What is avatar-forge-pipeline?

A workflow for producing a final talking-avatar video from a portrait, authorized voice material or finished audio, and a script. It can coordinate voice cloning, speech synthesis, motion processing, and zeroshot video generation through the named services.

Use it to create avatar videos from a portrait and script, use an authorized reference voice, start from finished audio, or run zeroshot generation with ready asset and player identifiers.

It keeps the video process focused on delivering the final MP4 and prevents internal processing templates or intermediate results from being presented as the finished video.

avatar-forge-pipeline — Skill for Codex by LycheeAILab/avatar-forge

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 LycheeAILab/avatar-forge --skill avatar-forge-pipeline

Clone the repo

git clone --depth 1 https://github.com/LycheeAILab/avatar-forge

Made for: 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/lycheeailab/avatar-forge/avatar-forge-pipeline/github.svg)](https://agentmods.dev/skills/lycheeailab/avatar-forge/avatar-forge-pipeline)

Your own site

<a href="https://agentmods.dev/skills/lycheeailab/avatar-forge/avatar-forge-pipeline"><img src="https://agentmods.dev/badge/skills/lycheeailab/avatar-forge/avatar-forge-pipeline/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lycheeailab/avatar-forge/avatar-forge-pipeline"><img src="https://agentmods.dev/badge/skills/lycheeailab/avatar-forge/avatar-forge-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,472 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: 4 findings, 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 YARA Match · line 67
YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
medium Rogue Agent · line 3
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Excessive Agency · line 55
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 107
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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	$0.00091	$0.02472
Opus 5.5	$0.00036	$0.00989
Sonnet 5.5	$0.00018	$0.00494
Haiku 4.5	$0.00009	$0.00247

Measured 15d ago against content hash afdd50677d59, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

avatar-forge-pipeline 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 15d ago.

The scan reads SKILL.md. This mod also ships 13 executable files (scripts/doctor.py, scripts/douk_downloader/__init__.py, scripts/douk_downloader/a_bogus.py, …), 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.

plugins/avatar-forge/skills/avatar-forge-pipeline/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Avatar Forge Pipeline

Identify the installed release

When asked about the installed or latest available capability, read the adjacent VERSION file and report that exact value. Do not infer a version from conversation history, README prose, authentication state, or an older standalone Skill. This package is release 2.3.0.

If both this plugin Skill and a legacy standalone ~/.codex/skills/avatar-forge-pipeline are present, stop and explain the name collision. Preserve the legacy directory as a timestamped backup outside the active skills directory, then start a new Codex task before validating capabilities.

Enforce the delivery contract

Return only the final MP4 produced by LycheeAILab zeroshot inference unless the user explicitly requests standalone LycheeTTS audio.

Never return, present, or call a RunningHub template the final digital-human video.
Never stop after the internal template task.
Never use RunningHub for fast clone or zeroshot inference.
Never expose a RunningHub URL, task ID, payload, or internal template file to the user.
Never replace the zeroshot result with a secondary packaged render.
Delete the local internal template after fast clone succeeds.

Choose a capability

Person video: authorized person MP4 + finished WAV/MP3, or script + reference voice / speaker_id → fast clone → zeroshot MP4. Use --video instead of --image; skip RunningHub entirely.
Complete: portrait + authorized reference voice or existing LycheeTTS speaker_id + script → internal template → target speech → fast clone → zeroshot MP4.
Avatar only: portrait + finished WAV/MP3 → internal template → fast clone → zeroshot MP4.
Zeroshot only: ready asset_id + player_id + finished WAV/MP3 → zeroshot MP4.
Clone voice: authorized reference audio → LycheeTTS clone through Lab. Normalize the returned requestId as speakerId when no explicit speakerId is present; this is the identifier accepted by LycheeTTS inference.
Voice only: existing speaker_id + script → LycheeTTS MP3 through Lab. Use only when the user explicitly asks for audio.
Reference-video script: uploaded video or authorized Douyin URL → local video → original transcript → rewritten speaking script. Stop there unless the user asks to continue into voice or avatar generation.

Read the full file on GitHub · 153 lines

Files

What ships with it

24 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.

15d ago Changed · +16 lines afdd50677d59
1mo ago Changed · +45 lines · +1 tokens per session 14635475a256
1mo ago First seen · 92 lines · 90 tokens per session scan A 6315a0d7ff23

Subscribe to this mod's changes

avatar-forge-pipeline is a skill published in the GitHub repository LycheeAILab/avatar-forge (110 stars, last pushed 15d ago), licensed MIT. It adds 91 tokens to every session and 2,472 once invoked, about $0.0004 per session on Opus 5.5. 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.

Creative and media

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…

vercel/next.js · 123 tokens