vibeguard: Command for Claude Code

.claude/commands/vibeguard/live-truth.md

VibeGuard: Live Truth is a command for Claude Code from majiayu000/vibeguard. It costs 20 tokens per session (553 once invoked), scanned A, original, MIT.

A verification command that checks current evidence for claims such as latest, ready to merge, merged, running, deployed, or published, while separating facts from assumptions and unknowns.

In plain words
What is it for?
Use it to check branch freshness, pull requests, CI and reviews, process health, live deployments, and whether package or release artifacts match their source.
Why use it?
It reduces the risk of reporting a project or release status based on stale information or inference alone.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is majiayu000/vibeguard's own configuration. It tells Claude Code how to work on vibeguard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibeguard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to majiayu000/vibeguard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/majiayu000/vibeguard/main/.claude/commands/vibeguard/live-truth.md
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: Live Truth

README.md
[![agentmods](https://agentmods.dev/badge/commands/majiayu000/vibeguard/live-truth/github.svg)](https://agentmods.dev/commands/majiayu000/vibeguard/live-truth)
Your own site
<a href="https://agentmods.dev/commands/majiayu000/vibeguard/live-truth"><img src="https://agentmods.dev/badge/commands/majiayu000/vibeguard/live-truth/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 VibeGuard: Live Truth

Your own site · 80×15
<a href="https://agentmods.dev/commands/majiayu000/vibeguard/live-truth"><img src="https://agentmods.dev/badge/commands/majiayu000/vibeguard/live-truth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 553 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 $0.00020 $0.00553
Opus 5 $0.00010 $0.00277
Sonnet 5 $0.00004 $0.00111
Haiku 4.5 $0.00002 $0.00055

Measured 9d ago against content hash fd8a4bbc60b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

VibeGuard: Live Truth 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 9d 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/live-truth.md · 51 lines

What it actually says

Core Concept

  • Turn stateful claims like "latest", "ready to merge", "merged", "running", "deployed", or "published" into fresh evidence.
  • Separate observed facts from inferences and unresolved gaps.
  • Produce a compact artifact that can be pasted into a final answer or PR comment.

Steps

  1. Pick the claim type from the user request:

    • latest: current git branch freshness against a fetched remote ref
    • pr-ready: PR state, draft state, mergeability, CI checks, and review evidence
    • merged: remote PR state plus optional local target branch containment
    • running: OS process identity plus optional health endpoint
    • deployed: live URL/health endpoint plus optional version/ref text
    • published: registry/package metadata plus tag, commit, or artifact checksum parity
  2. Run the reusable verifier:

    python3 ~/vibeguard/scripts/live_truth.py checklist
    python3 ~/vibeguard/scripts/live_truth.py latest --repo <repo_dir> --remote origin --branch main
    python3 ~/vibeguard/scripts/live_truth.py pr-ready --repo <owner/name> --pr <number>
    python3 ~/vibeguard/scripts/live_truth.py merged --repo <owner/name> --pr <number> --repo-path <repo_dir> --remote origin --branch main
    python3 ~/vibeguard/scripts/live_truth.py running --pid <pid> --health-url <url>
    python3 ~/vibeguard/scripts/live_truth.py deployed --url <url> --expect-text <version-or-ref>
    python3 ~/vibeguard/scripts/live_truth.py published --fixture <metadata.json>
    
  3. Report the verifier output without upgrading gaps into facts:

    LIVE-TRUTH <claim>
    verdict: pass | fail | gap
    facts:
    - ...
    inferences:
    - ...
    unresolved_gaps:
    - ...
    

Rules

  • Fresh evidence is required for mutable claims; memory alone is not proof.
  • A gap verdict must be stated as unresolved, not treated as success.
  • A fail verdict blocks claims that the state is ready, merged, live, current, or published.
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. 9d ago First seen · 51 lines · 20 tokens per session scan A fd8a4bbc60b2

Subscribe to this mod's changes

VibeGuard: Live Truth is a command published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 553 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.