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/dasein108/yt-mem-aiWrote 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/dasein108/yt-mem-ai/yt-config)<a href="https://agentmods.dev/commands/dasein108/yt-mem-ai/yt-config"><img src="https://agentmods.dev/badge/commands/dasein108/yt-mem-ai/yt-config/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/dasein108/yt-mem-ai/yt-config"><img src="https://agentmods.dev/badge/commands/dasein108/yt-mem-ai/yt-config.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 | $0.00024 | $0.00443 |
| Opus 5 | $0.00012 | $0.00221 |
| Sonnet 5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
yt-config 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 11d 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
Use the yt skill's "Configure & maintain" flow to run the requested config operation for: $ARGUMENTS
Map the request to the CLI (values persist to the global config
~/.yt-mem-ai/config.env, secrets masked):
list(or empty $ARGUMENTS) →uvx yt-mem-ai config list— every setting, value, source.set KEY VALUE→uvx yt-mem-ai config set KEY VALUEget KEY→uvx yt-mem-ai config get KEY(add--revealfor secrets)unset KEY→uvx yt-mem-ai config unset KEYpath→uvx yt-mem-ai config path
Common keys (run config list for the full set):
WEBSHARE_PROXY_USERNAME/WEBSHARE_PROXY_PASSWORD+YT_USE_WEBSHARE true— route yt-dlp + transcripts through the Webshare proxy.YT_CAPTIONS_USE_WEBSHARE true— proxy ONLY the transcript API (fixes IP-rate-limited captions; yt-dlp stays direct).YT_COOKIES_BROWSER chrome(orbrave/firefox/edge) — fixes the YouTube "Sign in to confirm you're not a bot" bot check.YT_EMBEDDING_MODEL paraphrase-multilingual-MiniLM-L12-v2— multilingual embeddings (runuvx yt-mem-ai reembedafterwards to migrate the library).YT_CAPTION_LANGS en,es,…— preferred caption languages (priority order).
Only known keys are accepted and choice-constrained values are validated; if the
key is unknown, show config list so the user can pick a valid one.
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.
- 11d ago First seen · 32 lines · 24 tokens per session scan A 9c9633745d97
yt-config is a command published in the GitHub repository dasein108/yt-mem-ai (7 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 443 once invoked, about $0.0001 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 commands, from other repositories
context-save
An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation across AI workflows. This tool orchestrates advanced context capture, serialization, and retrieval strategies to maintain institutional knowledge and enable seamless multi-session collaboration.
save-session-learnings
Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.
init-workspace-flow-discovery
Phase 3 Discovery of init-workspace-flow.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.