jordanrendric/claude-video-vision
Coding · tested 2026-09-30 · by the Hlido desk, not the vendor
In short: Popular Claude Code plugin that gives Claude frame-and-audio video understanding — strong traction and agent-consumable, but unversioned.
9 PASS · 1 FAIL of 10 public-surface claims
Quick answer
jordanrendric/claude-video-vision scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-30). STEADY (82) on strong repo health plus the agent-consumable pass, which the track rewards heavily. Pricing: Open source (free entry point documented).
claude-video-vision is a Claude Code plugin that extracts frames and analyses audio so Claude can 'watch' and reason about video. It is the strongest-traction item in this batch by community signal (997 stars, 115 forks) and, unlike most repos we rate on the surface track, it passes the agent-consumable check — it is built to be installed and driven inside an agent workflow, which is exactly the direction we weight highest. MIT-licensed, actively pushed, CI present. The vendor also makes a machine-readable marking statement in the repo, which we record but have not independently corroborated. The honest caveats are two: there are no tagged releases, so consumers pin to a moving branch rather than a stable version — a real operational risk for anything wired into a pipeline — and we have not hands-on tested extraction accuracy or how it degrades on long or low-quality video. As a capability-extender for Claude Code specifically, it is well-positioned; as a dependency, insist on pinning a commit until releases exist.
Why STEADY
STEADY (82) on strong repo health plus the agent-consumable pass, which the track rewards heavily. Below VITAL because of the repo-surface ceiling (no hands-on accuracy test) and the missing tagged releases — the one failed checklist item, and a genuine stability concern for a pipeline dependency.
Public-surface checklist
- PASS Repo reachable (required) — GH API 200 for jordanrendric/claude-video-vision
- PASS Readme present (required) — README length 7804
- PASS License present (required) — MIT
- PASS Install documented (required) — install/usage section found in README
- PASS Active 12mo (required) — last push 15d ago
- FAIL Releases present — no releases
- PASS Community traction — 997 stars
- PASS Ci or tests — 2 workflow file(s)
- PASS Recent commit 90d — last push 15d ago
- PASS Agent consumable — MCP server markers in README
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-d23e766fa2571b0a-github-com). Our own captures — not vendor marketing material.
What it does well
- Passes the agent-consumable check — designed to be installed and driven inside Claude Code
- Highest community traction in this cohort (997 stars, 115 forks)
- MIT-licensed, actively maintained, CI present
- Makes a machine-readable marking statement in the repository (recorded, not independently verified)
What it fails at
- No tagged releases — consumers pin to a moving branch, a real risk for a pipeline dependency
- Not hands-on tested: frame-extraction and audio-analysis accuracy are unverified
- Behaviour on long or low-quality video is undocumented
Best for
- Claude Code users who need video understanding without leaving the agent
- Developers who can pin to a specific commit to manage the no-release risk
- Multimodal workflows where frame + audio analysis is the missing capability
Not recommended for
- Teams that require versioned, release-pinned dependencies today
- Non-Claude-Code stacks (it is a Claude-specific plugin)
- Use cases needing verified accuracy guarantees on video analysis
Pricing & access
- ModelOpen source
- Free entry pointYes — a free tier or open-source edition is documented
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.
Related agents
Agent relevance
MCP
Agentic-Commerce Readiness 40/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
Installed as a Claude Code plugin and invoked in-agent to analyse video. Agent-consumable by design; pin to a commit given the absence of releases.
Agent-friendly score: 7/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
