Overview
intended-vs-implemented is an open-source docs skill for Claude Code and compatible agents, published by phuryn. Its author describes it as: “The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented i…”. The project has 25k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add phuryn/pm-skills`.
What intended-vs-implemented does
A linter scans code in a vacuum. It can tell you the code is *internally* consistent; it cannot tell you the code does what you *meant*, because it has no model of your intent. The highest-value security and correctness bugs live in that gap — a permission documented but never enforced, a "cron-only" endpoint anyone can call, a field marked public-only that leaks private data.
Best for
What’s inside
The SKILL.md for intended-vs-implemented is organised into these sections:
- Purpose
- Context
- Method
- What counts
- Notes
Installation
Add intended-vs-implemented to your agent with:
/plugin marketplace add phuryn/pm-skillsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
License
intended-vs-implemented is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in phuryn/pm-skills, an established project with 25,392 GitHub stars
- Works with Claude Code
- Actively maintained — repository updated in the last 90 days
Author
Topics
Frequently asked questions
- What does intended-vs-implemented do?
- The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy findings. Use when auditing AI-built code, reviewing access control against documented permissions, or checking whether a codebase matches its own documentation.
- How do I install intended-vs-implemented?
- Run /plugin marketplace add phuryn/pm-skills in your agent, then reload your skills. Review the source at https://github.com/phuryn/pm-skills before installing.
- Is intended-vs-implemented free to use?
- Yes. intended-vs-implemented is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does intended-vs-implemented work with?
- intended-vs-implemented lists Claude Code — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does intended-vs-implemented come from?
- intended-vs-implemented ships inside phuryn/pm-skills, a repository that contains 41 catalogued skills in total. The repository's 25,392 GitHub stars apply to that whole collection, not to this skill on its own.
