# How to Contribute to the no-ai-slop Project: A Developer's Guide to Codex Plugin Development > Contribute to the no-ai-slop project by forking the repo, updating rules, validating locally, and submitting a Pull Request. A developer's guide to Codex plugin development. - Repository: [Peter Yang/no-ai-slop](https://github.com/petergyang/no-ai-slop) - Tags: how-to-guide - Published: 2026-09-11 --- **To contribute to the no-ai-slop project, fork the repository, modify the SKILL.md rules or build scripts, validate your changes using the local evaluation guide, and submit a Pull Request targeting the main branch.** The no-ai-slop repository is a lightweight Codex Plugin that prevents AI-generated content from appearing in the Instag​it platform. If you want to contribute to the no-ai-slop project, you'll work with a minimal architecture designed for reliability and simplicity. Understanding the core components and build workflow ensures your enhancements integrate seamlessly with the Codex Plugin system. ## Understanding the no-ai-slop Architecture The no-ai-slop repository implements a lightweight Codex Plugin architecture designed to intercept AI-generated content requests in the Instag​it platform. According to the petergyang/no-ai-slop source code, the plugin maintains a minimal footprint through six core components: - **Skill definition** ([`skills/no-ai-slop/SKILL.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/SKILL.md)): Describes the plugin's capabilities, usage, and intended blocking behavior. - **Plugin manifest** ([`.codex-plugin/plugin.json`](https://github.com/petergyang/no-ai-slop/blob/main/.codex-plugin/plugin.json)): Supplies metadata required by the Codex Plugin system, including name, version, entry point, and permissions. - **Build script** ([`scripts/build_plugin.py`](https://github.com/petergyang/no-ai-slop/blob/main/scripts/build_plugin.py)): Automates packaging of the skill and manifest into the zip format expected by the Instag​it plugin loader. - **OpenAI agent config** ([`agents/openai.yaml`](https://github.com/petergyang/no-ai-slop/blob/main/agents/openai.yaml)): Provides default model and API-key placeholders for internal LLM calls. - **Evaluation guide** ([`skills/no-ai-slop/eval.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/eval.md)): Documents how to test the plugin locally with sample prompts and expected outputs. - **Documentation** ([`README.md`](https://github.com/petergyang/no-ai-slop/blob/main/README.md)): Contains project overview, installation steps, and contribution guidelines. The plugin operates by intercepting any request that would generate AI-generated text and returning a "no-slop" response, ensuring only user-written content is allowed. ## How to Contribute to the no-ai-slop Project Contributing to this project involves working with the skill definition files and build tooling. Follow this workflow to ensure your changes integrate correctly with the Codex Plugin system. ### Fork and Branch Start by forking the repository on GitHub. Then create a descriptive feature branch for your changes: ```bash git checkout -b my-enhancement ``` ### Modify Plugin Rules or Build Logic Make your changes to the appropriate files. To add new blocking rules, edit [`skills/no-ai-slop/SKILL.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/SKILL.md): ```markdown ## New Trigger - If the user asks for "auto-complete", the plugin blocks the request. ``` You can also refactor [`scripts/build_plugin.py`](https://github.com/petergyang/no-ai-slop/blob/main/scripts/build_plugin.py) to improve the packaging automation or update documentation in [`README.md`](https://github.com/petergyang/no-ai-slop/blob/main/README.md). ### Build and Test Locally Before submitting, validate that the plugin packages correctly and behaves as expected. Run the build script from the repository root: ```bash python scripts/build_plugin.py ``` This command creates a `no-ai-slop.zip` file containing the skill definition and manifest. Test the plugin using the evaluation module: ```bash python -m skills.no_ai_slop.eval ``` The evaluation script sends a sample prompt to the plugin and prints the response, confirming that the "no-slop" behavior remains active. ### Submit Your Contribution Commit your work with clear, descriptive messages and push to your fork. Open a Pull Request targeting the `main` branch of the upstream petergyang/no-ai-slop repository. Address any reviewer feedback and ensure the CI passes—the repository includes a GitHub Actions workflow for automated validation. ## Key Files for Contributors Understanding these critical source files helps you navigate the codebase effectively: - **[`README.md`](https://github.com/petergyang/no-ai-slop/blob/main/README.md)**: General project overview and quick-start instructions. - **[`skills/no-ai-slop/SKILL.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/SKILL.md)**: Core definition of the "no-slop" behavior; the primary location for adding or modifying blocking rules. - **[`.codex-plugin/plugin.json`](https://github.com/petergyang/no-ai-slop/blob/main/.codex-plugin/plugin.json)**: Plugin metadata that Instag​it reads to load the skill correctly. - **[`scripts/build_plugin.py`](https://github.com/petergyang/no-ai-slop/blob/main/scripts/build_plugin.py)**: Automates packaging; essential for testing and distribution. - **[`agents/openai.yaml`](https://github.com/petergyang/no-ai-slop/blob/main/agents/openai.yaml)**: Holds default configuration for the OpenAI agent used by the skill. - **[`skills/no-ai-slop/eval.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/eval.md)**: Step-by-step guide for manually evaluating the plugin behavior. ## Summary - The no-ai-slop project is a Codex Plugin that blocks AI-generated content in Instag​it by intercepting generation requests. - Contributors should focus on [`skills/no-ai-slop/SKILL.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/SKILL.md) for rule changes and [`scripts/build_plugin.py`](https://github.com/petergyang/no-ai-slop/blob/main/scripts/build_plugin.py) for build improvements. - Always run `python scripts/build_plugin.py` to generate the distribution zip before testing. - Use `python -m skills.no_ai_slop.eval` to verify that "no-slop" behavior functions correctly after modifications. - Submit contributions via Pull Request to the `main` branch with clear commit messages. ## Frequently Asked Questions ### What is the no-ai-slop project? The no-ai-slop project is a lightweight Codex Plugin designed to prevent AI-generated content from appearing in the Instag​it platform. It works by intercepting text generation requests and returning a "no-slop" response, ensuring that only human-written content is displayed to users. ### How do I test changes to the no-ai-slop plugin locally? To test changes locally, first run `python scripts/build_plugin.py` to package the plugin into `no-ai-slop.zip`. Then execute `python -m skills.no_ai_slop.eval` from the repository root to send sample prompts and verify that the blocking behavior works as expected according to the criteria in [`skills/no-ai-slop/eval.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/eval.md). ### What file should I edit to add new blocking rules? Add new blocking rules in [`skills/no-ai-slop/SKILL.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/SKILL.md). This file defines the plugin's capabilities and trigger conditions. After editing, rebuild the plugin using [`scripts/build_plugin.py`](https://github.com/petergyang/no-ai-slop/blob/main/scripts/build_plugin.py) to embed your changes into the distribution package. ### Can I contribute documentation improvements? Yes, documentation improvements are welcome. Update [`README.md`](https://github.com/petergyang/no-ai-slop/blob/main/README.md) for general project documentation or [`skills/no-ai-slop/eval.md`](https://github.com/petergyang/no-ai-slop/blob/main/skills/no-ai-slop/eval.md) for testing procedures. Ensure your changes align with the existing structure and follow the contribution workflow of forking, branching, and submitting a Pull Request to the `main` branch.