# AGENTS.md — Build guide for Hemingway Editor Plus ## Project scope Edit local prose, highlight sentence-length/readability heuristics, review optional rewrites and export the chosen revision. Catalogue verdict: yes. The core loop is small enough for a capable coding agent to produce a useful local version in one sitting. For Hemingway Editor Plus, flag readability problems and offer optional AI rewrites inside a distraction-free editor. The hard boundary is its polished deterministic readability rules and hosted ai allowance, plus polish, integrations, and proprietary language models. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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: TypeScript, React and a Node server with SQLite for a single small workspace. - Before starting: A local Node runtime, writable data directory, sample records and a documented backup/restore path. ## Stack and architecture - TypeScript, React and a Node server with SQLite for a single small workspace - Data design: Store DocumentRevision, SentenceRange, Diagnostic and RewriteProposal; diagnostics name their heuristic and rewrites apply only when the underlying sentence revision still matches. - Setup: A local Node runtime, writable data directory, sample records and a documented backup/restore path ## Security and data integrity - Use migrations and server-side validation; expose saved, pending and failed states. Keep each write atomic and reject stale edits using a revision number. - Keep deterministic checks local and cloud rewriting opt-in. Reading-grade scores are rough signals, not proof of quality or accessibility for every reader. - 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 DocumentRevision, SentenceRange, Diagnostic and RewriteProposal; diagnostics name their heuristic and rewrites apply only when the underlying sentence revision still matches. - Project rule — scope and recovery: Keep deterministic checks local and cloud rewriting opt-in. Reading-grade scores are rough signals, not proof of quality or accessibility for every reader. - Project rule — acceptance: Revise a sentence while a rewrite is pending and include dialogue/fragments; reject stale replacement and let the writer dismiss intentional style rather than marking it objectively wrong. - 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: [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. - 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: Edit local prose, highlight sentence-length/readability heuristics, review optional rewrites and export the chosen revision. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Revise a sentence while a rewrite is pending and include dialogue/fragments; reject stale replacement and let the writer dismiss intentional style rather than marking it objectively wrong. - State the limits before asking someone to replace their existing tool: Keep deterministic checks local and cloud rewriting opt-in. Reading-grade scores are rough signals, not proof of quality or accessibility for every reader. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Edit local prose, highlight sentence-length/readability heuristics, review optional rewrites and export the chosen revision. Confirm setup: A local Node runtime, writable data directory, sample records and a documented backup/restore path. 2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store DocumentRevision, SentenceRange, Diagnostic and RewriteProposal; diagnostics name their heuristic and rewrites apply only when the underlying sentence revision still matches. 3. Phase 3 — Connect the working view to real saved state. Use migrations and server-side validation; expose saved, pending and failed states. Keep each write atomic and reject stale edits using a revision number. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Keep deterministic checks local and cloud rewriting opt-in. Reading-grade scores are rough signals, not proof of quality or accessibility for every reader. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Revise a sentence while a rewrite is pending and include dialogue/fragments; reject stale replacement and let the writer dismiss intentional style rather than marking it objectively wrong. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - its polished deterministic readability rules and hosted AI allowance - cross-device sync - large proprietary style models - browser and office-suite extensions - team style guides ## Implementation prompt Build the following focused alternative to Hemingway Editor Plus. Implement the focused workflow below first; the verdict is not evidence of a completed or production-certified build. WORKING SLICE Edit local prose, highlight sentence-length/readability heuristics, review optional rewrites and export the chosen revision. SETUP AND ARCHITECTURE Use TypeScript, React and a Node server with SQLite for a single small workspace. Prerequisites: A local Node runtime, writable data directory, sample records and a documented backup/restore path. 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 DocumentRevision, SentenceRange, Diagnostic and RewriteProposal; diagnostics name their heuristic and rewrites apply only when the underlying sentence revision still matches. IMPLEMENTATION CONTRACT Use migrations and server-side validation; expose saved, pending and failed states. Keep each write atomic and reject stale edits using a revision number. 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 deterministic checks local and cloud rewriting opt-in. Reading-grade scores are rough signals, not proof of quality or accessibility for every reader. ACCEPTANCE SCENARIO Revise a sentence while a rewrite is pending and include dialogue/fragments; reject stale replacement and let the writer dismiss intentional style rather than marking it objectively wrong. 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.