# AGENTS.md — Build guide for PromptDrive

## Project scope
Save reusable prompts, search them instantly and generate a form for declared template variables. Preview the filled text and copy it to the clipboard without sending it to any model by default.

Catalogue verdict: yes. The core loop, save a prompt, file it in a folder, tag it, find it, fill in variables, copy it into a chat, is a small CRUD app around one SQLite table and ships in one sitting. What the subscription actually sells is the multiplayer part: shared folders with permissions, comments that let a team iterate on a prompt, and a Chrome extension that surfaces the library inside ChatGPT, Claude, and Gemini.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first.
- Implementation components: Node.js, TypeScript and Express with server-rendered HTML and small browser modules. SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.
- Scope boundary: team sharing, comments, and permissions; the Chrome extension inside ChatGPT, Claude, and Gemini

## Stack and architecture
- Node.js, TypeScript and Express with server-rendered HTML and small browser modules.
- SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.
- Domain model: prompt templates, folders, tags, variable definitions, immutable versions and filled previews

## Security and data integrity
- Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs.
- Correctness boundary: Template substitution cannot execute code; missing variables block final copy or remain visibly unresolved, and secrets are not stored as sample values.
- Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
- Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data.

## Agent implementation rules
- Project rule — data model: prompt templates, folders, tags, variable definitions, immutable versions and filled previews
- Project rule — preserve this invariant: Template substitution cannot execute code; missing variables block final copy or remain visibly unresolved, and secrets are not stored as sample values.
- Project rule — acceptance evidence: Fill a value containing braces and preserve it literally; editing a shared template creates a revision without changing earlier saved previews.

## Optional agent skills and references
- Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.

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 the actual PromptDrive-inspired workflow with owned or clearly labeled sample data: Save reusable prompts, search them instantly and generate a form for declared template variables. Preview the filled text and copy it to the clipboard without sending it to any model by default.
- Publish a reproducible walkthrough with this observable result: Fill a value containing braces and preserve it literally; editing a shared template creates a revision without changing earlier saved previews.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: team sharing, comments, and permissions; the Chrome extension inside ChatGPT, Claude, and Gemini Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Save reusable prompts, search them instantly and generate a form for declared template variables. Preview the filled text and copy it to the clipboard without sending it to any model by default. Record prerequisites, select representative user-owned fixtures and document the unsupported features: team sharing, comments, and permissions; the Chrome extension inside ChatGPT, Claude, and Gemini
2. Phase 2 — Durable model. Model prompt templates, folders, tags, variable definitions, immutable versions and filled previews Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Template substitution cannot execute code; missing variables block final copy or remain visibly unresolved, and secrets are not stored as sample values.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Fill a value containing braces and preserve it literally; editing a shared template creates a revision without changing earlier saved previews. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

## Paid-product capabilities outside this build
- team sharing, comments, and permissions
- the Chrome extension inside ChatGPT, Claude, and Gemini
- running prompts against models from the same workspace with your own API keys
- public share links with unique URLs
- someone else's servers & support

## Implementation prompt
WORKING SLICE
Save reusable prompts, search them instantly and generate a form for declared template variables. Preview the filled text and copy it to the clipboard without sending it to any model by default.

Build this scoped PromptDrive-inspired workflow with a documented data model and visible failure states.

Architecture
- Node.js, TypeScript and Express with server-rendered HTML and small browser modules.
- SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.

Prerequisites and limits
A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first.
Outside this release: team sharing, comments, and permissions; the Chrome extension inside ChatGPT, Claude, and Gemini

Data model and correctness
prompt templates, folders, tags, variable definitions, immutable versions and filled previews
Invariant: Template substitution cannot execute code; missing variables block final copy or remain visibly unresolved, and secrets are not stored as sample values.
Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.

Security and privacy
Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs.

Recovery and export
Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Save reusable prompts, search them instantly and generate a form for declared template variables. Preview the filled text and copy it to the clipboard without sending it to any model by default. Record prerequisites, select representative user-owned fixtures and document the unsupported features: team sharing, comments, and permissions; the Chrome extension inside ChatGPT, Claude, and Gemini
2. Phase 2 — Durable model. Model prompt templates, folders, tags, variable definitions, immutable versions and filled previews Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Template substitution cannot execute code; missing variables block final copy or remain visibly unresolved, and secrets are not stored as sample values.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Fill a value containing braces and preserve it literally; editing a shared template creates a revision without changing earlier saved previews. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Fill a value containing braces and preserve it literally; editing a shared template creates a revision without changing earlier saved previews.
Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees.

Optional agent guidance
Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: prompt templates, folders, tags, variable definitions, immutable versions and filled previews
Project rule — preserve this invariant: Template substitution cannot execute code; missing variables block final copy or remain visibly unresolved, and secrets are not stored as sample values.
Project rule — acceptance evidence: Fill a value containing braces and preserve it literally; editing a shared template creates a revision without changing earlier saved previews.

## 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.