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 skills add AgriciDaniel/youtuber --skill youtubergit clone --depth 1 https://github.com/AgriciDaniel/youtuberWrote 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/skills/agricidaniel/youtuber/youtuber)<a href="https://agentmods.dev/skills/agricidaniel/youtuber/youtuber"><img src="https://agentmods.dev/badge/skills/agricidaniel/youtuber/youtuber.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 | $0.00225 | $0.00877 |
| Opus 5 | $0.00112 | $0.00439 |
| Sonnet 5 | $0.00045 | $0.00175 |
| Haiku 4.5 | $0.00022 | $0.00088 |
Grade A, and why
youtube-brain 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Brain
Operate the vault first. Read CODEX.md, wiki/hot.md, and wiki/index.md
before changing notes.
Commands
/youtube-brain new <client-slug> --owner <name>
/youtube-brain ingest --vault <path> --file <source>
/youtube-brain synthesize --vault <path>
/youtube-brain report --vault <path>
/youtube-brain visuals --vault <path>
/youtube-brain lint --vault <path>
/youtube-brain next --vault <path>
Source checkout equivalent:
youtube-brain new <client-slug> --owner <name>
youtube-brain ingest --vault <path> --file <source>
youtube-brain synthesize --vault <path>
youtube-brain report --vault <path> --html-only
Required Operating Rules
- Read
<vault>/CODEX.md. - Read
<vault>/wiki/hot.md. - Read
<vault>/wiki/index.md. - Preserve
.raw/as immutable source material. - Never store credentials in the vault.
- Never make domain-specific claims without dated trustworthy sources.
- Keep
hot,index,overview, andlogcurrent. - Record research evidence in
references/source-ledger.json. - Record domain adapter completion in
references/adapter-manifest.json.
Script Mapping
new->python scripts/scaffold_vault.pyingest->python scripts/ingest_source.pysynthesize->python scripts/synthesize_brain.pyreport->python scripts/render_brain_report.pyvisuals->python scripts/generate_vault_visuals.pylint->python scripts/lint_vault.pynext->python scripts/guide_next_action.py
Quality Gates
- No growth, revenue, or monetization claim without a current official or primary source
- No credentials, OAuth tokens, cookies, earnings, or private audience data in repo artifacts
- No sub4sub, bot engagement, engagement bait, or platform-policy-violating tactics
- No account mutation or upload automation without explicit owner approval and an audit trail
- No irreversible recommendation without owner, confidence, source, and rollback note
Do not call this brain market-ready unless scripts/audit_brain.py --require market-ready passes. A scaffold is not a finished brain.
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 · 79 lines · 225 tokens per session scan A 2b01007a765c
youtube-brain is a skill published in the GitHub repository AgriciDaniel/youtuber (56 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 225 tokens to every session and 877 once invoked, about $0.0011 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 skills, from other repositories
cc-wiki
Distill the user's /.claude history into a Quartz knowledge base. Runs preprocess.py, dispatches parallel project-digest agents, then parallel cross-cutting synthesis agents (people / companies / projects / concepts / workflows / tools / playbooks), writes the spine, installs Quartz, and starts the dev server. Single…
note-promotion
Decide whether material should become a stable, reusable, linkable Obsidian note. Load when user asks to upgrade, promote, or stabilize material into a formal note. Do NOT use for inbox triage, link discovery, or weekly synthesis.
connection-review
Analyze relationships in a bounded set of Obsidian notes: candidate links, repeated patterns, contradictions, and follow-up opportunities. Load when user asks to find connections, suggest wikilinks, or surface contradictions. Do NOT use for inbox triage, weekly synthesis, or note promotion.
inbox-triage
Route raw Obsidian inbox captures into keep/promote/project/archive/deep-read. Load when user asks to triage inbox, sort captures, or process fleeting notes. Do NOT use for relationship analysis, synthesis, health diagnosis, or note creation.
opencode-context-maintenance
Diagnose drift across the OpenCode + Obsidian context stack when vault notes, config, or host reality no longer align. Load when context feels stale or records disagree with reality. Do NOT use for triage, synthesis, or vault CRUD.
vault-health-feedback
Diagnose whether an Obsidian knowledge workflow produces cognitive return or is becoming a passive archive. Load when vault feels archival or dead. Do NOT use for inbox triage, link review, synthesis, or direct restructuring.