation prompt Build the following focused alternative to Aurelius. This is a deliberately limited personal or small-team substitute, not parity with the paid service. WORKING SLICE Import interview notes, highlight exact evidence, apply a small codebook, group highlights into themes and publish an internal insight report with source links. 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 Study, ParticipantAlias, SourceRevision, HighlightRange, Code and Insight; every insight links to supporting and contradictory excerpts, with source revisions retained when text changes. 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 Keep participant identity separate from report aliases and require redaction review before sharing. Frequency counts describe this study's sample, not population prevalence. ACCEPTANCE SCENARIO Edit an interview after coding it; old highlights retain their quoted evidence and are marked stale rather than shifting silently onto different sentences. 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.