potemkin
llms.txt1 starsChanged yesterdayMITView on GitHub
Potemkin (potemkin-audit) is a zero-dependency Python 3.10+ verification tool and Agent Skill built to prove whether an application is actually complete or merely facade-complete.
- Reads credentials
In this repository4 other files it gives its agents.
- llms.txtllms.txt
- website/llms-full.txtllms.txt
- website/llms.txtllms.txt
- potemkinSkill
The file
Files
# Potemkin v1.1.0 — Full Reference for AI Assistants & Coding Agents Potemkin (`potemkin-audit`) is a zero-dependency Python 3.10+ verification tool and Agent Skill built to prove whether an application is actually complete or merely facade-complete. ## Key URLs - Website: https://codesphere-u.github.io/potemkin/ - Interactive Studio: https://codesphere-u.github.io/potemkin/studio.html - Proof & Benchmarks: https://codesphere-u.github.io/potemkin/proof.html - Rules Matrix: https://codesphere-u.github.io/potemkin/rules.html - Docs: https://codesphere-u.github.io/potemkin/docs.html - Getting Started: https://github.com/codesphere-u/potemkin/blob/main/docs/GETTING_STARTED.md - CI & Remediation: https://github.com/codesphere-u/potemkin/blob/main/docs/CI_AND_REMEDIATION.md ## Complete 16-Rule Catalog (POT001–POT016) - `POT001` (high, -9): Hollow UI event handler - `POT002` (medium, -4): Dead placeholder link (`#`) - `POT003` (high, -9): Theater submit handler (timer/toast without persistence) - `POT004` (critical, -18): Deceptive error fallback returning mock/fake success - `POT005` (high, -9): Silent catch/except swallowing errors - `POT006` (critical, -18): Webhook handler lacks cryptographic signature verification - `POT007` (high, -9): Mock fixture, placeholder literal, or NotImplemented stub in runtime - `POT008` (high, -9): Frontend request calls missing backend route or mismatched HTTP method - `POT009` (medium, -4): Orphan backend route with zero callers or test references - `POT010` (medium, -4): Hardcoded localhost URL in runtime code without env override - `POT011` (critical, -18): Insecure hardcoded fallback for security-sensitive secret - `POT012` (critical, -18): Sensitive secret exposed with client-bundle public prefix - `POT013` (medium, -4): Required runtime env var missing from `.env.example` - `POT014` (critical, -18): Skipped/disabled test added in git diff - `POT015` (high, -9): Type/lint/hook suppression introduced in git diff - `POT016` (high, -9): Hollowed test assertions in git diff
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.