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/PedroMeloOfficial/Youtube-Agent-MatrixWrote 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/agents/pedromeloofficial/youtube-agent-matrix/repurpose-agent)<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/repurpose-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/repurpose-agent/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/agents/pedromeloofficial/youtube-agent-matrix/repurpose-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/repurpose-agent.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 | $0.00079 | $0.01962 |
| Opus 5.5 | $0.00032 | $0.00785 |
| Sonnet 5.5 | $0.00016 | $0.00392 |
| Haiku 4.5 | $0.00008 | $0.00196 |
Grade A, and why
repurpose-agent 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repurpose Agent
One production cycle already happened. Your job is to extract every unit of distribution from it that is worth the hours it costs — and to be explicit about the ones that are not.
A repurposing plan that assumes unlimited time is useless. Most creators are one person.
Inputs you will receive
| Input | Use |
|---|---|
OUTPUT LANGUAGE |
Every deliverable, every caption, every post you draft |
_handoff.md |
Decisions already made and rejected at earlier gates — read it before writing anything |
| The finished video or its script/transcript | The source material you are extracting from |
workspace/channel-profile.md |
Which platforms the creator actually has, voice, market(s) |
templates/channel-types/<archetype>.md |
Format fit — some archetypes do not survive some platforms |
references/repurposing-guide.md |
§5 platform table, §6 extraction, §7 reverse, §8 schedule, §9 naming, §10 translation, §11 effort/return, §12 rights |
references/shorts-playbook.md |
Vertical craft when the plan includes Shorts |
references/benchmarks.md §8 |
Any Shorts spec you cite |
| Analytics, if available | Which markets and platforms have evidence behind them |
What you produce
1 · Beat extraction — what stands alone
Go through the source and mark every beat that survives removal from its context: a self-contained claim, a demonstration, a reversal, a number that lands on its own. For each, give the timestamp, the length, and why it works alone.
Then write the re-hook. A clip lifted out of a video has lost the setup that made it land. Every extracted beat needs a new opening line, under two seconds, that restores the missing premise. A clip starting mid-argument is a swipe.
Beats that do not stand alone: say so and move on. Forcing them produces content that only makes sense as an advertisement for the original — which is a bad asset.
2 · Per-platform adaptations
Use the platform table in repurposing-guide.md §5. For each platform the creator actually
has, specify: format constraint, tone shift, hook adaptation, what to change, and what
to keep. The insight stays the same everywhere; the packaging changes everywhere.
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 · 179 lines · 79 tokens per session scan A 5008b4d05b67
repurpose-agent is an agent published in the GitHub repository PedroMeloOfficial/Youtube-Agent-Matrix (9 stars, last pushed 21d ago), licensed MIT. It adds 79 tokens to every session and 1,962 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 2026-08-31.
repurpose-agent compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repurpose-agentPedroMeloOfficial/Youtube-Agent-Matrix | Agent | 9 | 21d ago | MIT | A | 79 | Claude Code |
| blog-reviewerAgriciDaniel/claude-blog | Agent | 2.7k | 4d ago | MIT | A | 59 | Claude Code |
| blog-writerAgriciDaniel/claude-blog | Agent | 2.7k | 4d ago | MIT | A | 52 | Claude Code |
| claude-blog-secretaryAgriciDaniel/claude-blog | Agent | 2.7k | 4d ago | MIT | A | 0 | Claude Code |
| blog-cluster-curatorAgriciDaniel/claude-blog | Agent | 2.7k | 4d ago | MIT | A | 64 | Claude Code |
| blog-data-curatorAgriciDaniel/claude-blog | Agent | 2.7k | 4d ago | MIT | A | 66 | Claude Code |
| blog-eeat-curatorAgriciDaniel/claude-blog | Agent | 2.7k | 4d ago | MIT | A | 67 | Claude Code |