# AGENTS.md — Build guide for Apify

## Project scope
Run one owned-site catalogue extractor from a reviewed URL list, inspect each request, checkpoint pagination and export a structured dataset.

Catalogue verdict: kinda. The visible web scraping platform loop is buildable, but a credible replacement needs more than the first screen. Apify earns its keep through connectors, auth, reliability, 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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- Runtime and tools: Python, HTTP parsing, SQLite and optional Playwright for explicitly permitted rendered pages.
- Before starting: A small authorized URL set, reviewed selectors or field schema and a user-approved crawl frequency; no proxy-evasion machinery.

## Stack and architecture
- Python, HTTP parsing, SQLite and optional Playwright for explicitly permitted rendered pages
- Data design: Store ExtractorVersion, Run, FrontierURL, PageResult and DatasetRow; deduplicate by canonical product ID and persist the next page only after current rows commit.
- Setup: A small authorized URL set, reviewed selectors or field schema and a user-approved crawl frequency; no proxy-evasion machinery

## Security and data integrity
- Bound hosts, redirects, page count, body size and timeout. Reject private-network destinations throughout redirects, respect access restrictions and backoff, and distinguish extraction failure from a missing field.
- Ship one trusted extractor, not arbitrary hosted actors. Constrain browser networking and resources; blocked access is a stopped run, not a trigger for fingerprint or account evasion.
- 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 ExtractorVersion, Run, FrontierURL, PageResult and DatasetRow; deduplicate by canonical product ID and persist the next page only after current rows commit.
- Project rule — scope and recovery: Ship one trusted extractor, not arbitrary hosted actors. Constrain browser networking and resources; blocked access is a stopped run, not a trigger for fingerprint or account evasion.
- Project rule — acceptance: Stop on page three, restart the run and introduce a changed selector on page four; previous products remain unique and the selector failure is shown instead of an empty successful dataset.
- 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: [modern-python](https://github.com/trailofbits/skills/blob/main/plugins/modern-python/skills/modern-python/SKILL.md) — structure the Python worker or explicitly optional read-only utility with pinned dependencies, typed boundaries and clear failure handling. Follow the maintainer's installation instructions and match its requirements to the chosen runtime.
- Recommended skill: [agent-browser](https://github.com/vercel-labs/agent-browser/blob/main/skills/agent-browser/SKILL.md) — inspect the approved browser workflow and reproduce permitted page interactions; the CLI/browser runtime is a separate prerequisite. 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: Run one owned-site catalogue extractor from a reviewed URL list, inspect each request, checkpoint pagination and export a structured dataset.
- Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Stop on page three, restart the run and introduce a changed selector on page four; previous products remain unique and the selector failure is shown instead of an empty successful dataset.
- State the limits before asking someone to replace their existing tool: Ship one trusted extractor, not arbitrary hosted actors. Constrain browser networking and resources; blocked access is a stopped run, not a trigger for fingerprint or account evasion.

## Engineering roadmap
1. Phase 1 — Pin the working slice and create its example input: Run one owned-site catalogue extractor from a reviewed URL list, inspect each request, checkpoint pagination and export a structured dataset. Confirm setup: A small authorized URL set, reviewed selectors or field schema and a user-approved crawl frequency; no proxy-evasion machinery.
2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store ExtractorVersion, Run, FrontierURL, PageResult and DatasetRow; deduplicate by canonical product ID and persist the next page only after current rows commit.
3. Phase 3 — Connect the working view to real saved state. Bound hosts, redirects, page count, body size and timeout. Reject private-network destinations throughout redirects, respect access restrictions and backoff, and distinguish extraction failure from a missing field.
4. Phase 4 — Expose the app-specific limits and recovery path in context: Ship one trusted extractor, not arbitrary hosted actors. Constrain browser networking and resources; blocked access is a stopped run, not a trigger for fingerprint or account evasion.
5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Stop on page three, restart the run and introduce a changed selector on page four; previous products remain unique and the selector failure is shown instead of an empty successful dataset. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

## Paid-product capabilities outside this build
- OAuth app verification
- durable execution at scale
- schema drift handling and enterprise controls
- calendar-provider edge cases and timezone correctness
- hundreds of maintained connectors

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

WORKING SLICE
Run one owned-site catalogue extractor from a reviewed URL list, inspect each request, checkpoint pagination and export a structured dataset.

SETUP AND ARCHITECTURE
Use Python, HTTP parsing, SQLite and optional Playwright for explicitly permitted rendered pages. Prerequisites: A small authorized URL set, reviewed selectors or field schema and a user-approved crawl frequency; no proxy-evasion machinery. 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 ExtractorVersion, Run, FrontierURL, PageResult and DatasetRow; deduplicate by canonical product ID and persist the next page only after current rows commit.

IMPLEMENTATION CONTRACT
Bound hosts, redirects, page count, body size and timeout. Reject private-network destinations throughout redirects, respect access restrictions and backoff, and distinguish extraction failure from a missing field. 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
Ship one trusted extractor, not arbitrary hosted actors. Constrain browser networking and resources; blocked access is a stopped run, not a trigger for fingerprint or account evasion.

ACCEPTANCE SCENARIO
Stop on page three, restart the run and introduce a changed selector on page four; previous products remain unique and the selector failure is shown instead of an empty successful dataset. 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.