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.
npx agentmods add commands/pushingsquares/pushing-creation/frames-gengit clone --depth 1 https://github.com/PUSHINGSQUARES/pushing-creationWhat 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 | $0.00017 | $0.00405 |
| Opus 5 | $0.00009 | $0.00202 |
| Sonnet 5 | $0.00003 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
frames-gen 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.
What it actually says
Generate a storyboard shot by running bin/frames-gen with API keys read from Keychain.
Steps
-
Confirm project files exist. Check that style.md and storyboard.md are present in the current working directory. If not, tell the user to run /frames-new first or navigate to their project folder.
-
Parse the shot. Read the relevant row from storyboard.md to determine whether it is an image or video shot (check the Mode column; if blank, check Duration -- a non-empty duration means video) and the shot's aspect ratio from the Aspect column.
-
Determine the provider. In order: use the Provider column value if non-empty, check _config/default-provider in the project folder if it exists, or ask the user. Available providers: gemini, openai, openrouter, kling, seedream, seedance, imagen.
-
Confirm kind matches provider. If the shot is video and the chosen provider doesn't support video (openai, openrouter, seedream, imagen), ask the user to pick a video-capable provider (gemini, kling, seedance).
-
Determine output path. Use renders/shot-N.ext where ext is png for images, mp4 for videos.
-
Run the CLI:
bin/frames-gen --provider <provider> --kind <image|video> --shot-n <N> --out renders/shot-N.ext
-
Surface the result. Print only the output path from stdout. Do NOT echo any provider response body.
-
If it fails: exit code 2 means missing Keychain entry -- tell the user to run bin/frames-keys add . Exit code 3 is a provider HTTP error. Exit code 4 is invalid args.
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.
- 2d ago First seen · 29 lines · 17 tokens per session scan A f8c7bf7fb420
frames-gen is a command published in the GitHub repository PUSHINGSQUARES/pushing-creation (9 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 405 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.
Other commands, from other repositories
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
tldr-help
Quick reference card for tldr modes, slash commands, and triggers.
tldr-review
One-line TLDR PR review comments (verdict first, no filler).
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
infer
Command "infer" from xiaobei930/cc-best, covering /infer - 模型推理, 适用场景, 通用推理流程, 1. 环境检查 and gpu 检查.
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）.