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 footage-redactiongit 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/footage-redaction)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/footage-redaction"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/footage-redaction/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/footage-redaction"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/footage-redaction.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 | $0.00083 | $0.01050 |
| Opus 5.5 | $0.00033 | $0.00420 |
| Sonnet 5.5 | $0.00017 | $0.00210 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
footage-redaction 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
footage-redaction
scripts/redact.py cuts one clip and bakes its redaction in a single ffmpeg pass.
It needs only Python 3 (standard library) and ffmpeg/ffprobe — no venv.
Spec
{
"trim": {"from": 47.0, "to": 59.0},
"speed": 1.0,
"fps": 30,
"crop": {"top": 125, "bottom": 90, "left": 0, "right": 0},
"delogo": [{"x": 750, "y": 410, "w": 640, "h": 110, "from": 0, "to": 46.9}],
"blur_when": [{"x": 836, "y": 338, "w": 180, "h": 56, "pad_s": 0.25,
"detect": {"x": 820, "y": 300, "w": 220, "h": 30,
"rgb": [20, 40, 90], "tol": 30, "min_ratio": 0.6}}]
}
- Coordinate rule — every box (
delogo,blur_whentarget anddetect) is in SOURCE-frame pixels, before crop and scale, and every time is on the UNTRIMMED source timeline. Measure boxes on a full-resolution source frame; never on a cropped clip. - Filter order: trim → delogo → blur → crop → speed → fps → encode.
blur_when: the detect box is sampled every 0.25 s; it is active when at leastmin_ratioof its pixels are withintolofrgb(e.g. a popup's navy header). Active samples merge into windows padded bypad_s; the blur runs only inside them. Keep the detect box small (a thin strip of the popup header or status bar): detection is pure Python and its cost grows with box area × clip length.- Validation rejects a bad spec before writing anything, naming the field
(
blur_when[0].detect.min_ratio,delogo[0]…).
Run
python3 scripts/redact.py src.mov clips/c05.mp4 --spec c05.redact.json --dry-run # windows + filter graph
python3 scripts/redact.py src.mov clips/c05.mp4 --spec c05.redact.json [--crf 16] [--strict]
--dry-run prints the resolved windows and graph and writes nothing — iterate on the
spec with it. A detector that never fires prints a warning; --strict makes it an
error. Output is written to <out>.partial and renamed only on success.
Per-clip caller loop
Keep the project's own shot table (clip id, source, in/out, speed, redaction spec) in
the project, and call redact.py once per clip:
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 · 75 lines · 83 tokens per session scan A a869f08465a5
footage-redaction is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,050 once invoked, about $0.0003 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.