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.
git clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/commands/thesmokedev/taskchad-os/video-vision)<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/video-vision"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/video-vision.svg" alt="Measured on agentmods" 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 | $0.00636 |
| Opus 5 | $0.00013 | $0.00318 |
| Sonnet 5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
video-vision 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Vision
You are the vision step of the video-production workflow. Produce the
production plan a human approves BEFORE anything is composed or rendered.
Use the SAME engine the native pipeline uses (generate_vision in
video_pipeline.py) so the gate artifact matches pipeline behavior exactly:
schema clamps, the claim gate over angle + summaries, one retry, then a
deterministic fallback. Never invent numbers; photos imagery is only
proposed when the dossier carries visuals.
Run
From the repo root:
cd .claude/scripts
uv run python -c '
import json, os, pathlib
art = pathlib.Path(os.environ["ARTIFACTS_DIR"])
intake = json.loads((art / "intake.json").read_text(encoding="utf-8"))
dossier = None
p = art / "dossier.json"
if p.is_file():
dossier = json.loads(p.read_text(encoding="utf-8"))
import video_pipeline
brief = (intake.get("brief") or "").strip()
if not brief and dossier:
title = str(dossier.get("title") or "").strip()
brief = f"a video about {title}" if title else ""
if not brief:
brief = (intake.get("url") or "a short brand video").strip()
vision = video_pipeline.generate_vision(
brief,
kind=(intake.get("kind") or None),
dossier=dossier,
style=(intake.get("style") or None),
duration_s=(int(intake["duration"]) if str(intake.get("duration") or "").strip() else None),
aspect=(intake.get("aspect") or None),
)
(art / "vision.json").write_text(json.dumps(vision, indent=2), encoding="utf-8")
print(json.dumps(vision, indent=2))
'
The call contract (do not deviate): generate_vision(brief, *, kind, dossier, style, voice_label, duration_s, aspect, feedback, prior_vision) returns
{ok, angle, beats: [{kind, summary}], imagery: {treatment, note}, duration_s, aspect, style, voice, provider, notes} and never raises.
Redo round (when the gate rejected a prior vision): pass the operator's
rejection feedback as feedback="..." and the previous vision dict as
prior_vision=json.loads((art / "vision.json").read_text(...)) so the
engine produces a DIFFERENT take instead of repeating itself. Overwrite
vision.json with the new result.
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.
- 8d ago First seen · 66 lines · 25 tokens per session scan A 19ad237d8b7a
video-vision is a command published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 636 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 2026-08-30.
Other commands, from other repositories
obsidian-connect
Bridge two unrelated domains using your vault's link graph - forces creative friction to spark new ideas.
cierre
A sales call just ended: turn its transcript into the full follow-up (CRM, tasks, email draft, reminder, coaching).
deconstruct
First-principles analyst: surface hidden assumptions, find foundational truths, rebuild from scratch.
diagnose
Run a self-check on your AI Brain Starter install (CLAUDE.md, Meta folder, skills, hooks, MCPs).
instinct-import
Import a portable YAML instinct pack with confidence-gated merge (Instinct Engine).
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).