# AGENTS.md — Build guide for Zapier ## Project scope Implement one trusted local webhook-to-API pipeline with a scheduled reconciliation job, step receipts and an operator-visible retry queue. Catalogue verdict: kinda. A few personal automations are easy; Zapier's moat is the 9,000+ app integration catalog, auth handling, retries, task history, UI, and reliability. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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, Express, node-cron and better-sqlite3 with trusted local pipeline modules. - Before starting: An always-on host, current API credentials for the selected two services and a writable SQLite run/outbox database. ## Stack and architecture - Node, Express, node-cron and better-sqlite3 with trusted local pipeline modules - Data design: Store PipelineVersion, TriggerID, Run, Step and ExternalReceipt in SQLite; deduplicate triggers and bind a replay to its original inputs and code version. - Setup: An always-on host, current API credentials for the selected two services and a writable SQLite run/outbox database ## Security and data integrity - Persist trigger identity, step input version and external receipts before marking success. Retry bounded transient failures; unknown write outcomes require reconciliation. Do not promise exactly-once execution across external services. - Retain the small trusted Node/SQLite runner, not a marketplace or sandbox for untrusted code. Verify provider signatures where available; a secret URL alone can leak through logs and is not a universal webhook protocol. - 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 PipelineVersion, TriggerID, Run, Step and ExternalReceipt in SQLite; deduplicate triggers and bind a replay to its original inputs and code version. - Project rule — scope and recovery: Retain the small trusted Node/SQLite runner, not a marketplace or sandbox for untrusted code. Verify provider signatures where available; a secret URL alone can leak through logs and is not a universal webhook protocol. - Project rule — acceptance: Deliver a webhook twice and crash after its API side effect; reconcile the recorded destination state before retrying so the operator cannot unknowingly duplicate the action. - 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: [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. 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: Implement one trusted local webhook-to-API pipeline with a scheduled reconciliation job, step receipts and an operator-visible retry queue. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Deliver a webhook twice and crash after its API side effect; reconcile the recorded destination state before retrying so the operator cannot unknowingly duplicate the action. - State the limits before asking someone to replace their existing tool: Retain the small trusted Node/SQLite runner, not a marketplace or sandbox for untrusted code. Verify provider signatures where available; a secret URL alone can leak through logs and is not a universal webhook protocol. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Implement one trusted local webhook-to-API pipeline with a scheduled reconciliation job, step receipts and an operator-visible retry queue. Confirm setup: An always-on host, current API credentials for the selected two services and a writable SQLite run/outbox database. 2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store PipelineVersion, TriggerID, Run, Step and ExternalReceipt in SQLite; deduplicate triggers and bind a replay to its original inputs and code version. 3. Phase 3 — Connect the working view to real saved state. Persist trigger identity, step input version and external receipts before marking success. Retry bounded transient failures; unknown write outcomes require reconciliation. Do not promise exactly-once execution across external services. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Retain the small trusted Node/SQLite runner, not a marketplace or sandbox for untrusted code. Verify provider signatures where available; a secret URL alone can leak through logs and is not a universal webhook protocol. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Deliver a webhook twice and crash after its API side effect; reconcile the recorded destination state before retrying so the operator cannot unknowingly duplicate the action. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - integration catalog - OAuth maintenance - retries/history - nontechnical builder - app triggers/actions - uptime ## Implementation prompt Build the following focused alternative to Zapier. This is a deliberately limited personal or small-team substitute, not parity with the paid service. WORKING SLICE Implement one trusted local webhook-to-API pipeline with a scheduled reconciliation job, step receipts and an operator-visible retry queue. SETUP AND ARCHITECTURE Use Node, Express, node-cron and better-sqlite3 with trusted local pipeline modules. Prerequisites: An always-on host, current API credentials for the selected two services and a writable SQLite run/outbox database. 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 PipelineVersion, TriggerID, Run, Step and ExternalReceipt in SQLite; deduplicate triggers and bind a replay to its original inputs and code version. IMPLEMENTATION CONTRACT Persist trigger identity, step input version and external receipts before marking success. Retry bounded transient failures; unknown write outcomes require reconciliation. Do not promise exactly-once execution across external services. 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 Retain the small trusted Node/SQLite runner, not a marketplace or sandbox for untrusted code. Verify provider signatures where available; a secret URL alone can leak through logs and is not a universal webhook protocol. ACCEPTANCE SCENARIO Deliver a webhook twice and crash after its API side effect; reconcile the recorded destination state before retrying so the operator cannot unknowingly duplicate the action. 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.