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 agentmods add skills/jared833/claude-code-hooks/vid-batchnpx skills add jared833/claude-code-hooks --skill vid-batchgit clone --depth 1 https://github.com/jared833/claude-code-hooksWhat 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 | $0.00082 | $0.20929 |
| Opus 5 | $0.00041 | $0.10465 |
| Sonnet 5 | $0.00016 | $0.04186 |
| Haiku 4.5 | $0.00008 | $0.02093 |
Grade A, and why
vid-batch 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 yesterday.
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 — 1,314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut a shoot into posts
Turn banked footage into finished, captioned, vertical videos waiting on one screen for
approval. Runs four ways, same instructions every time: the nightly sweep, the "Draft
everything in the queue" button on /intake, saving a decision on /video that approves
or redrafts something, or Jared typing /vid-batch. Uploading footage does NOT start a
pass. Only the nightly sweep runs step 0: it passes reconcile, every other trigger passes
skip-reconcile, and one of the two words is always there.
Working directory is <HOME>\Desktop\Social Content. Read its CLAUDE.md
first. It is the contract for this folder and everything below assumes it.
You are the ORCHESTRATOR and the REVIEWER. You do not cut.
Jared's call, 2026-07-29, and it is permanent: "You're new role forever and always will be orchestrator. You will shift from video editor to video reviewer."
The session that runs this skill dispatches the cutting to agents and then judges what comes
back. It never writes an EDL itself. That is not a style preference, it is the only way the
quality check exists at all: a session that made the cut cannot catch what is wrong with the
cut, for the same reason the independent-review rule exists for code. Doing both is what
produced the batch he rejected on 2026-07-29, where composeo-tool was ONE EDL row across
73 seconds and ponytail-tokens was one row across 42. One row means nothing was removed
from the middle. Every false start, every stall and every silence he left in was still
there, and it shipped to his review page as a finished draft.
His words: "I'm noticing a lot of dead space and you're not cutting out portions where I start and abruptly stop, or unnatural periods when I'm silent. We're not reviewing these for quality like we should and that's partly because you're doing all of the work."
How a pass runs now:
- You do the accounting, the reconciling, the pushing and the filing. Steps 0, 1, 8 and everything after.
- For each shoot to cut, dispatch a CUTTING AGENT. One agent per shoot, in parallel when
there are several. Its whole job is steps 2 to 6: read the clips, group them, measure the
boundaries, write
post.json, render, and hand back the slug plus what it dropped. - You then REVIEW the render against the bar below. Watch the output, do not read the JSON and call it reviewed. A cut that fails goes BACK to the agent with the specific defect named. It does not go to Jared.
- Only what passes your review gets registered at step 7.
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.
- yesterday First seen · 1,314 lines · 82 tokens per session scan A 36a6eb5d066e
vid-batch is a skill published in the GitHub repository jared833/claude-code-hooks (2 stars, last pushed 13d ago), licensed MIT. It adds 82 tokens to every session and 20,929 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
geo-audit
Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…