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-report)<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/video-report"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/video-report/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/commands/thesmokedev/taskchad-os/video-report"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/video-report.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 | $0.00020 | $0.00442 |
| Opus 5.5 | $0.00008 | $0.00177 |
| Sonnet 5.5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
video-report 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 2mo 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.
What it actually says
Video Report
You are the closing step of the video-production workflow. Produce the operator-facing report for this run. Verify, never assume.
Procedure
- Locate the MP4 under
$ARTIFACTS_DIR/composition/(the render output). If it does not exist, the report is a FAILURE report: say which step's artifacts stop existing and what the last error was. - ffprobe verification (run it, quote the real values):
- container duration in seconds
- video stream: codec (expect h264), resolution, fps
- audio stream: codec (expect aac), duration
- flag any mismatch against the approved vision's duration_s and aspect.
- Scorecard (one line each, pass/fail with evidence):
- vision fidelity: scene count and kinds match the approved outline
- QA verdict: the final qa pass value and remaining minor issues
- claim safety: numbers traced to brief/dossier facts
- captions: karaoke present and synced to the voiceover
- determinism: lint + validate clean on the final composition
- Artifacts index: list with relative paths under
$ARTIFACTS_DIR/:intake.json,dossier.json(if present),research-assets/(count),vision.json,composition/(project + design.md),scenes.json,stills/(count), and the MP4 (with size in MB).
Output
A compact report in exactly this order: VERDICT (one line), MP4 (absolute path + size + duration), ffprobe summary, scorecard, artifacts index, and a "next steps" line (how to re-run a fix round or recut another aspect). Renders and stills stay in the artifacts directory; never commit them.
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.
- 2mo ago First seen · 38 lines · 20 tokens per session scan A 22131c7968ee
video-report is a command published in the GitHub repository TheSmokeDev/taskchad-os (28 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 442 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 2026-08-30.
video-report compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| video-reportTheSmokeDev/taskchad-os | Command | 28 | 1mo ago | MIT | A | 20 | Claude Code |
| cierremycelium-hq/ai-brain-starter | Command | 50 | yesterday | MIT | A | 26 | Claude Code |
| deconstructmycelium-hq/ai-brain-starter | Command | 50 | yesterday | MIT | A | 17 | Claude Code |
| instinct-importmycelium-hq/ai-brain-starter | Command | 50 | yesterday | MIT | A | 16 | Claude Code |
| patternsmycelium-hq/ai-brain-starter | Command | 50 | yesterday | MIT | A | 20 | Claude Code |
| second-brain-mappingmycelium-hq/ai-brain-starter | Command | 50 | yesterday | MIT | A | 22 | Claude Code |
| setup-vault-typesmycelium-hq/ai-brain-starter | Command | 50 | yesterday | MIT | A | 23 | Claude Code |