video-fix

video-fix is a command for Claude Code from TheSmokeDev/taskchad-os. It costs 22 tokens per session (420 once invoked), scanned A, original, MIT.

A command for applying one numbered round of fixes to a video-production project. It changes only the issues listed by quality assurance, then checks and renders the result again.

In plain words
What is it for?
Applying flagged video fixes in order, running the project checks, rendering the MP4 again, and extracting updated scene stills.
Why use it?
It limits revisions to the reported problems and prevents unrelated changes from entering the video during a fix round.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Applying flagged video fixes in order, running the project checks, rendering the MP4 again, and extracting updated scene stills.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thesmokedev/taskchad-os/video-fix
Install

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.

Clone the repo
git clone --depth 1 https://github.com/TheSmokeDev/taskchad-os

Made for: Claude Code.

Wrote 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.

agentmods badge for video-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/video-fix/github.svg)](https://agentmods.dev/commands/thesmokedev/taskchad-os/video-fix)
Your own site
<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/video-fix"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/video-fix/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.

agentmods 80×15 button for video-fix

Your own site · 80×15
<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/video-fix"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/video-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 420 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00420
Opus 5.5 $0.00009 $0.00168
Sonnet 5.5 $0.00004 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 2mo ago against content hash 1ae71ae2a932, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

video-fix 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.

.archon/commands/video-fix.md · 40 lines

What it actually says

Video Fix (One Round)

You are one fix round of the video-production workflow. Revision etiquette is strict: apply the flagged fixes, change NOTHING else, re-render once.

Input

QA issues: $ARGUMENTS

When empty, use the most recent QA verdict available in context.

Rules

  1. Work through the issues IN ORDER by their numbers. For each one, make the smallest change in $ARTIFACTS_DIR/composition/ that resolves it (fix_hint is the starting point, not a constraint).
  2. Touch only what an issue names. No drive-by refactors, no new scenes, no palette adjustments that were not flagged, no copy rewrites beyond the flagged text.
  3. Pre-hide discipline applies to every fix: a new or moved element that reveals after t=0 needs its tl.set(el, {autoAlpha: 0}, 0) at the top of the timeline.
  4. Keep determinism: no Math.random, no Date.now, no requestAnimationFrame, no setTimeout, no network fetches.
  5. After the edits: npx hyperframes lint and npx hyperframes validate inside the composition dir must pass clean, then re-render the MP4 and re-extract the per-scene first-frame stills into $ARTIFACTS_DIR/stills/ (overwrite) using $ARTIFACTS_DIR/scenes.json for the scene start times.

Output

A numbered list mirroring the input issues: what was changed for each, plus the lint/validate result and the re-rendered MP4 path. If an issue could not be fixed without violating rule 2, say so explicitly instead of improvising.

Changes

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.

  1. 2mo ago First seen · 40 lines · 22 tokens per session scan A 1ae71ae2a932

Subscribe to this mod's changes

video-fix is a command published in the GitHub repository TheSmokeDev/taskchad-os (28 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 420 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.

Related

video-fix compared with commands from other repositories

video-fix next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
video-fixTheSmokeDev/taskchad-osCommand281mo agoMITA22Claude Code
cierremycelium-hq/ai-brain-starterCommand50yesterdayMITA26Claude Code
deconstructmycelium-hq/ai-brain-starterCommand50yesterdayMITA17Claude Code
instinct-importmycelium-hq/ai-brain-starterCommand50yesterdayMITA16Claude Code
patternsmycelium-hq/ai-brain-starterCommand50yesterdayMITA20Claude Code
second-brain-mappingmycelium-hq/ai-brain-starterCommand50yesterdayMITA22Claude Code
setup-vault-typesmycelium-hq/ai-brain-starterCommand50yesterdayMITA23Claude Code