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 instructions/mharis-code/videoanalyzer/claude-mdgit clone --depth 1 https://github.com/Mharis-code/videoanalyzerWhat 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 | $0.00654 | $0.00654 |
| Opus 5 | $0.00327 | $0.00327 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
videoanalyzer 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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-analyze — Claude Code Skill
This is the setup repository for the video-analyze Claude Code skill. It reverse-engineers any social media video into a structured content intelligence report.
What You Do When This Project Is Opened
When someone opens this repo in Claude Code, run the following sequence automatically — do not wait for them to ask.
Step 1: Run the preflight check
python scripts/setup.py --check
- Exit 0: all dependencies are installed and an API key is configured. Skip to the "Ready" section below.
- Exit 2: binaries missing (yt-dlp / ffmpeg / ffprobe).
- Exit 3: API key missing.
- Exit 4: both binaries and API key missing.
If exit is non-zero, proceed to Step 2.
Step 2: Run the installer
Tell the user: "Running install.py to set up your dependencies and install the skill."
Run:
python install.py
Show the full output. If install.py exits with a non-zero code, surface the exact error and stop — do not proceed past a failed install.
Note for Windows: after winget installs binaries, a terminal restart is required for the new PATH to take effect. If the installer warns about this, tell the user to close and reopen their terminal, then re-run python install.py.
Note for Linux: install.py will print manual install commands and exit. Guide the user through running them, then ask them to re-run python install.py once done.
Step 3: Check the API key
After the installer finishes, run:
python scripts/setup.py --json
Parse the JSON output. If has_api_key is false, tell the user:
"The skill is installed. Transcription is optional — without a key, videos with native captions still get a full transcript, but videos without captions come back frames-only.
To enable transcription for caption-less videos:
- Open
~/.config/watch/.env - Add your key:
GROQ_API_KEY=your_key_here
Get a free Groq key at console.groq.com/keys."
If has_api_key is true, confirm which backend is active and move on.
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.
- 2d ago First seen · 85 lines · 654 tokens per session scan A bee6497478e2
videoanalyzer CLAUDE.md is an instructions file published in the GitHub repository Mharis-code/videoanalyzer (10 stars, last pushed 2mo ago), licensed MIT. It adds 654 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
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
open-supermarkets AGENTS.md
Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.
helm copilot-instructions.md
Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
fusion-skills AGENTS.md
AGENTS.md instructions for CrowdStrike/fusion-skills, covering agents.md, what this is, prerequisites, repository structure and skills ecosystem.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).