A tool for creating still images, short animated videos, narrated episodes, avatar content, podcast videos, and looping background videos through the Higgsfield service. It provides command-line instructions for choosing models and submitting generation jobs.

Generating images, turning a keyframe into a video, listing available image or video models, rendering narrated episodes or podcast videos, and creating ambient loops.

It gives developers a way to request different kinds of visual media from scripts or terminal commands. This avoids having to build separate integrations for each supported generation task.

higgsfield — Skill for Claude Code and Codex by OpenCoven

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.

Any agent

npx skills add OpenCoven/coven --skill higgsfield

Clone the repo

git clone --depth 1 https://github.com/OpenCoven/coven

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/opencoven/coven/higgsfield.svg)](https://agentmods.dev/skills/opencoven/coven/higgsfield)

Your own site

<a href="https://agentmods.dev/skills/opencoven/coven/higgsfield"><img src="https://agentmods.dev/badge/skills/opencoven/coven/higgsfield.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,965 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 9
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01965
Opus 5	$0.00000	$0.00983
Sonnet 5	$0.00000	$0.00393
Haiku 4.5	$0.00000	$0.00197

Measured 8d ago against content hash 7eee394851af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

higgsfield 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 8d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (higgsfield-generate.sh, scripts/assemble_episode.py, scripts/check_setup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/higgsfield/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Higgsfield Skill

Generate images and videos via Higgsfield API. Covers: still images (flux_2), animated clips (Kling, Veo, Seedance), full narrated episodes, familiar avatars, podcast video rendering, and ambient loops.

Auth

Credentials live at ~/.config/higgsfield/credentials.json (set by higgsfield auth login). Never pass keys as CLI args or bake them into specs. HIGGSFIELD_API_KEY / HIGGSFIELD_API_SECRET are the env var names if needed.

CLI Path

HIGGS="$(npm root -g)/@higgsfield/cli/bin/higgsfield.js"
node "$HIGGS" <command>
# or if installed globally:
higgsfield <command>

Core Commands

# Image generation (flux_2 for stills)
higgsfield generate create flux_2 \
  --prompt "..." --aspect_ratio "16:9" --resolution "2k" --model "pro" \
  --wait --wait-timeout 5m --wait-interval 5s --json

# Video generation (Kling 3.0 for i2v)
higgsfield generate create kling3_0 \
  --prompt "..." --image path/to/keyframe.png \
  --aspect_ratio "9:16" --duration 5 --resolution "720p" --mode "std" \
  --wait --wait-timeout 10m --wait-interval 10s --json

# Model list
higgsfield model list --video
higgsfield model list --image

Image Models

Model	Use
`flux_2` pro	Canonical — high-quality stills, portraits, covers
`nano_banana_2`	Fast keyframes for i2v pipelines
`seedream_v4_5`	Character reference fidelity

Video Models

Model	Credits	Best for
`kling3_0`	2cr/s std	Image-to-video, coherence, expressions
`veo3_1`	22cr/8s	Native audio, dialogue lip-sync
`seedance_2_0`	22.5cr/5s	Multi-shot scenes, timeline prompts

Prompting Rules (distilled from docs/video-prompting-guide.md)

Universal skeleton

Camera/shot grammar + Subject + Action + Environment + Lighting/Style + Audio

Critical rules

Image-first: build stills, then animate. Still iteration is ~100x cheaper.
i2v prompts: never re-describe the input image. Action + camera + audio only.
Always specify ambient audio or models invent random dialogue/sounds.
Front-load dialogue — lip-sync degrades in the last third of long clips.
One camera move per clip. Stacked moves cause morphing.
Anchor phrases: "maintains exact appearance throughout", "consistent lighting", "stable camera movement".
Draft cheap (fast/720p), finalize expensive: regenerate good prompts 4–7x, harvest best.
Screenshot the last good frame as the next clip's start frame to chain beats.

Read the full file on GitHub · 184 lines

Files

What ships with it

18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 184 lines · 0 tokens per session scan A 7eee394851af

Subscribe to this mod's changes

higgsfield is a skill published in the GitHub repository OpenCoven/coven (47 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,965 tokens. 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.

Claude Code Creative and media agent-orchestration ai-agents codex model-agnostic opencoven

recording

Capture screen recordings and screenshots on any registered computer (macOS, Windows, Linux, HarmonyOS) and manage the recording library.

Hmbown/Codewhale · 29 tokens

figure-composer

Compose one publication-grade multi-panel figure. Start from a one-line claim plus immutable data Artifact Version references, or inspect an existing figure and draft its outline directly. Plan a 12-column panel outline, delegate one worker per panel, compose and inspect the result, then run at most three adversarial…

aipoch/open-science · 93 tokens

stage-assemble

How to execute a validated, currently authorized project/plan.json into one finished file. Start/resume with production.status; if planapprovalcurrent is false, pass the state to gate-control and stop instead of producing or opening child gates. Walk the signed EDL; do not re-plan. Host-neutral: VideoStudio-specific…

Orkas-AI/Orkas · 3 tokens

stage-plan

How to turn "here is my material + here's the video I want" into a single, inspectable plan that spans reference images, reference videos, deterministic editing, semantic editing, generation, and composition. The output is project/plan.json — a cross-modal Edit Decision List (EDL) — which the assembler walks.…

Orkas-AI/Orkas · 2 tokens

frontend-design

Use this as the design-lead layer for VideoStudio COMPOSE work. It shapes project/composition/composition-manifest.json::artdirection and the model-authored HTML/SVG motion graphics in index.html.