fk-review-board

fk-review-board is a command for Claude Code from crisng95/flowkit. It costs 0 tokens per session (742 once invoked), scanned C, original, MIT.

A command that starts a web-based Scene Review Board for inspecting video scenes. It groups scenes by chain and lets reviewers play them, label them, and record feedback.

In plain words
What is it for?
Use it to review scene videos, mark scenes as approved or needing image, video, or text changes, and export the feedback as JSON.
Why use it?
It gives a project team one place to review generated scenes and identify which ones need regeneration or editing.

Command for Claude Code

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/crisng95/flowkit/fk-review-board
Clone the repo
git clone --depth 1 https://github.com/crisng95/flowkit

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 fk-review-board

README.md
[![agentmods](https://agentmods.dev/badge/commands/crisng95/flowkit/fk-review-board.svg)](https://agentmods.dev/commands/crisng95/flowkit/fk-review-board)
Your own site
<a href="https://agentmods.dev/commands/crisng95/flowkit/fk-review-board"><img src="https://agentmods.dev/badge/commands/crisng95/flowkit/fk-review-board.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 742 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00000 $0.00742
Opus 5 $0.00000 $0.00371
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 4d ago against content hash 25592ad34fb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

fk-review-board scanned grade C with 2 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 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s http://127.0.0.1:8100/api/projects?limit=10 | python3 -c "

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

ACTIVE=$(curl -s http://127.0.0.1:8100/api/active-project)
.claude/commands/fk-review-board.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start the Scene Review Board web app for visual feedback on scene chains.

Usage: /fk-review-board [<video_id>]

What it does

Launches tools/review_server.py on port 8200, serving tools/review_board.html — a visual review board where you can:

  • See all scenes grouped by chain
  • Play scene videos inline
  • Tag scenes: OK / Regen Image / Regen Video / Edit
  • Write text feedback per scene
  • Export feedback as JSON

The board loads scenes for ?video_id=<id> query param (or a hardcoded fallback inside the HTML). Always pass the current project's video_id so the board reflects what the user is working on, not a stale default.

Steps

1. Resolve current video_id

Priority order — stop at first match:

a. Explicit arg — if user passed <video_id> to the skill, use that.

b. Active project — read GET /api/active-project:

ACTIVE=$(curl -s http://127.0.0.1:8100/api/active-project)
VID=$(echo "$ACTIVE" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('video_id',''))")
PNAME=$(echo "$ACTIVE" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('project_name','(none)'))")

c. No active project / no video_id — list recent projects and ask user to pick:

curl -s http://127.0.0.1:8100/api/projects?limit=10 | python3 -c "
import sys, json
for p in json.load(sys.stdin):
    print(f\"  {p['id']}  {p.get('name','-')}\")"

Then PUT /api/active-project with the chosen project_id and re-resolve.

If still empty, abort: "No active project. Run /fk-switch-project first."

2. Kill any existing process on port 8200

kill $(lsof -ti :8200) 2>/dev/null

3. Start the review server in background

python3 tools/review_server.py &

4. Open the board with explicit video_id query param

open "http://localhost:8200?video_id=${VID}"

The query param overrides the HTML's hardcoded default, so the board always loads the project resolved in step 1.

Read the full file on GitHub · 79 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. 4d ago First seen · 79 lines · 0 tokens per session scan C 25592ad34fb9

Subscribe to this mod's changes

fk-review-board 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 742 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.