flowkit: Instructions file for Claude Code

CLAUDE.md

flowkit CLAUDE.md is an instructions file for Claude Code from crisng95/flowkit. It costs 1,059 tokens per session, scanned A, original, MIT.

Project instructions for Flow Kit, a local service used to create projects, research topics, generate images and videos, and review them. They define required checks and the available workflow commands.

In plain words
What is it for?
Use them when creating Flow Kit projects, researching content, generating reference images, scene images, or videos, and reviewing generated media.
Why use it?
They reduce errors when working with the service by requiring a health check and a standard troubleshooting step when a pipeline fails.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Codex.

This is crisng95/flowkit's own configuration. It tells Claude Code how to work on flowkit 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 flowkit configures →

About the project

FlowKit is a standalone system that uses a Chrome extension to connect AI agents to Google Flow for generating images and videos, including text-to-video and image-to-video work. It is for people who want to create video content through Google Flow rather than operate its web interface manually. The catalogue entries provide commands and instructions for working with FlowKit.

crisng95/flowkit · 1,125 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to crisng95/flowkit. 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/crisng95/flowkit/main/CLAUDE.md
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 flowkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/crisng95/flowkit/claude-md/github.svg)](https://agentmods.dev/instructions/crisng95/flowkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/crisng95/flowkit/claude-md"><img src="https://agentmods.dev/badge/instructions/crisng95/flowkit/claude-md/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 flowkit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/crisng95/flowkit/claude-md"><img src="https://agentmods.dev/badge/instructions/crisng95/flowkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,059 This file is loaded in full into every session.
When invoked 1,059 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01059 $0.01059
Opus 5.5 $0.00424 $0.00424
Sonnet 5.5 $0.00212 $0.00212
Haiku 4.5 $0.00106 $0.00106

Measured 1mo ago against content hash e87394d3aabd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flowkit CLAUDE.md 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 1mo 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
CLAUDE.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow Kit

Base URL: http://127.0.0.1:8100

Pre-flight

curl -s http://127.0.0.1:8100/health
# Must return: {"extension_connected": true}

curl -s http://127.0.0.1:8100/api/flow/status
# Must return: {"transport": "batch", "flow_project_id": "<uuid>", ...}

Also needed: one signed-in https://flow.google.com/ tab left open. Only the page can sign a Flow request, so nothing works headless.

How to work

  • Always use /fk-* skills — all rules and workflows live inside each skill
  • Never write scripts to loop API calls — use POST /api/requests/batch
  • media_id is always UUID format (xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx), never CAMS... strings
  • On any pipeline error (request FAILED, stuck PROCESSING, extension_connected: false, HTTP 4xx/5xx from :8100, YouTube HttpError, error strings like UNSAFE_GENERATION / not found / CAPTCHA / NO_AT_TOKEN / NO_FLOW_PROJECT / UNSUPPORTED_ON_BATCH_API): invoke /fk-doctor before guessing a fix
  • flow_key_present: false is normal — the current transport has no bearer token

Since Flow moved (September 2026)

Flow lives at flow.google.com and signs every call in the page. Consequences that change how you work:

  • Projects are not created by Flow Kit any more. Make one in the Flow UI and pin its uuid as FLOW_PROJECT_ID, or pass flow_project_id to POST /api/projects.
  • Three capabilities are unported, all on the Veo path, because their payloads were never captured: video upscale (not image export, which works), Veo r2v, and Veo start+end-frame chaining. They fail with UNSUPPORTED_ON_BATCH_API rather than silently producing the wrong thing. Omni covers frame, first+last and reference modes — use model_family=omni_flash. FLOW_ALLOW_DEGRADED=1 drops Veo chaining and r2v to plain i2v; video upscale has no fallback. See docs/CAPTURE.md.
  • A poll saying "Media not found." is not a failure. Finished jobs report it.

Skills

Skill When to use
/fk-create-project New project with entities + scenes
/fk-research Fact-check before scripting
/fk-gen-refs Generate reference images for entities
/fk-gen-images Generate scene images
/fk-gen-videos Generate scene videos
/fk-gen-chain-videos Videos with scene chaining transitions
/fk-review-video Review video quality before upscale
/fk-review-board Visual scene review board for feedback
/fk-concat Download + concat final video
/fk-concat-fit-narrator Concat trimmed to narrator duration
/fk-gen-narrator Generate narrator text + TTS
/fk-gen-text-overlays Generate text overlays from narrator text
/fk-gen-tts-template Create voice template for narration
/fk-gen-music Generate music via Suno
/fk-creative-mix Creative video mixing techniques
/fk-pipeline Full pipeline orchestration
/fk-monitor Monitor running pipeline
/fk-status Project status dashboard
/fk-switch-project Switch active project
/fk-fix-uuids Fix non-UUID media_ids
/fk-refresh-urls Refresh expired signed media URLs
/fk-doctor Diagnose errors + prescribe fixes (Flow/extension/worker/YT)
/fk-add-material Set image material style
/fk-change-model Change video/image model
/fk-change-provider View & switch the AI CLI, model and effort per role (claude/agy/codex)
/fk-insert-scene Insert scenes into chain
/fk-upload-image Upload local image to get media_id
/fk-thumbnail Generate YouTube thumbnails
/fk-brand-logo Apply channel logo watermark
/fk-youtube-seo Generate YouTube metadata
/fk-youtube-upload Upload to YouTube
/fk-camera-guide Cinematic camera reference
/fk-thumbnail-guide Thumbnail design reference
/fk-import-voice Import existing voice template
/fk-dashboard Live statusline setup

Read the full file on GitHub · 81 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. 1mo ago Changed · +2 tokens per session e87394d3aabd
  2. 1mo ago Changed · +2 lines · +38 tokens per session 002c3d3a76ea
  3. 2mo ago Changed · +21 lines · +311 tokens per session 771cf3a3c8ec
  4. 2mo ago First seen · 58 lines · 708 tokens per session scan A 0a925d4bec7f

Subscribe to this mod's changes

flowkit CLAUDE.md is an instructions file published in the GitHub repository crisng95/flowkit (1,125 stars, last pushed 2d ago), licensed MIT. It adds 1,059 tokens to every session, about $0.0042 per session on Opus 5.5. 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.

Related

flowkit CLAUDE.md compared with instructions from other repositories

flowkit CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
flowkit CLAUDE.mdcrisng95/flowkitInstructions file1.1k2d agoMITA1,059Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode