# AGENTS.md — Build guide for OutFriend

## Project scope
Review a user-supplied recipient CSV, draft personalized emails using approved sent-mail examples and queue confirmed messages with reply-aware follow-ups.

Catalogue verdict: kinda. This one is closer to buildable than most outreach tools, because OutFriend sends through your own Gmail rather than its own infrastructure. That removes the moat that usually saves this category: no warmup pools, no IP reputation, no deliverability engineering you cannot replicate. What is left is a Gmail OAuth integration, a voice sample you pass to a model, a scheduler with send windows and daily caps, and the one piece that is genuinely fiddly, watching threads so a sequence stops the instant someone replies. That is a weekend if you have written against the Gmail API before, and a long weekend if you have not.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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: Node, TypeScript, better-sqlite3, googleapis and a CLI review queue with a scheduled worker.
- Before starting: One authorized Gmail account using its currently supported desktop OAuth flow, consented or appropriately permissioned recipients, and reviewed voice examples.

## Stack and architecture
- Node, TypeScript, better-sqlite3, googleapis and a CLI review queue with a scheduled worker
- Data design: Store Recipient, ConsentOrRelationshipBasis, VoiceExample, DraftRevision, SendReceipt and ThreadReply; one recipient's examples cannot leak into another person's email.
- Setup: One authorized Gmail account using its currently supported desktop OAuth flow, consented or appropriately permissioned recipients, and reviewed voice examples

## Security and data integrity
- Separate drafts, recipient snapshots, attempts and provider receipts. Honor unsubscribe and suppression at dispatch time, authenticate provider webhooks, and never replay an ambiguous send automatically.
- Preserve one authorized Gmail account and restrained schedules. No lead sourcing, warmup, spam bypass or inferred consent; user reviews each recipient and message before external delivery.
- 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 Recipient, ConsentOrRelationshipBasis, VoiceExample, DraftRevision, SendReceipt and ThreadReply; one recipient's examples cannot leak into another person's email.
- Project rule — scope and recovery: Preserve one authorized Gmail account and restrained schedules. No lead sourcing, warmup, spam bypass or inferred consent; user reviews each recipient and message before external delivery.
- Project rule — acceptance: A reply arrives just before a follow-up dispatch; recheck the thread and suppress the send, while an unknown original-send result requires manual reconciliation.
- 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: [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.
- Recommended skill: [copywriting](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md) — write clear, evidence-grounded draft copy or notifications without invented claims; sending/publishing remains separately approved. 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: Review a user-supplied recipient CSV, draft personalized emails using approved sent-mail examples and queue confirmed messages with reply-aware follow-ups.
- Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: A reply arrives just before a follow-up dispatch; recheck the thread and suppress the send, while an unknown original-send result requires manual reconciliation.
- State the limits before asking someone to replace their existing tool: Preserve one authorized Gmail account and restrained schedules. No lead sourcing, warmup, spam bypass or inferred consent; user reviews each recipient and message before external delivery.

## Engineering roadmap
1. Phase 1 — Pin the working slice and create its example input: Review a user-supplied recipient CSV, draft personalized emails using approved sent-mail examples and queue confirmed messages with reply-aware follow-ups. Confirm setup: One authorized Gmail account using its currently supported desktop OAuth flow, consented or appropriately permissioned recipients, and reviewed voice examples.
2. Phase 2 — Implement durable result files and command invariants before formatting terminal output: Store Recipient, ConsentOrRelationshipBasis, VoiceExample, DraftRevision, SendReceipt and ThreadReply; one recipient's examples cannot leak into another person's email.
3. Phase 3 — Connect CLI commands to real saved state and explicit result/exit statuses. Separate drafts, recipient snapshots, attempts and provider receipts. Honor unsubscribe and suppression at dispatch time, authenticate provider webhooks, and never replay an ambiguous send automatically.
4. Phase 4 — Expose the app-specific limits and recovery path in context: Preserve one authorized Gmail account and restrained schedules. No lead sourcing, warmup, spam bypass or inferred consent; user reviews each recipient and message before external delivery.
5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: A reply arrives just before a follow-up dispatch; recheck the thread and suppress the send, while an unknown original-send result requires manual reconciliation. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

## Paid-product capabilities outside this build
- reply detection that is thread-based rather than naive, so out-of-office replies do not count as interest and a reply from a different address still stops the sequence
- verification and suppression, meaning unverified, bounced and opted-out addresses filtered before anything queues
- a review surface where every draft is readable and editable before it goes, instead of trusting a script with your inbox
- lead generation, which the paid tiers include and your CSV does not
- the Google OAuth verification process, which you will meet the moment you want this on more than your own account

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

WORKING SLICE
Review a user-supplied recipient CSV, draft personalized emails using approved sent-mail examples and queue confirmed messages with reply-aware follow-ups.

SETUP AND ARCHITECTURE
Use Node, TypeScript, better-sqlite3, googleapis and a CLI review queue with a scheduled worker. Prerequisites: One authorized Gmail account using its currently supported desktop OAuth flow, consented or appropriately permissioned recipients, and reviewed voice examples. 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 Recipient, ConsentOrRelationshipBasis, VoiceExample, DraftRevision, SendReceipt and ThreadReply; one recipient's examples cannot leak into another person's email.

IMPLEMENTATION CONTRACT
Separate drafts, recipient snapshots, attempts and provider receipts. Honor unsubscribe and suppression at dispatch time, authenticate provider webhooks, and never replay an ambiguous send automatically. Provide documented CLI inputs, progress/status output, reviewable result files and explicit exit codes; do not add a web application. 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
Preserve one authorized Gmail account and restrained schedules. No lead sourcing, warmup, spam bypass or inferred consent; user reviews each recipient and message before external delivery.

ACCEPTANCE SCENARIO
A reply arrives just before a follow-up dispatch; recheck the thread and suppress the send, while an unknown original-send result requires manual reconciliation. Also resume the configured workflow 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 the CLI/skill folder with its dependency manifest, versioned configuration/result files, a non-sensitive example, setup instructions, exact acceptance commands and a recovery/export 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.