# AGENTS.md — Build guide for Taskade

## Project scope
Organize a small team's work in nested lists and simple boards, capture comments and apply reusable templates. An optional agent proposes subtasks for review instead of acting autonomously.

Catalogue verdict: kinda. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Taskade, combine tasks, outlines, simple agents, and collaborative project spaces. The hard boundary is multiplayer, templates, integrations, ai agents, and cross-platform apps, plus cross-device reliability and workflow polish.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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, PostgreSQL, HTTPS for a shared deployment, and a backup destination. Begin with one workspace and explicit owner/member permissions.
- Implementation components: Next.js App Router and TypeScript for server-rendered pages and validated mutations. PostgreSQL with Drizzle migrations; Better Auth sessions for a small private workspace.
- Scope boundary: multiplayer, templates, integrations, AI agents, and cross-platform apps; perfect mobile sync

## Stack and architecture
- Next.js App Router and TypeScript for server-rendered pages and validated mutations.
- PostgreSQL with Drizzle migrations; Better Auth sessions for a small private workspace.
- Domain model: project outlines, nested tasks, assignees, due dates, template revisions and approved agent suggestions

## Security and data integrity
- Authorize every record read and mutation on the server using its workspace membership; validate payloads, protect mutations against CSRF, and escape user-authored HTML.
- Correctness boundary: AI proposals cannot assign work or execute external tools until accepted; moving a task preserves comments and completion history.
- Commit related database changes in one transaction. Use version checks for competing edits and an outbox for external notifications; retry delivery independently of saving the record.
- Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching.

## Agent implementation rules
- Project rule — data model: project outlines, nested tasks, assignees, due dates, template revisions and approved agent suggestions
- Project rule — preserve this invariant: AI proposals cannot assign work or execute external tools until accepted; moving a task preserves comments and completion history.
- Project rule — acceptance evidence: Reject a generated outline and keep the original project unchanged; moving a completed subtask between parents retains its completion date.

## Optional agent skills and references
- Optional external skill: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — Improve React and Next.js data fetching, rendering, bundle size and server performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [supabase-postgres-best-practices](https://github.com/supabase/agent-skills/blob/main/skills/supabase-postgres-best-practices/SKILL.md) — Review PostgreSQL schemas, queries, indexes, pooling, concurrency and row-level security. 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 Taskade-inspired workflow with owned or clearly labeled sample data: Organize a small team's work in nested lists and simple boards, capture comments and apply reusable templates. An optional agent proposes subtasks for review instead of acting autonomously.
- Publish a reproducible walkthrough with this observable result: Reject a generated outline and keep the original project unchanged; moving a completed subtask between parents retains its completion date.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: multiplayer, templates, integrations, AI agents, and cross-platform apps; perfect mobile sync Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Organize a small team's work in nested lists and simple boards, capture comments and apply reusable templates. An optional agent proposes subtasks for review instead of acting autonomously. Record prerequisites, select representative user-owned fixtures and document the unsupported features: multiplayer, templates, integrations, AI agents, and cross-platform apps; perfect mobile sync
2. Phase 2 — Durable model. Model project outlines, nested tasks, assignees, due dates, template revisions and approved agent suggestions Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: AI proposals cannot assign work or execute external tools until accepted; moving a task preserves comments and completion history.
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. Commit related database changes in one transaction. Use version checks for competing edits and an outbox for external notifications; retry delivery independently of saving the record.
4. Phase 4 — Permissions and integration failure. Authorize every record read and mutation on the server using its workspace membership; validate payloads, protect mutations against CSRF, and escape user-authored HTML. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Reject a generated outline and keep the original project unchanged; moving a completed subtask between parents retains its completion date. 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
- multiplayer, templates, integrations, AI agents, and cross-platform apps
- perfect mobile sync
- calendar and email integrations
- shared workspaces
- behavioral coaching polish

## Implementation prompt
WORKING SLICE
Organize a small team's work in nested lists and simple boards, capture comments and apply reusable templates. An optional agent proposes subtasks for review instead of acting autonomously.

Build this scoped Taskade-inspired workflow with a documented data model and visible failure states.

Architecture
- Next.js App Router and TypeScript for server-rendered pages and validated mutations.
- PostgreSQL with Drizzle migrations; Better Auth sessions for a small private workspace.

Prerequisites and limits
A supported Node release, PostgreSQL, HTTPS for a shared deployment, and a backup destination. Begin with one workspace and explicit owner/member permissions.
Outside this release: multiplayer, templates, integrations, AI agents, and cross-platform apps; perfect mobile sync

Data model and correctness
project outlines, nested tasks, assignees, due dates, template revisions and approved agent suggestions
Invariant: AI proposals cannot assign work or execute external tools until accepted; moving a task preserves comments and completion history.
Commit related database changes in one transaction. Use version checks for competing edits and an outbox for external notifications; retry delivery independently of saving the record.

Security and privacy
Authorize every record read and mutation on the server using its workspace membership; validate payloads, protect mutations against CSRF, and escape user-authored HTML.

Recovery and export
Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Organize a small team's work in nested lists and simple boards, capture comments and apply reusable templates. An optional agent proposes subtasks for review instead of acting autonomously. Record prerequisites, select representative user-owned fixtures and document the unsupported features: multiplayer, templates, integrations, AI agents, and cross-platform apps; perfect mobile sync
2. Phase 2 — Durable model. Model project outlines, nested tasks, assignees, due dates, template revisions and approved agent suggestions Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: AI proposals cannot assign work or execute external tools until accepted; moving a task preserves comments and completion history.
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. Commit related database changes in one transaction. Use version checks for competing edits and an outbox for external notifications; retry delivery independently of saving the record.
4. Phase 4 — Permissions and integration failure. Authorize every record read and mutation on the server using its workspace membership; validate payloads, protect mutations against CSRF, and escape user-authored HTML. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Reject a generated outline and keep the original project unchanged; moving a completed subtask between parents retains its completion date. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Reject a generated outline and keep the original project unchanged; moving a completed subtask between parents retains its completion date.
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: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — Improve React and Next.js data fetching, rendering, bundle size and server performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [supabase-postgres-best-practices](https://github.com/supabase/agent-skills/blob/main/skills/supabase-postgres-best-practices/SKILL.md) — Review PostgreSQL schemas, queries, indexes, pooling, concurrency and row-level security. 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: project outlines, nested tasks, assignees, due dates, template revisions and approved agent suggestions
Project rule — preserve this invariant: AI proposals cannot assign work or execute external tools until accepted; moving a task preserves comments and completion history.
Project rule — acceptance evidence: Reject a generated outline and keep the original project unchanged; moving a completed subtask between parents retains its completion date.

## 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.