# AGENTS.md — Build guide for Hive CPQ ## Project scope Configure one product family through option groups, validate compatibility, price a reviewed configuration and issue a versioned quotation PDF. Catalogue verdict: kinda. The mechanical core of CPQ is not mysterious: a product tree, option groups, compatibility rules, a pricing formula, a PDF at the end. An agent can produce a working configurator for one product family in a weekend, and if you sell a few hundred SKUs with predictable option logic, that build may genuinely be enough. What you are not one-shotting is the part that makes CPQ a purchase: ERP and CRM sync, dealer accounts with their own price lists and discounts, 3D or 2D visual previews, multi-language catalogs, and someone maintaining the rule set when engineering changes a hinge. Also worth being honest that CPQ failure is expensive: a bad rule ships a quote that cannot be manufactured at the price you promised. So: buildable, and a bad idea to trust for anything you actually invoice on until the rules have been beaten on for months. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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, React, Node, SQLite and decimal.js for explicit decimal calculations. - Before starting: A representative CSV with known totals, currency and date conventions, and an agreed calculation specification. ## Stack and architecture - TypeScript, React, Node, SQLite and decimal.js for explicit decimal calculations - Data design: Store ProductVersion, OptionGroup, Constraint, PriceRule and QuoteSnapshot; selected options must satisfy all constraints and issued quotes preserve their original price/rule versions. - Setup: A representative CSV with known totals, currency and date conventions, and an agreed calculation specification ## Security and data integrity - Preserve imported source rows and units, use decimal arithmetic with stated rounding, and retain correction history. Missing values are unknown rather than zero; reports describe records and assumptions rather than giving advice. - Model one deterministic rule language without executing arbitrary expressions. Taxes, discounts and approval thresholds are explicit business inputs; a quote is not a tax invoice or purchase contract. - 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 ProductVersion, OptionGroup, Constraint, PriceRule and QuoteSnapshot; selected options must satisfy all constraints and issued quotes preserve their original price/rule versions. - Project rule — scope and recovery: Model one deterministic rule language without executing arbitrary expressions. Taxes, discounts and approval thresholds are explicit business inputs; a quote is not a tax invoice or purchase contract. - Project rule — acceptance: Select a high-power accessory with an incompatible base unit, then change the price list; block the invalid combination and leave an already issued quote unchanged. - 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. - Recommended skill: [pdf](https://github.com/anthropics/skills/blob/main/skills/pdf/SKILL.md) — inspect PDF source/extraction or generated report layout in the workflow; check the skill license and required PDF/OCR binaries. 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: Configure one product family through option groups, validate compatibility, price a reviewed configuration and issue a versioned quotation PDF. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Select a high-power accessory with an incompatible base unit, then change the price list; block the invalid combination and leave an already issued quote unchanged. - State the limits before asking someone to replace their existing tool: Model one deterministic rule language without executing arbitrary expressions. Taxes, discounts and approval thresholds are explicit business inputs; a quote is not a tax invoice or purchase contract. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Configure one product family through option groups, validate compatibility, price a reviewed configuration and issue a versioned quotation PDF. Confirm setup: A representative CSV with known totals, currency and date conventions, and an agreed calculation specification. 2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store ProductVersion, OptionGroup, Constraint, PriceRule and QuoteSnapshot; selected options must satisfy all constraints and issued quotes preserve their original price/rule versions. 3. Phase 3 — Connect the working view to real saved state. Preserve imported source rows and units, use decimal arithmetic with stated rounding, and retain correction history. Missing values are unknown rather than zero; reports describe records and assumptions rather than giving advice. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Model one deterministic rule language without executing arbitrary expressions. Taxes, discounts and approval thresholds are explicit business inputs; a quote is not a tax invoice or purchase contract. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Select a high-power accessory with an incompatible base unit, then change the price list; block the invalid combination and leave an already issued quote unchanged. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - ERP and CRM integrations, so accepted quotes become copy-paste work - A dealer or reseller portal with per-account price lists, discount tiers and order history - Visual product previews, 3D or otherwise, which is often the thing that closes the sale - Anyone but you maintaining the rule engine when the catalog changes - Version control on quotes and catalogs, audit trails, and the boring guarantees a buyer expects when a quote is contractual ## Implementation prompt Build the following focused alternative to Hive CPQ. This is a deliberately limited personal or small-team substitute, not parity with the paid service. WORKING SLICE Configure one product family through option groups, validate compatibility, price a reviewed configuration and issue a versioned quotation PDF. SETUP AND ARCHITECTURE Use TypeScript, React, Node, SQLite and decimal.js for explicit decimal calculations. Prerequisites: A representative CSV with known totals, currency and date conventions, and an agreed calculation specification. 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 ProductVersion, OptionGroup, Constraint, PriceRule and QuoteSnapshot; selected options must satisfy all constraints and issued quotes preserve their original price/rule versions. IMPLEMENTATION CONTRACT Preserve imported source rows and units, use decimal arithmetic with stated rounding, and retain correction history. Missing values are unknown rather than zero; reports describe records and assumptions rather than giving advice. 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 Model one deterministic rule language without executing arbitrary expressions. Taxes, discounts and approval thresholds are explicit business inputs; a quote is not a tax invoice or purchase contract. ACCEPTANCE SCENARIO Select a high-power accessory with an incompatible base unit, then change the price list; block the invalid combination and leave an already issued quote unchanged. 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.