# AGENTS.md — Build guide for Portfolio Coach

## Project scope
Enter a family portfolio, inspect allocation and compare explicitly chosen projection assumptions. Allow an optional AI explanation of the supplied numbers, with any UK tax references separately source-dated and marked for professional review.

Catalogue verdict: kinda. A private dashboard for holdings, family members, projections, and CSV imports is a credible weekend build. Reliable live pricing for UK funds, a ledger-correct Vanguard importer, household data boundaries, maintained tax rules, and AI advice grounded in every account turn the complete product into a multi-day project.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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.
- 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. Integer minor units or a decimal library for money; CSV parsers with explicit date, currency and sign mapping. Server-rendered SVG or browser Canvas charts for explicit scenario projections; no React-only chart package. An optional provider receives only a reviewed calculated summary.
- Scope boundary: Live brokerage access, investment suitability and tax filing are not implemented.

## 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.
- Integer minor units or a decimal library for money; CSV parsers with explicit date, currency and sign mapping.
- Server-rendered SVG or browser Canvas charts for explicit scenario projections; no React-only chart package. An optional provider receives only a reviewed calculated summary.
- Domain model: household members, accounts/wrappers, holdings, dated valuations, assumptions and evidence-linked review notes

## 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. No bank credentials in uploads or logs; restrict exports and backups to the owner. Never initiate transfers or infer investment suitability.
- Correctness boundary: No personalized investment or tax recommendation is inferred; unknown fees, prices and tax assumptions remain visible, and projected returns are scenarios.
- 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: household members, accounts/wrappers, holdings, dated valuations, assumptions and evidence-linked review notes
- Project rule — preserve this invariant: No personalized investment or tax recommendation is inferred; unknown fees, prices and tax assumptions remain visible, and projected returns are scenarios.
- Project rule — acceptance evidence: A holding without a current price is shown stale and excluded or explicitly estimated; changing growth assumptions never changes actual recorded balances.

## Optional agent skills and references
- Optional external skill: [xlsx](https://github.com/anthropics/skills/blob/main/skills/xlsx/SKILL.md) — Create, edit and inspect spreadsheet files, formulas, formatting and tabular imports or exports. 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.
- 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.

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 Portfolio Coach-inspired workflow with owned or clearly labeled sample data: Enter a family portfolio, inspect allocation and compare explicitly chosen projection assumptions. Allow an optional AI explanation of the supplied numbers, with any UK tax references separately source-dated and marked for professional review.
- Publish a reproducible walkthrough with this observable result: A holding without a current price is shown stale and excluded or explicitly estimated; changing growth assumptions never changes actual recorded balances.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: Live brokerage access, investment suitability and tax filing are not implemented. Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Enter a family portfolio, inspect allocation and compare explicitly chosen projection assumptions. Allow an optional AI explanation of the supplied numbers, with any UK tax references separately source-dated and marked for professional review. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Live brokerage access, investment suitability and tax filing are not implemented.
2. Phase 2 — Durable model. Model household members, accounts/wrappers, holdings, dated valuations, assumptions and evidence-linked review notes Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: No personalized investment or tax recommendation is inferred; unknown fees, prices and tax assumptions remain visible, and projected returns are scenarios.
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. No bank credentials in uploads or logs; restrict exports and backups to the owner. Never initiate transfers or infer investment suitability. 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. A holding without a current price is shown stale and excluded or explicitly estimated; changing growth assumptions never changes actual recorded balances. 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
- reliable live pricing and UK fund symbol mapping
- ledger-backed Vanguard history import
- secure cloud accounts, family sharing, and support access
- maintained UK tax and estate-planning assumptions
- hosted AI reviews with current web context

## Implementation prompt
WORKING SLICE
Enter a family portfolio, inspect allocation and compare explicitly chosen projection assumptions. Allow an optional AI explanation of the supplied numbers, with any UK tax references separately source-dated and marked for professional review.

Build this scoped Portfolio Coach-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.
- Integer minor units or a decimal library for money; CSV parsers with explicit date, currency and sign mapping.
- Server-rendered SVG or browser Canvas charts for explicit scenario projections; no React-only chart package. An optional provider receives only a reviewed calculated summary.

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.
Outside this release: Live brokerage access, investment suitability and tax filing are not implemented.

Data model and correctness
household members, accounts/wrappers, holdings, dated valuations, assumptions and evidence-linked review notes
Invariant: No personalized investment or tax recommendation is inferred; unknown fees, prices and tax assumptions remain visible, and projected returns are scenarios.
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. No bank credentials in uploads or logs; restrict exports and backups to the owner. Never initiate transfers or infer investment suitability.

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: Enter a family portfolio, inspect allocation and compare explicitly chosen projection assumptions. Allow an optional AI explanation of the supplied numbers, with any UK tax references separately source-dated and marked for professional review. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Live brokerage access, investment suitability and tax filing are not implemented.
2. Phase 2 — Durable model. Model household members, accounts/wrappers, holdings, dated valuations, assumptions and evidence-linked review notes Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: No personalized investment or tax recommendation is inferred; unknown fees, prices and tax assumptions remain visible, and projected returns are scenarios.
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. No bank credentials in uploads or logs; restrict exports and backups to the owner. Never initiate transfers or infer investment suitability. 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. A holding without a current price is shown stale and excluded or explicitly estimated; changing growth assumptions never changes actual recorded balances. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
A holding without a current price is shown stale and excluded or explicitly estimated; changing growth assumptions never changes actual recorded balances.
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: [xlsx](https://github.com/anthropics/skills/blob/main/skills/xlsx/SKILL.md) — Create, edit and inspect spreadsheet files, formulas, formatting and tabular imports or exports. 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.
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.
Project rule — data model: household members, accounts/wrappers, holdings, dated valuations, assumptions and evidence-linked review notes
Project rule — preserve this invariant: No personalized investment or tax recommendation is inferred; unknown fees, prices and tax assumptions remain visible, and projected returns are scenarios.
Project rule — acceptance evidence: A holding without a current price is shown stale and excluded or explicitly estimated; changing growth assumptions never changes actual recorded balances.

## 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.