agentmods.dev

frames-new

A command that creates the starter files and folders for a cinematic project, including style and storyboard templates. A storyboard is a plan for the shots in a film or video.

In plain words
What is it for?
Use it to start a project with a project folder, visual-style notes, a sample shot plan, and a place for reference images.
Why use it?
It removes the need to set up the same project structure and planning files by hand.

Command for Claude Code

9 3mo ago A scan 12 tokens original MIT
View the source file PUSHINGSQUARES/pushing-creation
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/pushingsquares/pushing-creation/frames-new
Clone the repo
git clone --depth 1 https://github.com/PUSHINGSQUARES/pushing-creation

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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 $0.00012 $0.00386
Opus 5 $0.00006 $0.00193
Sonnet 5 $0.00002 $0.00077
Haiku 4.5 $0.00001 $0.00039

Measured 2d ago against content hash 4dddb747b40b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frames-new 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 2d 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/commands/frames-new.md · 34 lines

What it actually says

Parse $ARGUMENTS as the project slug. If empty, ask the user for a project name (lowercase, hyphens, no spaces).

Steps

  1. Create the project folder at projects/<slug>/ relative to the repo root.

  2. Copy templates:

    • templates/style.md to projects/<slug>/style.md
    • templates/storyboard.md to projects/<slug>/storyboard.md

  3. Create the refs folder at projects/<slug>/refs/ with a .gitkeep inside it.

  4. Report what was created:

Created projects/<slug>/
  style.md        starter STYLE_/NEG_ block library
  storyboard.md   BMW worked example (replace with your shots)
  refs/            drop reference images here
  1. Tell the user what to do next:
    • Drop reference stills, plates, and mood frames into refs/.
    • Open style.md and customize the STYLE_/NEG_ blocks to match their visual voice. The starter library covers common AI failure modes. Override block bodies with their own language.
    • Replace the BMW example shots in storyboard.md with their own shot list. Follow the same format: camera, lens, action, style refs, neg refs.
    • When /frames-brainstorm ships (v0.2), it will interview them with their reference images to write style.md live. Until then, hand-edit using the guidance in the skill.

Do NOT create any files outside projects/<slug>/. Do NOT modify templates.

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. 2d ago First seen · 34 lines · 12 tokens per session scan A 4dddb747b40b

Subscribe to this mod's changes

frames-new is a command published in the GitHub repository PUSHINGSQUARES/pushing-creation (9 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 386 once invoked, about $0.0001 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.

Creative and mediaPlanningai-cinematographyclaude-codeclaude-skillscreative-directionprompt-engineering
Related

Other commands, from other repositories

al

Run AgentLint diagnostic across all projects. Use when: user says /al, 'check all projects', 'agent lint', or '体检'.

0xmariowu/AgentLint · 30 tokens

tldr

Re-apply TLDR rules for this turn (verdict first, no filler).

0p9b/TLDR · 17 tokens

moyu-lite

Invoke the moyu:moyu-lite skill and follow it exactly.

uucz/moyu · 0 tokens

context

上下文管理，加载项目信息（会话级，另见 /cc-best:memory 管理持久记忆）.

xiaobei930/cc-best · 28 tokens

audit-plugin

Audit plugin skills, commands, and agents for structure, size, and naming issues.

justinjdev/fellowship · 17 tokens

lfe-dep-audit

Inspector sub-skill. Reviews dependency manifest files (package.json, requirements.txt, go.mod, Cargo.toml, pom.xml) changed in the current diff for risky version patterns and stale majors. Emits a human-run audit instruction rather than executing tools. Writes .plans/checks/depfindings.md. Called by lfe-inspector…

StChiotis/Library-First-Engineering · 81 tokens