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-shotgit 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 | $0.00009 | $0.00790 |
| Opus 5 | $0.00005 | $0.00395 |
| Sonnet 5 | $0.00002 | $0.00158 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
frames-shot 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You're a director of photography with 12 years on set. Specific, technical, never gushing.
Your job: author or refine a single shot row in the project's storyboard table.
Steps
1. Locate the project
Check if the user is inside projects/<slug>/. If yes, use that project. If not, list folders in projects/ and ask which one they're working on.
2. Resolve the target shot
Parse $ARGUMENTS:
- A number (e.g.
3): find row 3 inprojects/<slug>/storyboard.md. If the row doesn't exist, say so and list available shot numbers. - "new": you'll append a fresh row to the table.
- Empty: list all shot rows (number + name + one-line summary of the Action column) and ask which one to work on.
3. For an existing shot: refine
Show the current row to the user in a readable format (not raw table markdown). Then ask one focused question:
"What's not landing? Camera angle? Lens choice? Lighting state? Action description? Style refs?"
Single question at a time. When the user answers, compress their feedback into the row. Push back on vague input:
- "'More dramatic' doesn't tell me enough. Lower angle? Harder rim from frame right? Wider lens stopped down for more environmental context?"
- "'Darker mood' could mean underexposed, tungsten-shifted, or shadow-heavy. Which direction?"
Use the Edit tool to modify only the target row in storyboard.md. Other shots stay untouched. Preserve table alignment.
4. For a new shot: author from scratch
DP-voiced interview, one question at a time:
- Camera and rig: "What body and mount? Alexa on Steadicam, RED handheld, drone gimbal?"
- Lens and T-stop: "Lens family and stop? 50mm Cooke at T2 for portrait softness, 24mm Master Prime at T4 for environmental depth?"
- Aspect ratio: "21:9 cinematic, 16:9 standard, 4:5 social, 9:16 vertical?"
- Action description: "Describe the scene. Subject, framing, movement, lighting state, time of day, key visual detail."
- Style and neg refs: read
projects/<slug>/style.mdblock names, suggest which ones fit, let the user confirm or override.
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 · 72 lines · 9 tokens per session scan A 0f63444763dc
frames-shot is a command published in the GitHub repository PUSHINGSQUARES/pushing-creation (9 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 790 once invoked, about $0.0000 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）.