# AGENTS.md — Build guide for Surfer SEO

## Project scope
Build a dated content brief from permitted reference pages and compare a user draft against transparent topic/heading coverage rules.

Catalogue verdict: kinda. A SERP-scrape-to-content-brief tool is buildable, but reliable SERP data, NLP scoring, editor workflow, AI articles, audits, and integrations create ongoing work.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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, Cheerio/Readability and a CLI for briefs and draft comparison.
- Before starting: A search-result API account or imported result set, permitted reference URLs and a user-written Markdown draft.

## Stack and architecture
- Node, TypeScript, better-sqlite3, Cheerio/Readability and a CLI for briefs and draft comparison
- Data design: Store QuerySnapshot, ReferencePage, ExtractedSection, BriefRevision and DraftScore; missing pages reduce coverage and cached results retain their age rather than implying current rankings.
- Setup: A search-result API account or imported result set, permitted reference URLs and a user-written Markdown draft

## 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.
- Start with a Node CLI and user-reviewed outlines. Scores are heuristics, not ranking predictions; cache hits avoid repeat calls only while valid and do not guarantee zero provider charges.
- 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 QuerySnapshot, ReferencePage, ExtractedSection, BriefRevision and DraftScore; missing pages reduce coverage and cached results retain their age rather than implying current rankings.
- Project rule — scope and recovery: Start with a Node CLI and user-reviewed outlines. Scores are heuristics, not ranking predictions; cache hits avoid repeat calls only while valid and do not guarantee zero provider charges.
- Project rule — acceptance: One reference page is blocked and a draft repeats every keyword unnaturally; show incomplete evidence and do not reward repetition as demonstrated content quality.
- 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: [seo-audit](https://github.com/coreyhaines31/marketingskills/blob/main/skills/seo-audit/SKILL.md) — review crawlability, metadata and evidence-based on-page findings without promising search rankings. 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: Build a dated content brief from permitted reference pages and compare a user draft against transparent topic/heading coverage rules.
- Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: One reference page is blocked and a draft repeats every keyword unnaturally; show incomplete evidence and do not reward repetition as demonstrated content quality.
- State the limits before asking someone to replace their existing tool: Start with a Node CLI and user-reviewed outlines. Scores are heuristics, not ranking predictions; cache hits avoid repeat calls only while valid and do not guarantee zero provider charges.

## Engineering roadmap
1. Phase 1 — Pin the working slice and create its example input: Build a dated content brief from permitted reference pages and compare a user draft against transparent topic/heading coverage rules. Confirm setup: A search-result API account or imported result set, permitted reference URLs and a user-written Markdown draft.
2. Phase 2 — Implement durable result files and command invariants before formatting terminal output: Store QuerySnapshot, ReferencePage, ExtractedSection, BriefRevision and DraftScore; missing pages reduce coverage and cached results retain their age rather than implying current rankings.
3. Phase 3 — Connect CLI commands to real saved state and explicit result/exit statuses. 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: Start with a Node CLI and user-reviewed outlines. Scores are heuristics, not ranking predictions; cache hits avoid repeat calls only while valid and do not guarantee zero provider charges.
5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: One reference page is blocked and a draft repeats every keyword unnaturally; show incomplete evidence and do not reward repetition as demonstrated content quality. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

## Paid-product capabilities outside this build
- SERP data reliability
- scoring model
- editor UX
- AI article workflows
- integrations
- audits
- support

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

WORKING SLICE
Build a dated content brief from permitted reference pages and compare a user draft against transparent topic/heading coverage rules.

SETUP AND ARCHITECTURE
Use Node, TypeScript, better-sqlite3, Cheerio/Readability and a CLI for briefs and draft comparison. Prerequisites: A search-result API account or imported result set, permitted reference URLs and a user-written Markdown draft. 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 QuerySnapshot, ReferencePage, ExtractedSection, BriefRevision and DraftScore; missing pages reduce coverage and cached results retain their age rather than implying current rankings.

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 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
Start with a Node CLI and user-reviewed outlines. Scores are heuristics, not ranking predictions; cache hits avoid repeat calls only while valid and do not guarantee zero provider charges.

ACCEPTANCE SCENARIO
One reference page is blocked and a draft repeats every keyword unnaturally; show incomplete evidence and do not reward repetition as demonstrated content quality. 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.