# AGENTS.md — Build guide for AirHelp ## Project scope Organize a flight disruption case, record the route and known facts, show a possible compensation tier with unresolved questions, and produce an editable claim-letter draft. Keep official-source links and user-entered escalation reminders with the case. Catalogue verdict: kinda. A useful personal organizer is buildable, but AirHelp is more than the visible intake form. A local app can assess EC261 and UK261 eligibility, organize evidence, draft letters, and track deadlines. It cannot responsibly reproduce AirHelp's managed airline correspondence, cross-jurisdictional legal judgment, funded court action, and professional accountability in one sitting. This is a credible personal substitute for straightforward self-service claims, not a full replacement. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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 - A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first. User-entered journey facts, evidence files and selected current official passenger-rights sources. No scraping, law-firm integration or model key is needed. - Implementation components: Node.js, TypeScript and Express with server-rendered HTML and small browser modules. SQLite through better-sqlite3 with migrations, prepared statements and a single background worker. - Scope boundary: No legal representation, airline negotiation, funded litigation or guaranteed compensation. ## Stack and architecture - Node.js, TypeScript and Express with server-rendered HTML and small browser modules. - SQLite through better-sqlite3 with migrations, prepared statements and a single background worker. - Domain model: journeys, flight legs, passengers, disruptions, evidence, source-versioned EU/UK rule packs and correspondence ## Security and data integrity - Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. - Correctness boundary: Unknown facts stay unknown; rule packs require an explicit source/date and cannot manufacture eligibility, legal advice or deadlines. - Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. - Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. ## Agent implementation rules - Project rule — data model: journeys, flight legs, passengers, disruptions, evidence, source-versioned EU/UK rule packs and correspondence - Project rule — preserve this invariant: Unknown facts stay unknown; rule packs require an explicit source/date and cannot manufacture eligibility, legal advice or deadlines. - Project rule — acceptance evidence: An incomplete multi-leg journey cannot receive a definitive eligibility result; editing the arrival delay changes the explainable advisory result without altering evidence. ## Optional agent skills and references - 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 AirHelp-inspired workflow with owned or clearly labeled sample data: Organize a flight disruption case, record the route and known facts, show a possible compensation tier with unresolved questions, and produce an editable claim-letter draft. Keep official-source links and user-entered escalation reminders with the case. - Publish a reproducible walkthrough with this observable result: An incomplete multi-leg journey cannot receive a definitive eligibility result; editing the arrival delay changes the explainable advisory result without altering evidence. - Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: No legal representation, airline negotiation, funded litigation or guaranteed compensation. Avoid guaranteed savings, performance scores or implied endorsement. ## Engineering roadmap 1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Organize a flight disruption case, record the route and known facts, show a possible compensation tier with unresolved questions, and produce an editable claim-letter draft. Keep official-source links and user-entered escalation reminders with the case. Record prerequisites, select representative user-owned fixtures and document the unsupported features: No legal representation, airline negotiation, funded litigation or guaranteed compensation. 2. Phase 2 — Durable model. Model journeys, flight legs, passengers, disruptions, evidence, source-versioned EU/UK rule packs and correspondence Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Unknown facts stay unknown; rule packs require an explicit source/date and cannot manufacture eligibility, legal advice or deadlines. 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. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. 4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results. 5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README. 6. Phase 6 — Acceptance scenarios. An incomplete multi-leg journey cannot receive a definitive eligibility result; editing the arrival delay changes the explainable advisory result without altering evidence. 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 - AirHelp staff handling airline correspondence and negotiation - case-specific legal judgment across jurisdictions - lawyer access and funded legal action under a no-win, no-fee model - commercial flight, weather, and disruption data used to validate claims - professional support and accountability when a claim becomes contested ## Implementation prompt WORKING SLICE Organize a flight disruption case, record the route and known facts, show a possible compensation tier with unresolved questions, and produce an editable claim-letter draft. Keep official-source links and user-entered escalation reminders with the case. Build this scoped AirHelp-inspired workflow with a documented data model and visible failure states. Architecture - Node.js, TypeScript and Express with server-rendered HTML and small browser modules. - SQLite through better-sqlite3 with migrations, prepared statements and a single background worker. Prerequisites and limits A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first. User-entered journey facts, evidence files and selected current official passenger-rights sources. No scraping, law-firm integration or model key is needed. Outside this release: No legal representation, airline negotiation, funded litigation or guaranteed compensation. Data model and correctness journeys, flight legs, passengers, disruptions, evidence, source-versioned EU/UK rule packs and correspondence Invariant: Unknown facts stay unknown; rule packs require an explicit source/date and cannot manufacture eligibility, legal advice or deadlines. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. Security and privacy Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Recovery and export Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Implementation order 1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Organize a flight disruption case, record the route and known facts, show a possible compensation tier with unresolved questions, and produce an editable claim-letter draft. Keep official-source links and user-entered escalation reminders with the case. Record prerequisites, select representative user-owned fixtures and document the unsupported features: No legal representation, airline negotiation, funded litigation or guaranteed compensation. 2. Phase 2 — Durable model. Model journeys, flight legs, passengers, disruptions, evidence, source-versioned EU/UK rule packs and correspondence Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Unknown facts stay unknown; rule packs require an explicit source/date and cannot manufacture eligibility, legal advice or deadlines. 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. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. 4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results. 5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README. 6. Phase 6 — Acceptance scenarios. An incomplete multi-leg journey cannot receive a definitive eligibility result; editing the arrival delay changes the explainable advisory result without altering evidence. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder. Acceptance An incomplete multi-leg journey cannot receive a definitive eligibility result; editing the arrival delay changes the explainable advisory result without altering evidence. 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: [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: journeys, flight legs, passengers, disruptions, evidence, source-versioned EU/UK rule packs and correspondence Project rule — preserve this invariant: Unknown facts stay unknown; rule packs require an explicit source/date and cannot manufacture eligibility, legal advice or deadlines. Project rule — acceptance evidence: An incomplete multi-leg journey cannot receive a definitive eligibility result; editing the arrival delay changes the explainable advisory result without altering evidence. ## 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.