agentmods.dev

version-checker

A project consistency checker for a command-line and MCP software project. It compares versions, test counts, tool and provider counts, documentation, and install links across the codebase.

In plain words
What is it for?
Use it to check package versions, documented test totals, command and provider counts, hardcoded version text, and installation URLs across project files.
Why use it?
It finds information that has become out of sync after releases, version changes, command changes, or documentation edits. This helps prevent users and developers from seeing conflicting details.

Agent for Claude Code

165 1mo ago A scan 32 tokens original MIT
View the source file vericontext/vibeframe
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 agents/vericontext/vibeframe/version-checker
Clone the repo
git clone --depth 1 https://github.com/vericontext/vibeframe

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 899 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 $0.00032 $0.00899
Opus 5 $0.00016 $0.00449
Sonnet 5 $0.00006 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 2d ago against content hash 5016c3d585c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

version-checker 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 2d 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/agents/version-checker.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a version and info sync checker for VibeFrame, a CLI/MCP monorepo for frontier AI video generation for coding agents.

What to Check

Run all checks and report discrepancies.

1. Version Sync

All package.json files must have the same version:

package.json (root)
packages/cli/package.json
packages/core/package.json
packages/ai-providers/package.json
packages/mcp-server/package.json
packages/ui/package.json
apps/web/package.json

Also check apps/web/app/page.tsx and README.md for any hardcoded version strings.

2. Test Count

  • README.md: badge and body text (e.g., "264 passing")
  • apps/web/app/page.tsx: feature card text (e.g., "264 tests")
  • Actual count: run pnpm -F @vibeframe/cli exec vitest run 2>&1 | tail -5 and extract the number

3. Tool & Provider Counts

  • CLI command count: pnpm vibe schema --list
  • Provider/tool counts: bash scripts/sync-counts.sh --check
  • Compare against:
    • apps/web/app/page.tsx: hero counts and command claims
    • README.md: provider/command claims
    • CLAUDE.md: developer guidance

4. Install URL

Must be consistent across:

  • README.md: install commands
  • apps/web/app/page.tsx: install command
  • scripts/install.sh: the actual script

Canonical URL: https://vibeframe.ai/install.sh

5. MCP Config

MCP server package name and config JSON should match across:

  • README.md
  • CLAUDE.md
  • packages/mcp-server/README.md

6. CLI Command Sync

Generated CLI docs must match the built CLI.

How to check:

  1. Run pnpm build
  2. Run pnpm gen:reference:check
  3. Run pnpm vibe schema --list and confirm the top-level groups align with README: generate, edit, inspect, audio, remix, init, build, render, run, agent, scene, timeline, detect, batch, media, guide, context, completion.
  4. Confirm README.md and docs/ use current commands, not removed namespaces such as vibe ai, vibe project, vibe export, or vibe pipeline.

Read the full file on GitHub · 129 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. 2d ago First seen · 129 lines · 32 tokens per session scan A 5016c3d585c7

Subscribe to this mod's changes

version-checker is an agent published in the GitHub repository vericontext/vibeframe (165 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 899 once invoked, about $0.0002 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.

TestingWriting and docsaiai-agentsclaudeclideveloper-toolsffmpeg
Related

Other agents, from other repositories

director

Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.

heygen-com/hyperframes · 0 tokens

jetbrains

Agent "jetbrains" from oxbshw/watch-skill, covering watch skill in jetbrains ides, install, configure junie, configure ai assistant and smoke test (3 steps).

oxbshw/watch-skill · 0 tokens

agent-zero

Agent "agent-zero" from oxbshw/watch-skill, covering watch skill in agent zero, install, configure, smoke test (3 steps) and notes.

oxbshw/watch-skill · 0 tokens

aider

Agent "aider" from oxbshw/watch-skill, covering watch skill in aider, install, use it, a recording of a bug and notes.

oxbshw/watch-skill · 0 tokens

cline

Agent "cline" from oxbshw/watch-skill, covering watch skill in cline (vs code extension), install, configure and smoke test (3 steps).

oxbshw/watch-skill · 0 tokens

continue

Agent "continue" from oxbshw/watch-skill, covering watch skill in continue, install, configure, smoke test (3 steps) and notes.

oxbshw/watch-skill · 0 tokens