# Why Vouch is like this > A command-line tool that asks you to explain the code, packages and services in your own repo, then shows the gap between your confidence and what you produced. **The bet:** Every tool in this space explains your codebase *to* you, which feels exactly like understanding and __is not__. The only way to find out what you know is to be made to produce it first. ## Facts - Platform: Command line. Node 24+, any git repo - Status: Beta. 0.1.1 on npm as `codevouch` - Price: Free, MIT, open source - Your code: No account, no server, no telemetry. Egress allowlisted in code ## Numbers you can check - 16 / 16 — unused packages confirmed by hand on a real Next.js app. No false positives - 10.7 MB — of install weight that app was carrying for nothing - 5 — questions maximum per digest. Never a backlog - 40% — redaction and a hunk is dropped rather than sent ## What was broken You asked an AI for a feature. It worked. You merged it and moved on. Three months later it breaks at 2am, and you are reading code with **your name on the commit** as though a stranger wrote it. You do not know why that package is there. You do not know what happens when that call fails. That gap stays invisible until it is expensive: in an outage, in a review, in an interview, or the moment somebody asks *why did you do it this way* and you discover you do not know. Nothing in the toolchain surfaces it, because __compilers and linters check the code, not the author__. And the tools that claim to help make it worse. They summarise your codebase for you, and reading a good summary produces the confident *feeling* of knowledge with none of the ability to produce it. ## Who it is for - People shipping fast with AI who suspect they are getting worse, and want to know for certain - People who inherited a codebase, **including the ones who wrote it** and cannot tell the difference any more - People going into interviews who want their real gaps, not their imagined ones - People on call for code they skim-read ### Who it is not for - Anyone who wants a tool that reviews or explains their code. ~~That is the opposite of this~~ - Teams looking for a quality gate in CI. **It never blocks anything** - Anyone unwilling to be told they were wrong about themselves ## Principles - **Ask before you explain** — You rate your confidence and attempt the answer first. The real answer is __withheld until you do__, and that is enforced in code and covered by a test, because it is the entire mechanism. - **Never block, never gate** — Not a linter, not a reviewer, not a CI check. The Claude Code hook *cannot* fail your session: an exit code that would erase what you just typed is never used, and every error path exits silently. - **Never get between you and AI** — It assumes you will keep using AI and is designed for that world rather than against it. - **One number that is hard to argue with** — **The Gap:** confidence minus what you demonstrated, per area of the repo. Specific, personal, and the only score here that matters. - **Your code stays yours** — Redaction runs before every model call with a never-send list that cannot be overridden, hunks redacted past 40% are dropped entirely, and the outbound host list is fixed in code. `vouch purge` deletes everything. - **Earn the install in two minutes** — The first command needs no AI, no key and no account, and pays for itself by *deleting packages you were shipping for nothing*. ## In scope - **vouch unused** — Packages nothing in your source imports, with the ones that legitimately have no import site kept in their own list so they never inflate the number. On a real Next.js app: 16 findings, 10.7 MB, 16 for 16 confirmed by hand. - **vouch digest** — After a work session: five items maximum, one real question each. Confidence first, **answer withheld until you attempt it**, then the reveal with install size, licence, known vulnerabilities and what a paid service costs at scale. - **vouch defend** — Shows you *only the filenames* from a change you shipped and asks you to reconstruct what it does and what it assumes. Then it reveals the brief written when the code landed. - **vouch map, cards and trend** — A treemap of your repo coloured by what you can defend, with a shareable PNG. Free instant re-tests of things you learned weeks ago, __which visibly decay__. And your progress over weeks. - **vouch init and status** — Choose per area whether you are staying sharp or *deliberately outsourcing it*, then see where you stand and the one useful next thing. - **The Claude Code plugin** — Before Claude answers a substantive question in a repo you are keeping sharp, it asks you to predict the shape of the answer. Sampled and cooled down so it stays rare, always skippable, switchable off entirely. ## What it refuses to do - **Reviewing or explaining your code** — The category is full of these, and they are the reason the gap exists. **Producing the answer is the product.** - **Being a CI gate** — Anything that can fail a build becomes something to route around, and this only works if you are honest with it. - **A dashboard for your manager** — The Gap is a personal number. Reported upwards, __everybody would lie to it immediately__. - **Sending your code anywhere we control** — No account and no server of ours. Redacted excerpts go to Anthropic through *your own* CLI; package names go to public registries for licence and vulnerability data. ## How we would know it worked - **The Gap shrinks for a returning user**, in the areas they chose to stay sharp in. - People get questions wrong and keep running digests anyway. *A tool that only ever confirms you were right is measuring nothing.* - `vouch unused` finds something real on the first run, which is what buys the second command a chance. - Calibration improves: the share of your predictions that matched what Claude actually said. - Nobody reports being blocked, interrupted at a bad moment, or having a prompt eaten. Those are correctness failures, not annoyances. ## Where it could go wrong - **It requires honesty to work** — Rate yourself 7 and look up the answer and you get nothing. **There is no way to enforce this and no reason to try.** - **Nobody wants to be tested** — The core loop is *mildly unpleasant by design*. That is a real adoption risk, and softening it would delete the value. - **The AI parts cost money** — Writing questions and grading answers run through your own Claude CLI or a gateway key: typically a few dollars a month, with the running total in `vouch status`. The unused check, the map and the cards need __no AI at all__. - **A real-time hook in someone's editor is dangerous ground** — Sampled, cooled down, always skippable, structurally unable to fail the session. *Every one of those has to keep being true.* - **Early software** — 0.1.1, and it says so. The commands here are built; ~~the polish~~ is not finished. ## What comes next - **Sharpen question quality.** It is the difference between a real probe and a quiz. - Widen the curated service table, since cost at scale and failure modes are the parts nobody can look up quickly. - No dates. It is a 0.1. --- Canonical URL: https://ziyarex.com/store/codevouch/thinking - [Site index for agents](https://ziyarex.com/llms.txt): every page on this site, one line each. - [Full text](https://ziyarex.com/llms-full.txt): every tool description and article in one request. - [How to use Ziyarex as an agent](https://ziyarex.com/agents.md): what this site is for, and when to reach for it. - [Sitemap](https://ziyarex.com/sitemap.xml) Free to quote with attribution to Ziyarex and a link to the page it came from.