Borrowing it
Nothing to install: this file belongs to nikhilbhansali/youtube-data-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nikhilbhansali/youtube-data-skills/master/CLAUDE.mdgit clone --depth 1 https://github.com/nikhilbhansali/youtube-data-skillsWrote 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/instructions/nikhilbhansali/youtube-data-skills/claude-md)<a href="https://agentmods.dev/instructions/nikhilbhansali/youtube-data-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/nikhilbhansali/youtube-data-skills/claude-md/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/instructions/nikhilbhansali/youtube-data-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/nikhilbhansali/youtube-data-skills/claude-md.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 | $0.00667 | $0.00667 |
| Opus 5 | $0.00333 | $0.00333 |
| Sonnet 5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
youtube-data-skills CLAUDE.md 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 12d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Youtube Data Analysis skills
🔄 GitHub Auto-Sync
This folder is a private GitHub repository (origin) and is automatically kept in sync with GitHub by a Claude Code hook (~/.claude/hooks/git-autosync.sh).
- On every session start and end, the hook runs:
git add -A→ commit →git pull --rebase→git push. - Local and GitHub therefore stay mirrored with no manual steps. Sync activity is logged to
~/.claude/hooks/autosync.log.
Guidelines
- Secrets stay local.
.env,credentials,client_secret*.json,*.key,*.pemare git-ignored — never force-add them. - Large files (>95 MB) go through Git LFS. Run
git lfs track "*.ext"for new big/media files before committing. - Dependencies/junk (
node_modules/,venv/,.venv/,__pycache__/,.DS_Store) are git-ignored. - The auto-sync uses rebase and skips on conflict rather than forcing — if
autosync.logreports a conflict, resolve it manually.
Repo Conventions
- 12 skills live in
skills/<name>/— each is self-contained (SKILL.md+ bundledscripts/*.py+ optionalreferences/), because skills are distributed individually via skills.sh. Shared helper functions are intentionally duplicated (byte-identical) across scripts; if you change one helper, change it in all of them. - Outputs: raw JSON →
reports/data/, markdown reports →reports/, thumbnails →reports/thumbnails/. Thereports/dir is git-ignored (generated data). - Quota discipline: channel video listing uses the uploads playlist (
playlistItems.list, 1 unit/page) and handle resolution useschannels.list(forHandle=...). Never reintroducesearch.listfor channel-owned data — it costs 100 units/call and returns approximate results.search.listis only for keyword/topic search. - Two OAuth skills, two-token model — credentials live in
~/.config/youtube-skills/(override:YT_OAUTH_DIR), never in the repo.youtube-channel-insightsuses the read-only token (token.json; itsauth.pyrefuses write scopes).youtube-metadata-updateris the suite's ONLY write-capable skill: separatetoken_write.jsonwith exactlyyoutube.force-ssl(itsauth_write.pyrefuses any other scope set), titles/descriptions only, neverpart="status". Never merge the tokens, and never remove the metadata-updater's approval gate: preview must be shown to and approved by the user in conversation before anyapply --confirm. dist/*.skillare zip packages of each skill folder (git-ignored). Regenerate after skill changes:cd skills && zip -r ../dist/<name>.skill <name>.
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.
- 12d ago First seen · 24 lines · 667 tokens per session scan A 303e9f5f6aa5
youtube-data-skills CLAUDE.md is an instructions file published in the GitHub repository nikhilbhansali/youtube-data-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 667 tokens to every session, about $0.0033 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).