# AGENTS.md — Build guide for posterly

## Project scope
Expose an authenticated caption-drafting endpoint and reviewed compose queue, then publish approved text/media to the chosen documented networks.

Catalogue verdict: kinda. A basic compose-queue-publish loop against open-API networks (Mastodon, Bluesky, Telegram) is a weekend build, same as any scheduler. What's specific to posterly and harder to fake is the agent-native layer: an MCP server exposing tools like generate_captions, get_learned_voice, and find_available_slot so a coding agent can draft and post on your behalf, plus a voice model that's actually learned from your posting history and its own performance data rather than a one-off few-shot prompt. Add Google Business Profile review management, per-platform video transcoding, and client approval workflows for agencies, and the moat is upkeep and depth, not the initial compose/publish loop.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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, Node, SQLite, a scheduled worker and a React draft/calendar interface.
- Before starting: An approved account for one documented publishing API, its current media/character rules and a sample post; API access and provider charges are separate.

## Stack and architecture
- TypeScript, Node, SQLite, a scheduled worker and a React draft/calendar interface
- Data design: Store CaptionRequest, DraftRevision, Approval, Schedule and DestinationReceipt; agent-created drafts are never automatically authorized for publication.
- Setup: An approved account for one documented publishing API, its current media/character rules and a sample post; API access and provider charges are separate

## Security and data integrity
- Freeze the approved content revision at enqueue time. Keep one receipt per destination and stop on revoked credentials or ambiguous publish results; retry only after checking provider state. Offer manual export for unsupported networks.
- Keep generation separate from publication and rate-limit both endpoints. No arbitrary remote media fetches or secret-bearing prompts; unsupported networks use manual exports.
- 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 CaptionRequest, DraftRevision, Approval, Schedule and DestinationReceipt; agent-created drafts are never automatically authorized for publication.
- Project rule — scope and recovery: Keep generation separate from publication and rate-limit both endpoints. No arbitrary remote media fetches or secret-bearing prompts; unsupported networks use manual exports.
- Project rule — acceptance: Call the caption endpoint twice with the same request identity, edit the result and queue it; show one draft lineage and publish only the explicitly approved revision.
- 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: [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.
- Recommended skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — review configuration and API defaults against the app-specific invariants and recovery boundaries above; this is not a security certification. 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: Expose an authenticated caption-drafting endpoint and reviewed compose queue, then publish approved text/media to the chosen documented networks.
- Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Call the caption endpoint twice with the same request identity, edit the result and queue it; show one draft lineage and publish only the explicitly approved revision.
- State the limits before asking someone to replace their existing tool: Keep generation separate from publication and rate-limit both endpoints. No arbitrary remote media fetches or secret-bearing prompts; unsupported networks use manual exports.

## Engineering roadmap
1. Phase 1 — Pin the working slice and create its example input: Expose an authenticated caption-drafting endpoint and reviewed compose queue, then publish approved text/media to the chosen documented networks. Confirm setup: An approved account for one documented publishing API, its current media/character rules and a sample post; API access and provider charges are separate.
2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store CaptionRequest, DraftRevision, Approval, Schedule and DestinationReceipt; agent-created drafts are never automatically authorized for publication.
3. Phase 3 — Connect the working view to real saved state. Freeze the approved content revision at enqueue time. Keep one receipt per destination and stop on revoked credentials or ambiguous publish results; retry only after checking provider state. Offer manual export for unsupported networks.
4. Phase 4 — Expose the app-specific limits and recovery path in context: Keep generation separate from publication and rate-limit both endpoints. No arbitrary remote media fetches or secret-bearing prompts; unsupported networks use manual exports.
5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Call the caption endpoint twice with the same request identity, edit the result and queue it; show one draft lineage and publish only the explicitly approved revision. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

## Paid-product capabilities outside this build
- 18 maintained platform integrations, including approval-gated ones (Instagram, LinkedIn, TikTok, Facebook, Google Business Profile)
- a voice model trained on your actual post history and what performed well, not a static prompt template
- Google Business Profile review replies and photo management
- client approval portal and content-plan review for agencies managing multiple brands
- per-platform video/image transcoding tuned to each network's limits
- a hosted MCP server + REST API built for agents, not bolted on after the fact

## Implementation prompt
Build the following focused alternative to posterly. This is a deliberately limited personal or small-team substitute, not parity with the paid service.

WORKING SLICE
Expose an authenticated caption-drafting endpoint and reviewed compose queue, then publish approved text/media to the chosen documented networks.

SETUP AND ARCHITECTURE
Use TypeScript, Node, SQLite, a scheduled worker and a React draft/calendar interface. Prerequisites: An approved account for one documented publishing API, its current media/character rules and a sample post; API access and provider charges are separate. 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 CaptionRequest, DraftRevision, Approval, Schedule and DestinationReceipt; agent-created drafts are never automatically authorized for publication.

IMPLEMENTATION CONTRACT
Freeze the approved content revision at enqueue time. Keep one receipt per destination and stop on revoked credentials or ambiguous publish results; retry only after checking provider state. Offer manual export for unsupported networks. 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 generation separate from publication and rate-limit both endpoints. No arbitrary remote media fetches or secret-bearing prompts; unsupported networks use manual exports.

ACCEPTANCE SCENARIO
Call the caption endpoint twice with the same request identity, edit the result and queue it; show one draft lineage and publish only the explicitly approved revision. 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.