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 skills add cafe3310/public-agent-skills --skill crane-shotgit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote 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.
[](https://agentmods.dev/skills/cafe3310/public-agent-skills/crane-shot)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/crane-shot"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/crane-shot/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.
<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/crane-shot"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/crane-shot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.00699 |
| Opus 5.5 | $0.00010 | $0.00280 |
| Sonnet 5.5 | $0.00005 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
crane-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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crane Shot Camera Animation
Camera begins at a low angle looking up at the product, then smoothly rises to reveal the full product from above. Creates a dramatic unveiling effect.
When to Use
- User wants a "reveal" or "unveil" shot
- User says "crane", "rise up", "low to high", "dramatic reveal"
- Product on a pedestal or platform
Parameters
| Parameter | Default | Description |
|---|---|---|
duration |
5 |
Video length in seconds |
fps |
24 |
Frames per second |
start_height |
-0.2 |
Starting height (below product level) |
end_height |
3.5 |
Ending height (above product) |
start_distance |
3.0 |
Starting distance |
end_distance |
4.0 |
Ending distance (pulls back as it rises) |
Flow
Step 1: Set Up Camera
import bpy, math
bpy.ops.object.empty_add(type='PLAIN_AXES', location=(0, 0, 0.05))
tgt = bpy.context.active_object
tgt.name = 'CraneTarget'
bpy.ops.object.camera_add(location=(1.0, -START_DISTANCE, START_HEIGHT))
cam = bpy.context.active_object
cam.name = 'CraneCam'
cam.data.lens = 45
trk = cam.constraints.new(type='TRACK_TO')
trk.target = tgt
trk.track_axis = 'TRACK_NEGATIVE_Z'
trk.up_axis = 'UP_Y'
bpy.context.scene.camera = cam
Step 2: Animate Crane Movement
TOTAL_FRAMES = DURATION * FPS
scene = bpy.context.scene
scene.frame_start = 1
scene.frame_end = TOTAL_FRAMES
scene.render.fps = FPS
# Start low
cam.location = (1.0, -START_DISTANCE, START_HEIGHT)
cam.keyframe_insert(data_path='location', frame=1)
cam.data.lens = 45
cam.data.keyframe_insert(data_path='lens', frame=1)
# Rise up and pull back
cam.location = (1.5, -END_DISTANCE, END_HEIGHT)
cam.keyframe_insert(data_path='location', frame=TOTAL_FRAMES)
cam.data.lens = 35
cam.data.keyframe_insert(data_path='lens', frame=TOTAL_FRAMES)
# BEZIER for smooth crane motion
Step 3: Render + Encode
Same pipeline — Cycles, PNG sequence, ffmpeg ProRes 4444.
ffmpeg -y -framerate 24 \
-i "~/Desktop/Blender Videos/crane_frames/%04d.png" \
-c:v prores_ks -profile:v 4444 -pix_fmt yuva444p10le \
"~/Desktop/Blender Videos/crane_shot.mov"
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 · 93 lines · 25 tokens per session scan A 1f7253a3144b
crane-shot is a skill published in the GitHub repository cafe3310/public-agent-skills (256 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 699 once invoked, about $0.0001 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 2026-11-05.
crane-shot compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crane-shotcafe3310/public-agent-skills | Skill | 256 | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |
| expertsflc1125/skills | Skill | 39 | yesterday | MIT | A | 62 | Claude Code, Codex |
| asyncflc1125/skills | Skill | 39 | yesterday | MIT | A | 52 | Claude Code, Codex |
| github-release-pr-writerflc1125/skills | Skill | 39 | yesterday | MIT | A | 80 | Claude Code, Codex |
| yuqueflc1125/skills | Skill | 39 | yesterday | MIT | A | 72 | Claude Code, Codex |
| getnoteflc1125/skills | Skill | 39 | yesterday | MIT | A | 83 | Claude Code, Codex |
| opentelemetry-go-reviewerflc1125/skills | Skill | 39 | yesterday | MIT | A | 34 | Claude Code, Codex |