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.
npx agentmods add commands/crisng95/flowkit/fk-review-videogit clone --depth 1 https://github.com/crisng95/flowkitWrote 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.
[](https://agentmods.dev/commands/crisng95/flowkit/fk-review-video)<a href="https://agentmods.dev/commands/crisng95/flowkit/fk-review-video"><img src="https://agentmods.dev/badge/commands/crisng95/flowkit/fk-review-video.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02267 |
| Opus 5 | $0.00000 | $0.01133 |
| Sonnet 5 | $0.00000 | $0.00453 |
| Haiku 4.5 | $0.00000 | $0.00227 |
Grade A, and why
fk-review-video scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:8100/health How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review AI-generated scene videos for quality using Claude Vision.
Usage: /fk-review-video <video_id> [--mode light|deep]
Default mode: light. Orientation auto-detected from project meta.json.
Prerequisites
ANTHROPIC_API_KEYenv var setffmpeg+ffprobeinstalled- Scenes must have completed videos (
${ori}_video_status = COMPLETED)
Step 1: Pre-check
# Verify server + extension connected
curl -s http://127.0.0.1:8100/health
# Must return: {"extension_connected": true}
# Verify video exists
curl -s http://127.0.0.1:8100/api/videos/<VID>
ABORT if extension not connected or video not found.
Step 2: Check scenes have completed videos
curl -s "http://127.0.0.1:8100/api/scenes?video_id=<VID>"
For each scene, verify ${ori}_video_status = COMPLETED (orientation auto-detected from meta.json).
ABORT if any scene is missing a completed video — tell user to run /fk-gen-videos first.
Step 3: Run review via API
curl -X POST "http://127.0.0.1:8100/api/videos/<VID>/review?project_id=<PID>&mode=light&orientation=${ORI}"
Parameters:
mode:light(default) ordeeporientation: auto-detected from meta.json (${ORI})
The API will extract frames from each scene video, send them to Claude Vision, and return per-scene quality scores.
Poll until complete:
curl -s http://127.0.0.1:8100/api/requests/<RID>
# Wait for status: "COMPLETED"
Step 4: Interpret results
The response is an array of per-scene review objects:
[
{
"scene_id": "abc-123",
"display_order": 0,
"total_score": 8.5,
"dimensions": {
"character_consistency": 9.0,
"prompt_adherence": 8.5,
"motion_quality": 8.0,
"visual_fidelity": 8.5,
"temporal_coherence": 8.0,
"composition": 9.0
},
"errors": ["Slight motion blur at 4s mark"],
"fix_guide": "Acceptable as-is. If re-generating, add 'sharp focus, crisp motion' to prompt.",
"usable": true,
"verdict": "good",
"usable_segments": [
{"start": "0s", "end": "4s", "score": 9.0},
{"start": "5s", "end": "8s", "score": 8.5}
]
}
]
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.
- 4d ago First seen · 222 lines · 0 tokens per session scan A 41d60628c02e
fk-review-video is a command published in the GitHub repository crisng95/flowkit (625 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,267 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
tag
Add or remove free-form tags on photos, then find them with search --tag.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.