Leak Sweep
An AI tool secret scanner app idea: a scanner for secrets leaking into AI coding tool folders. One week build with Node.js, TypeScript, Claude API and Commander, for developers using ai coding assistants on real projects.
Why now
The Dev.to post "Your secrets don't need a git commit to leak into an AI tool" shows developers worrying about this gap that pre-commit hooks miss. The @supabase/supabase-js package is up 85% in weekly downloads, so more fresh projects are wiring keys into code and env files. From the signals of the week of 26 Oct 2026.
The spec
Scans your project and the config, history and context files that AI tools create, and flags API keys and tokens that never touched a git commit. It gives a short report with the file and a fix suggestion.
Build time
One weekAPIs or integrations · Level 3 of 5Audience
Developers using AI coding assistants on real projects.
Stack
- Node.js
- TypeScript
- Claude API
- Commander
Fun factor
Running it for the first time on your own folder is a mildly terrifying reveal.
Core features
- Scan project plus common AI tool folders
- Pattern and entropy based key detection
- Report grouped by file with masked values
- Pre-session CLI check
AI features
- Classify whether a flagged string is a real secret or a placeholder using surrounding context
- Generate a per-finding fix such as moving the key to an env var and rotating it
Stretch goals
- Git hook mode that blocks sessions on findings
- Allowlist file for known test keys
- GitHub Action version
First version
A CLI that scans a directory and AI tool config folders and prints masked findings with fix hints.
Build plan
4 milestones, in the order you would build them. Saved ideas get this plan with checkboxes and notes.
The build prompt
Paste this into ChatGPT, Claude, Codex, or Cursor, then build the first version before anything else.
# Build Leak Sweep You are a senior full-stack engineer pairing with me on a side project. Build a working first version of the product described below. Read the whole brief before writing any code, then follow "How to work" at the end. ## The idea **Leak Sweep.** Scans your project and the config, history and context files that AI tools create, and flags API keys and tokens that never touched a git commit. It gives a short report with the file and a fix suggestion. **Why now:** The Dev.to post "Your secrets don't need a git commit to leak into an AI tool" shows developers worrying about this gap that pre-commit hooks miss. The @supabase/supabase-js package is up 85% in weekly downloads, so more fresh projects are wiring keys into code and env files. **Who it is for:** Developers using AI coding assistants on real projects **What makes it fun:** Running it for the first time on your own folder is a mildly terrifying reveal. ## Scope - **Build time:** One week. Size every decision to ship a working first version inside this window. - **Technical ambition:** Level 3 of 5, "APIs or integrations". The product leans on third-party APIs. Wrap each integration in its own module, handle its failures and rate limits, and cache what is safe to cache. - **First version only.** Ship the core features below end to end. Stretch goals are listed so you can design around them, not build them. ## Core features (each must work end to end in the first version) 1. Scan project plus common AI tool folders 2. Pattern and entropy based key detection 3. Report grouped by file with masked values 4. Pre-session CLI check ## AI features - Classify whether a flagged string is a real secret or a placeholder using surrounding context - Generate a per-finding fix such as moving the key to an env var and rotating it How to build them: - Put every model call behind one server-side module with a typed interface, so the provider can change without touching the UI. - Read API keys from environment variables only, and document each one in `.env.example`. - Write prompts as versioned constants with clear instructions and an example of the expected output; parse and validate responses before using them. - Handle timeouts, rate limits, and malformed output with a graceful fallback the user can understand. Stream responses where a wait would exceed a couple of seconds. - Never let a feature depend on the model being perfect. Show the result, let the user edit or retry. ## Stretch goals (later, not in the first version) - Git hook mode that blocks sessions on findings - Allowlist file for known test keys - GitHub Action version Leave clean seams for these (a module boundary, a nullable column, a feature flag), but do not implement them unless I ask. ## Tech stack Use exactly: Node.js, TypeScript, Claude, Commander. Stay on current stable versions, follow each tool's official conventions, and add a library only when the standard library or the chosen stack cannot do the job cleanly. If part of this stack is a poor fit for a specific requirement, say so and propose the smallest change. ## Owner's notes Written by me, the project owner. Treat these as requirements and preferences that override the generated material above when they conflict. The first version should be exactly this, and no bigger: A CLI that scans a directory and AI tool config folders and prints masked findings with fix hints. ## Build plan (with saved progress) 0 of 4 steps complete. Resume at step 1: Walk the files. Before you start it, check what is already implemented so you do not repeat finished work. 1. **Walk the files** [not started] Collect project and AI tool files while respecting ignore rules. 2. **Detect candidates** [not started] Match key patterns and high entropy strings. 3. **Add AI triage** [not started] Send masked context to an LLM to separate real keys from fakes. 4. **Print the report** [not started] Group by file with a suggested fix each. ## Definition of done for the first version - [ ] Scan project plus common AI tool folders works end to end, with real data, not a placeholder. - [ ] Pattern and entropy based key detection works end to end, with real data, not a placeholder. - [ ] Report grouped by file with masked values works end to end, with real data, not a placeholder. - [ ] Pre-session CLI check works end to end, with real data, not a placeholder. - [ ] Every screen handles loading, empty, and error states. - [ ] Typecheck, lint, and any tests pass, and the main user flow was exercised by hand. - [ ] A README explains setup, environment variables, and how to run it locally. ## Quality bar - Responsive from a phone to a desktop, keyboard-accessible, semantic HTML, visible focus states, labelled inputs, and sensible contrast. - Loading, empty, and error states for every screen that reads or writes data. Errors say what happened and what to do next. - Validate on the server, never trust the client, and keep secrets in environment variables with a committed `.env.example`. - Type-safe end to end. No `any` without a comment explaining why. - Small, readable modules named after what they do. No premature abstraction, no dead code, no TODOs left for later without a note. - Sensible defaults over settings. If a choice is not in this brief, pick the simplest option that keeps the product coherent and say what you chose. ## How to work 1. **Read, then restate.** Summarize the product in three sentences and list your assumptions. Ask only the questions that block implementation. For everything else, decide and note the decision. 2. **Plan before code.** List the files and modules you will create, in build order, mapped to the core features. If a build plan is included above, use it instead: resume at the first step not marked done and check what already exists before touching it. 3. **Set up.** If a project already exists, inspect its code, instructions, and conventions first and build on them. Otherwise scaffold the stack above with linting, formatting, a typecheck script, `.env.example`, and a README stub. 4. **Model the data first.** Define the types, schema, and any migrations before the UI, so the shape of the product is settled early. 5. **Build in vertical slices.** Finish one core feature end to end (data, logic, UI) before starting the next. Keep the app runnable after every slice and commit each slice with a message that says what changed and why. 6. **Then the interface.** Apply the quality bar above to each screen as it lands, not as a final pass. 7. **Verify.** Run typecheck, lint, and tests. Exercise the main user flow by hand. Check each item in the definition of done and each acceptance criterion. 8. **Report.** Tell me what works, what you tested and how, what is not done, every setup step I must complete myself, and the three most useful next steps. Never claim a service, test, or flow was verified when it was not. If you can edit and run the project, start implementing right after the short plan. If you cannot, give me concrete code and the exact commands to run for the next step. Rules: keep the product name and the scope as written, do not invent features, prefer boring and proven choices, and stop to ask me when a decision would be expensive to reverse.
How to use
- Copy the prompt above.
- Open ChatGPT, Claude, or your AI editor and paste it into a new conversation.
- Build milestone one, run it, then move to the next. Add stretch goals only after the first version works.
Want ideas built around you instead? Generate four from your own interests, time, and stack.
FAQ
Frequently asked questions
Answers on what Leak Sweep is, how to build it, and where example ideas come from.
Similar to Leak Sweep
More developer tools ideas, then a few from other categories.
Ready to generate yours?
Four ideas per round, shaped by your interests, skill level, and how much time you have.