VibeGuard: Check

VibeGuard: Check is a command for Claude Code from majiayu000/vibeguard. It costs 18 tokens per session (1,351 once invoked), scanned A, original, MIT.

A read-only project check that detects whether a codebase uses Rust, JavaScript or TypeScript, Python, or Go, then runs its guard scripts and reports problems by severity.

In plain words
What is it for?
Use it to inspect project health during development, compare results with a provided baseline, and decide which reported issues to fix.
Why use it?
It provides one health check for several common project types and helps spot new problems after code changes without modifying files.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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.

agentmods
npx agentmods add commands/majiayu000/vibeguard/check
Clone the repo
git clone --depth 1 https://github.com/majiayu000/vibeguard

Made for: Claude Code.

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 VibeGuard: Check

README.md
[![agentmods](https://agentmods.dev/badge/commands/majiayu000/vibeguard/check.svg)](https://agentmods.dev/commands/majiayu000/vibeguard/check)
Your own site
<a href="https://agentmods.dev/commands/majiayu000/vibeguard/check"><img src="https://agentmods.dev/badge/commands/majiayu000/vibeguard/check.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,351 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.01351
Opus 5 $0.00009 $0.00675
Sonnet 5 $0.00004 $0.00270
Haiku 4.5 $0.00002 $0.00135

Measured 6d ago against content hash 45b473614562, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

VibeGuard: Check 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 6d 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.

.claude/commands/vibeguard/check.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core Concept

  • Quickly and non-invasively check the code health of your current project
  • Automatically detect the project language and run the corresponding guard script
  • Output structured reports, sorted by severity
  • Can be run at any time during the coding process to verify that modifications do not introduce new problems

Guardrails

  • Read-only operation, no modification of any files
  • No automatic fixes — just report the problem and fix it at the user's discretion
  • If the user provides a preflight constraint set baseline, report changes compared to the baseline

Steps

  1. Determine project path and language

    • Project path: User parameters > Current working directory
    • Language detection:
      • Cargo.toml → Rust
      • package.json → TypeScript/JavaScript
      • pyproject.toml / setup.py / requirements.txt → Python
      • go.mod → Go
    • Locate the vibeguard installation path (~/Desktop/code/AI/tools/vibeguard/ or via the VIBEGUARD_DIR environment variable)
  2. Run universal guards and the guard script corresponding to the language

    Universal Project Checks:

    bash ${VIBEGUARD_DIR}/guards/universal/check_doc_overload.sh <project_dir>
    

    Rust Project:

    bash ${VIBEGUARD_DIR}/guards/rust/check_unwrap_in_prod.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/rust/check_duplicate_types.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/rust/check_nested_locks.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/rust/check_workspace_consistency.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/rust/check_single_source_of_truth.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/rust/check_semantic_effect.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/rust/check_taste_invariants.sh <project_dir>
    

    TypeScript/JavaScript Project:

    # eslint_guards: Automatically run npx eslint --max-warnings=0 when the project has eslint configuration.
    bash ${VIBEGUARD_DIR}/guards/typescript/check_any_abuse.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/typescript/check_console_residual.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/typescript/check_component_duplication.sh <project_dir>
    

    Python Project:

    python3 ${VIBEGUARD_DIR}/guards/python/check_duplicates.py <project_dir>
    python3 ${VIBEGUARD_DIR}/guards/python/check_naming_convention.py <project_dir>
    python3 ${VIBEGUARD_DIR}/guards/python/test_code_quality_guards.py
    

    Go Project:

    go vet ./...                                 # vet(MCP go.vet)
    bash ${VIBEGUARD_DIR}/guards/go/check_error_handling.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/go/check_goroutine_leak.sh <project_dir>
    bash ${VIBEGUARD_DIR}/guards/go/check_defer_in_loop.sh <project_dir>
    

    Each guard operates independently, and the failure of one does not affect other guards.

  3. Run Compliance Check

    bash ${VIBEGUARD_DIR}/scripts/verify/compliance_check.sh <project_dir>
    
  4. Summary Report

    Output format:

    ══════════════════════════════════
    VibeGuard Health Report
    Project: <project_name>
    Date: <date>
    ══════════════════════════════════
    
    ┌─ RS-03 unwrap/expect ─────────┐
    │ Found: 50 │
    │ Severity: Moderate │
    └────────────────────────────────┘
    
    ┌─ RS-05 Repeat Type ──────────────┐
    │ Found: 2 places │
    │ Severity: Moderate │
    │ - SearchQuery (server, core)  │
    │ - AppState (desktop, server)  │
    └────────────────────────────────┘
    
    ┌─ RS-01 Nested Lock ─────────────────┐
    │ Found: 0 places │
    │ Severity: ✓ Pass │
    └────────────────────────────────┘
    
    ┌─ RS-06 cross-entry consistency ──────────┐
    │ Found: 2 places │
    │ Severity: Moderate │
    └────────────────────────────────┘
    
    ┌─ Compliance Inspection ─────────────────────┐
    │ PASS: 3  WARN: 3  FAIL: 2    │
    └────────────────────────────────┘
    
    Overall rating: 6.5/10
    

Read the full file on GitHub · 137 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. 6d ago First seen · 137 lines · 18 tokens per session scan A 45b473614562

Subscribe to this mod's changes

VibeGuard: Check is a command published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,351 once invoked, about $0.0001 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 2026-08-30.