vibeproof

vibeproof is a skill for Claude Code, Codex from mrsametyildirim/vibeproof. It costs 93 tokens per session (3,991 once invoked), scanned A, original, MIT.

An audit for AI-generated applications that checks whether the features shown in the interface are actually connected to working code and stored data.

In plain words
What is it for?
Tracing forms, buttons, notifications, charts, and other visible promises from the interface through requests and database updates, using source evidence for each finding.
Why use it?
It exposes fake completeness, such as buttons that do nothing, success messages shown before a request finishes, hardcoded charts, or changes that vanish after a refresh.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Tracing forms, buttons, notifications, charts, and other visible promises from the interface through requests and database updates, using source evidence for each finding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mrsametyildirim/vibeproof/vibeproof
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mrsametyildirim/vibeproof --skill vibeproof
Clone the repo
git clone --depth 1 https://github.com/mrsametyildirim/vibeproof

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for vibeproof

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrsametyildirim/vibeproof/vibeproof/github.svg)](https://agentmods.dev/skills/mrsametyildirim/vibeproof/vibeproof)
Your own site
<a href="https://agentmods.dev/skills/mrsametyildirim/vibeproof/vibeproof"><img src="https://agentmods.dev/badge/skills/mrsametyildirim/vibeproof/vibeproof/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vibeproof

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrsametyildirim/vibeproof/vibeproof"><img src="https://agentmods.dev/badge/skills/mrsametyildirim/vibeproof/vibeproof.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,991 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.03991
Opus 5 $0.00046 $0.01996
Sonnet 5 $0.00019 $0.00798
Haiku 4.5 $0.00009 $0.00399

Measured 12d ago against content hash 68abd65cad96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vibeproof scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/vibeproof/SKILL.md · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeProof

Linters inspect your code. VibeProof inspects your product promises.

The failure mode this skill exists for is not a bug. It is a lie: a button that looks clickable and does nothing, a toast that says "Saved" before the request resolves, a chart drawn from a hardcoded array, a form that updates React state and loses it on refresh. The code has no syntax error. The linter is happy. The app is not done.

Your job is to find the gap between what the interface promises and what the code actually delivers — and to prove every claim you make.


The one rule that makes this tool worth trusting

A finding without quoted evidence is not a finding. Delete it.

You are auditing someone's work and telling them not to ship. That claim must be verifiable in seconds. For every single finding you must have:

  1. A real path/to/file.ext:LINE you actually opened and read
  2. The actual source line(s), quoted verbatim — not paraphrased, not reconstructed
  3. The specific broken link in the chain, named

If you cannot produce all three, the finding does not go in the report. A tool that cries wolf gets uninstalled after one run. Under-reporting is recoverable; false accusation is not.

Never guess a line number. Never describe code you did not read. If you suspect something but cannot open the file, say so in the Coverage section instead.


Never modify anything

VibeProof is read-only. Do not fix, refactor, add, or delete a single line — not even an obvious one-character fix, not even if asked politely mid-run.

The auditor who also patches loses the ability to be trusted about what was broken. The user fixes things afterwards in a separate, explicit request (fix VP-004), so the diff is theirs and the audit stays a record.

If the user asks you to fix something during a run: finish the report first, then treat fixing as a new task.


Procedure

Step 1 — Detect the product

Before looking for problems, understand what the app claims to be. Read, in order:

Read the full file on GitHub · 398 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 398 lines · 93 tokens per session scan A 68abd65cad96

Subscribe to this mod's changes

vibeproof is a skill published in the GitHub repository mrsametyildirim/vibeproof (1 stars, last pushed 13d ago), licensed MIT. It adds 93 tokens to every session and 3,991 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

laravel-audit-dsa

Run a read-only, orchestrated audit of a Laravel codebase for data structures, state representation, algorithms, and ownership. Use when asked for a DSA audit, subsystem inventory, or Aaron-style bounded agent audit.

MrPunyapal/laravel-auditor · 51 tokens

laravel-audit

Perform a deep, structured, evidence-based audit of a Laravel application and produce actionable findings backed by concrete project evidence. Use when asked to audit, review, assess, or evaluate an existing Laravel codebase.

MrPunyapal/laravel-auditor · 46 tokens

create_plan

Create detailed implementation plans through interactive research and iteration.

hoblin/claude-ruby-marketplace · 9 tokens

review-pr

Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.

hoblin/claude-ruby-marketplace · 39 tokens

laravel-audit-security

Audit a Laravel application's security boundaries: authorization, mass assignment, sensitive data, file/URL handling, CSRF, XSS, injection, and secrets. Use when auditing security or when asked to review security of a Laravel app.

MrPunyapal/laravel-auditor · 52 tokens

activerecord

This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…

hoblin/claude-ruby-marketplace · 180 tokens