# AGENTS.md — Build guide for FeedHive

## Project scope
Plan social content in a calendar, adapt a draft to one connected network and optionally reuse an evergreen post only after review. AI assistance produces suggestions beside the saved original.

Catalogue verdict: kinda. The visible AI social scheduling loop is buildable, but a credible replacement needs more than the first screen. FeedHive earns its keep through platform APIs, distribution, so expect a weekend or multi-day build and a narrower personal scope.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- Credentials and the required API access for one chosen network. Verify permissions and quotas; provide an export/manual-post workflow for unsupported networks.
- 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. One official platform API adapter with declared text/media capabilities and a persisted scheduled-post worker.
- Scope boundary: analytics history and attribution; team approvals and asset workflows

## 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.
- One official platform API adapter with declared text/media capabilities and a persisted scheduled-post worker.
- Domain model: drafts, reusable content categories, platform variants, scheduled slots and reuse history

## Security and data integrity
- Keep OAuth tokens server-side and encrypt persistent tokens with a separately managed key. Publication requires an explicit approved revision and target account.
- Correctness boundary: Recycling is opt-in with a cooldown and explicit approved revision; unsupported platform analytics remain unavailable rather than zero.
- Track each target independently with pending, publishing, delivered, failed and unknown states. Reconcile a timeout using provider receipts before retrying; respect rate-limit backoff.
- 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: drafts, reusable content categories, platform variants, scheduled slots and reuse history
- Project rule — preserve this invariant: Recycling is opt-in with a cooldown and explicit approved revision; unsupported platform analytics remain unavailable rather than zero.
- Project rule — acceptance evidence: Cancel a recycled post and preserve its earlier publication receipt; changing a network limit flags queued variants before publication.

## Optional agent skills and references
- 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.
- Optional external skill: [copywriting](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md) — Write landing pages and product copy grounded in the intended audience, product value and a clear next action. 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 FeedHive-inspired workflow with owned or clearly labeled sample data: Plan social content in a calendar, adapt a draft to one connected network and optionally reuse an evergreen post only after review. AI assistance produces suggestions beside the saved original.
- Publish a reproducible walkthrough with this observable result: Cancel a recycled post and preserve its earlier publication receipt; changing a network limit flags queued variants before publication.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: analytics history and attribution; team approvals and asset workflows Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Plan social content in a calendar, adapt a draft to one connected network and optionally reuse an evergreen post only after review. AI assistance produces suggestions beside the saved original. Record prerequisites, select representative user-owned fixtures and document the unsupported features: analytics history and attribution; team approvals and asset workflows
2. Phase 2 — Durable model. Model drafts, reusable content categories, platform variants, scheduled slots and reuse history Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Recycling is opt-in with a cooldown and explicit approved revision; unsupported platform analytics remain unavailable rather than zero.
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. Track each target independently with pending, publishing, delivered, failed and unknown states. Reconcile a timeout using provider receipts before retrying; respect rate-limit backoff.
4. Phase 4 — Permissions and integration failure. Keep OAuth tokens server-side and encrypt persistent tokens with a separately managed key. Publication requires an explicit approved revision and target account. 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. Cancel a recycled post and preserve its earlier publication receipt; changing a network limit flags queued variants before publication. 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
- analytics history and attribution
- team approvals and asset workflows
- protection from API and policy changes
- calendar-provider edge cases and timezone correctness
- reliable direct publishing across networks

## Implementation prompt
WORKING SLICE
Plan social content in a calendar, adapt a draft to one connected network and optionally reuse an evergreen post only after review. AI assistance produces suggestions beside the saved original.

Build this scoped FeedHive-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.
- One official platform API adapter with declared text/media capabilities and a persisted scheduled-post worker.

Prerequisites and limits
Credentials and the required API access for one chosen network. Verify permissions and quotas; provide an export/manual-post workflow for unsupported networks.
Outside this release: analytics history and attribution; team approvals and asset workflows

Data model and correctness
drafts, reusable content categories, platform variants, scheduled slots and reuse history
Invariant: Recycling is opt-in with a cooldown and explicit approved revision; unsupported platform analytics remain unavailable rather than zero.
Track each target independently with pending, publishing, delivered, failed and unknown states. Reconcile a timeout using provider receipts before retrying; respect rate-limit backoff.

Security and privacy
Keep OAuth tokens server-side and encrypt persistent tokens with a separately managed key. Publication requires an explicit approved revision and target account.

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: Plan social content in a calendar, adapt a draft to one connected network and optionally reuse an evergreen post only after review. AI assistance produces suggestions beside the saved original. Record prerequisites, select representative user-owned fixtures and document the unsupported features: analytics history and attribution; team approvals and asset workflows
2. Phase 2 — Durable model. Model drafts, reusable content categories, platform variants, scheduled slots and reuse history Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Recycling is opt-in with a cooldown and explicit approved revision; unsupported platform analytics remain unavailable rather than zero.
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. Track each target independently with pending, publishing, delivered, failed and unknown states. Reconcile a timeout using provider receipts before retrying; respect rate-limit backoff.
4. Phase 4 — Permissions and integration failure. Keep OAuth tokens server-side and encrypt persistent tokens with a separately managed key. Publication requires an explicit approved revision and target account. 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. Cancel a recycled post and preserve its earlier publication receipt; changing a network limit flags queued variants before publication. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Cancel a recycled post and preserve its earlier publication receipt; changing a network limit flags queued variants before publication.
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: [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.
Optional external skill: [copywriting](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md) — Write landing pages and product copy grounded in the intended audience, product value and a clear next action. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: drafts, reusable content categories, platform variants, scheduled slots and reuse history
Project rule — preserve this invariant: Recycling is opt-in with a cooldown and explicit approved revision; unsupported platform analytics remain unavailable rather than zero.
Project rule — acceptance evidence: Cancel a recycled post and preserve its earlier publication receipt; changing a network limit flags queued variants before 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.