AI Coding Agents · ferrislucas

promptr

Promptr is a CLI tool that applies plain-language instructions to your codebase using OpenAI LLMs (GPT-4, GPT-4o). It reads your prompt, processes templated instructions, and automatically applies code changes directly to files.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/ferrislucas/promptr

950

GitHub stars

Forks

JavaScript

Primary language

MIT

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	ferrislucas/promptr
Owner	ferrislucas
Primary language	JavaScript
License	MIT — OSI-approved
Stars	950
Forks	35
Open issues	10
Latest release	v6.0.7 (2024-05-18)
Last updated	2026-04-24
Source	https://github.com/ferrislucas/promptr

What promptr is

Node.js CLI that sends file context and liquidjs-templated prompts to OpenAI's API, parses structured responses, and applies filesystem mutations. Supports dry-run mode, multiple built-in templates (refactor, swe, test-first), and optional liquidjs templating for reusable includes.

Quickstart

Get the promptr source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/ferrislucas/promptr.git2cd promptr3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Codebase Refactoring at Scale

Apply consistent refactoring patterns across multiple files with a single prompt (e.g., migrate from require to import, rename methods). Useful for enforcing coding standards across large projects.

Code Generation with Project Context

Generate boilerplate, API endpoints, model definitions, or test files while respecting project-specific standards defined in liquidjs include files. Reduces manual scaffolding.

Rapid Experimentation and Prototyping

Test hypothetical changes to your codebase (via dry-run mode) or quickly iterate on implementations without manual editing. Useful for proof-of-concepts and exploratory development.

Implementation considerations

Enforce a strict workflow: commit before running Promptr, then inspect git diffs before acceptance. The tool modifies files in-place and relies on human review to catch model errors.
Budget API costs carefully. Each prompt execution incurs OpenAI API charges; high-volume or complex prompts will accumulate expenses. Test with dry-run mode (`-d` flag) first.
Craft clear, specific prompts with relative file paths and project context. Vague or ambiguous instructions produce low-quality output. Use liquidjs includes to embed project standards consistently.
Verify Node 18+ is installed and OPENAI_API_KEY environment variable is set before deployment. Binary releases are macOS-only; other platforms require npm/yarn installation.
Test templates and prompts in a development branch first. The default 'refactor' template works well; custom templates require the `-x` flag for filesystem application.

When to avoid it — and what to weigh

No OpenAI API Budget or Access — Promptr requires an OpenAI API key with active billing. If you lack OpenAI access or cannot justify per-request costs, this tool is not viable.
Require Offline or Air-Gapped Environments — The tool is entirely dependent on external OpenAI API calls; it cannot function without internet connectivity and API access.
Safety-Critical or Highly Regulated Codebases — LLM-generated code changes lack formal verification. Industries requiring auditable, deterministic change processes (banking, healthcare, safety-critical systems) should not rely on this for production modifications.
Teams Uncomfortable with LLM Output Review — Changes are applied directly to files. Teams without a strong code review or git-diff inspection discipline risk introducing bugs or security issues from model hallucinations.

License & commercial use

Released under MIT License (OSI-compliant). Permissive, allows commercial use, modification, and distribution with attribution. No warranty or liability.

MIT License permits commercial use without restrictions. However, you must account for OpenAI API costs and ensure your use of LLM-generated code complies with OpenAI's terms of service. No guarantee that generated code is free of licensing issues or legal liabilities; conduct your own review.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Adequate
License clarity	Clear
Deployment complexity	Low
DEV.co fit	Good
Assessment confidence	High

Security considerations

Promptr sends file context and prompts to external OpenAI API servers. Ensure no sensitive credentials, secrets, or proprietary logic are passed to the tool. The `-dac` flag can prevent auto-inclusion of referenced files, giving control over context sent. LLM-generated code may contain unintended vulnerabilities; mandatory code review required before applying. No local encryption, audit logging, or data retention guarantees for OpenAI requests.

Alternatives to consider

GitHub Copilot / Copilot CLI

Similar intent (LLM-assisted coding), but integrated into IDEs and GitHub, with different pricing (subscription vs. pay-per-API). Lacks direct filesystem mutation CLI.

Aider (ai-assisted coding)

CLI tool for LLM-driven code changes, supports multiple LLM backends (OpenAI, Claude, local models). Similar workflow but broader model flexibility.

Manual Code Generation + Templating (e.g., Plop, Yeoman)

Deterministic, offline-capable scaffolding and refactoring. No LLM cost, but requires predefined templates; less flexible for ad-hoc changes.

Software development agency

Build on promptr with DEV.co software developers

Promptr streamlines refactoring and code generation for teams comfortable with AI-assisted development. Start with a trial on a feature branch, enforce code review practices, and unlock faster iteration cycles.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

prompty promptfoo prompt-master

Related on DEV.co

Explore the category and the services that help you build with it.

AI Coding Agents AI Application Development Custom Software Development Talk to DEV.co

promptr FAQ

Does Promptr work offline or with local LLMs?

No. Promptr is hard-wired to OpenAI's API. Local or alternative LLM backends are not supported.

What happens if the LLM generates incorrect or harmful code?

Promptr applies the output directly to your files. You must review changes via git diff before committing. Use dry-run mode (`-d` flag) to preview before applying.

Can I use Promptr in CI/CD pipelines?

Technically yes, but not recommended without strong safeguards. LLM output is non-deterministic. Requires human code review after each run, which breaks automation.

How much does it cost to run Promptr?

Cost depends on OpenAI API pricing per token. Complex prompts and large file contexts incur higher charges. Not clearly stated; test with dry-run and monitor API usage.

Work with a software development agency

DEV.co is a software development agency delivering custom software development services to companies building on open source. Our software developers and web developers design, integrate, and ship production systems — spanning web development, APIs, AI, data, and cloud. If promptr is part of your ai coding agents roadmap, our team can implement, customize, migrate, and maintain it.

Ready to Accelerate Code Changes with LLM Assistance?

Talk to DEV.co Schedule a Consultation