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 BlackBeltTechnology/pi-agent-dashboard --skill hyperframes-showreelgit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/hyperframes-showreel)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/hyperframes-showreel"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/hyperframes-showreel/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/blackbelttechnology/pi-agent-dashboard/hyperframes-showreel"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/hyperframes-showreel.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 | $0.00089 | $0.01534 |
| Opus 5.5 | $0.00036 | $0.00614 |
| Sonnet 5.5 | $0.00018 | $0.00307 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
hyperframes-showreel 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 19d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hyperframes-showreel
End-to-end pipeline from real footage to a delivered HyperFrames showreel. HyperFrames
is used only through its public CLI (npx hyperframes …); none of its skills or code
is vendored here. Last verified with HyperFrames 0.8.72 (2026-09-24) — a data point,
not a pin.
Ground rules
- Footage-only rule — every process shown on screen comes from real footage. No AI insert may depict a process that has no footage; if there is no recording of it, the beat is cut from the script.
- Screen-blend FX rule — Veo output is used only as an additive FX layer: rendered
on a black background and composited with
mix-blend-mode: screenover the footage (light, particles, flares, scan lines). It never replaces a shot.
Pipeline
- Footage sampling — contact sheets of every source (
ffmpeg -i src.mov -vf "fps=1/2,scale=480:-2,tile=6x6" sheet_%02d.png); note sensitive regions and usable moments with timecodes. - Edit script — acts, shots, source timecodes, on-screen copy, FX layer map. Every shot names its source clip and in/out.
- Clip cutting with redaction baked in — one call per clip via the
footage-redactionskill (crop / delogo / timed blur in source-frame coordinates), then contact-sheet verification of every clip. - Generated composition, pass 1 — a generator script turns the shot table into
index.html+ one scene sub-composition per act, with provisional scene durations and a temp track or none. See references/generator-pattern.md. - Optional Veo FX layers — black-background renders (e.g.
veo-showreel-production-kit+veo-generator), screen-blended per the rule above. npx hyperframes checkand snapshots —checkmust report 0 errors;npx hyperframes snapshot --at <t1>,<t2>,…at scene midpoints to verify framing.- Preview and user review —
npx hyperframes preview; the user approves the picture before music is fitted. - Music, punches, generation pass 2 — cut the music with
music-edit-to-length(listen-before-lock), pick hits withbeat-sync-video, then regenerate the composition: re-run the generator with scene starts from_edit.json(downbeats_video, a boundary on each drop), punches from_hits.json, and root duration = the edit'sduration. - Delivery render —
npx hyperframes render . -o ../export/showreel_v1.mp4 --fps 30 --quality delivery --video-frame-format png. - Export QA — the gate below; a render is not "done" until it passes.
- Upload — copy the export (and its subtitles) to the agreed share; record the location next to the file.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 19d ago First seen · 82 lines · 89 tokens per session scan A 5be98675c4d8
hyperframes-showreel is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 1,534 once invoked, about $0.0004 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 2026-09-27.
Other skills, from other repositories
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-plan-by-design
Compile a design document into a ralphex execution plan.
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-project
Understand the current project before defining a product change that must fit into an existing product.
goga-define-requirements
Define the product requirements that describe what the product must do to deliver the established user experience and achieve the agreed product goals.