character-lock

character-lock is a skill for Claude Code, Codex from MrJPTech/macro-pickle. It costs 37 tokens per session (2,629 once invoked), scanned A, original, MIT.

A workflow for keeping the same character looking consistent across multiple AI-generated images or video shots. It uses a reference image and written identity details as fixed points.

In plain words
What is it for?
Use it to create character reference sheets, prepare multi-shot sequences, extract identity details from a reference image, and troubleshoot character drift.
Why use it?
AI image and video generators can change a character's face, clothing, or other features between generations; this workflow helps reduce those changes.

Skill for Claude CodeCodex

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 skills/mrjptech/macro-pickle/character-lock
Any agent
npx skills add MrJPTech/macro-pickle --skill character-lock
Clone the repo
git clone --depth 1 https://github.com/MrJPTech/macro-pickle

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.

agentmods badge for character-lock

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrjptech/macro-pickle/character-lock.svg)](https://agentmods.dev/skills/mrjptech/macro-pickle/character-lock)
Your own site
<a href="https://agentmods.dev/skills/mrjptech/macro-pickle/character-lock"><img src="https://agentmods.dev/badge/skills/mrjptech/macro-pickle/character-lock.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00037 $0.02629
Opus 5 $0.00018 $0.01314
Sonnet 5 $0.00007 $0.00526
Haiku 4.5 $0.00004 $0.00263

Measured 4d ago against content hash 30c3790bfaa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

character-lock 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 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.

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.

.claude/skills/character-lock/SKILL.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Character Consistency for AI Video

Maintain strict character identity across multi-shot AI video and image sequences. This skill provides the Visual Anchor Workflow, Gemini JSON extraction protocol, and redundant text anchoring techniques to prevent character drift between generations.

When to Use This Skill

  • Creating a character that must appear identical across multiple video clips
  • Building multi-shot sequences (establishing shot, medium, close-up) of the same person
  • Preparing character reference sheets for Google Flow, Veo 3.1, or image generators
  • Extracting identity details from an existing reference image
  • Troubleshooting character drift between generations

Visual Anchor Workflow

Four sequential steps that lock a character's identity before generation begins.

Step 1: Establishing Shot (Create the Anchor Image)

Generate or select ONE hero image that defines the character. This becomes the ground truth for all subsequent shots.

Requirements for a strong anchor image:

  • Full body visible (head to mid-thigh minimum)
  • Neutral pose (standing or seated, facing camera or 3/4 angle)
  • Clean background (solid color or minimal environment)
  • Good lighting (even, no harsh shadows obscuring features)
  • All key accessories visible (glasses, jewelry, hat, bag)

Generation prompt template:

Full-body portrait photograph of [FULL CHARACTER DESCRIPTION].
Standing in a neutral pose against a [solid gray / white] backdrop.
Even studio lighting, sharp focus, high detail. No motion blur.
Photorealistic, 85mm portrait lens.

Step 2: Asset Binding (Extract and Lock Identity)

Once you have the anchor image, extract every visual detail into a structured character sheet. This is your binding document -- every future prompt references it.

Character Description Template:

CHARACTER: [Name / Identifier]

FACE & BONE STRUCTURE:
- Face shape: [oval / square / heart / round / diamond]
- Jawline: [sharp / soft / angular / rounded]
- Cheekbones: [high and prominent / subtle / wide-set]
- Forehead: [broad / narrow / high / low]
- Nose: [straight / aquiline / button / wide bridge / narrow]
- Lips: [full / thin / asymmetric / cupid's bow]
- Eyes: [shape, color, spacing, brow arch]
- Ears: [visible? pierced? size relative to head]
- Skin tone: [specific description, not just "light" or "dark"]
- Distinguishing marks: [moles, scars, freckles, dimples]

HAIR:
- Color: [specific — not just "brown" but "warm chestnut with copper highlights"]
- Length: [inches or reference point — "falls to collarbone"]
- Texture: [straight / wavy / curly / coily / kinky]
- Style: [how it is worn — "parted left, tucked behind right ear"]
- Hairline: [widow's peak, receding, straight across]

BUILD & PROPORTIONS:
- Height impression: [tall / average / short — relative to environment]
- Build: [slim / athletic / stocky / heavyset / wiry]
- Shoulder width: [narrow / broad / proportional]
- Posture: [upright / slightly hunched / relaxed slouch]

CLOTHING:
- Top: [garment type, color, material, fit, condition]
- Bottom: [garment type, color, material, fit]
- Footwear: [type, color, condition]
- Outerwear: [if any — jacket, coat, vest]
- Fit notes: [oversized, tailored, casual, rumpled]

ACCESSORIES:
- Eyewear: [glasses type, frame color, lens shape]
- Jewelry: [rings, necklace, earrings, watch — which hand/ear]
- Bag/carry: [type, color, how carried]
- Hat/headwear: [type, color, how worn]
- Other: [phone, badge, lanyard, gloves]

AGE INDICATORS:
- Estimated age range: [e.g., "early 30s"]
- Age markers: [crow's feet, laugh lines, gray at temples, youthful skin]

Read the full file on GitHub · 314 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 · 314 lines · 37 tokens per session scan A 30c3790bfaa7

Subscribe to this mod's changes

character-lock is a skill published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,629 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

剪辑环境的唯一管理者:就绪检查(skills 是否最新 → Runtime 是否配套)、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用;业务 Skill(剪口播/字幕/画面/导出)第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

infographic-template-updater

Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.

antvis/Infographic · 43 tokens