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 tonbistudio/buzz-skills --skill buzz-media-attachmentsgit clone --depth 1 https://github.com/tonbistudio/buzz-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/skills/tonbistudio/buzz-skills/buzz-media-attachments)<a href="https://agentmods.dev/skills/tonbistudio/buzz-skills/buzz-media-attachments"><img src="https://agentmods.dev/badge/skills/tonbistudio/buzz-skills/buzz-media-attachments/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/skills/tonbistudio/buzz-skills/buzz-media-attachments"><img src="https://agentmods.dev/badge/skills/tonbistudio/buzz-skills/buzz-media-attachments.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 | $0.00031 | $0.01064 |
| Opus 5 | $0.00015 | $0.00532 |
| Sonnet 5 | $0.00006 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade C, and why
buzz-media-attachments scanned grade C with 2 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
env = os.environ.copy() Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buzz Media Attachments
Use this workflow when a user asks to post a local media file into the current Buzz conversation and normal MEDIA:/path delivery fails.
Workflow
-
Verify the source file exists and is readable. Use
ffprobefor video metadata when relevant. -
Find the current Buzz channel UUID from the live gateway log rather than guessing:
# Search ~/.hermes/logs/gateway.log for the user's latest inbound Buzz message. # The line contains: platform=buzz ... chat=<CHANNEL_UUID> -
Use Buzz's native attachment mechanism:
buzz messages send \ --channel <CHANNEL_UUID> \ --content - \ --file /absolute/path/to/file--filemay be repeated to attach several files to one message. -
Load Buzz credentials without shell-sourcing
.env.BUZZ_AUTH_TAGcan contain JSON that shellsourcemangles. Parse the file withpython-dotenvand pass values through a subprocess environment:import os, subprocess from dotenv import dotenv_values env = os.environ.copy() env.update({ k: v for k, v in dotenv_values(os.path.expanduser("~/.hermes/.env")).items() if v is not None }) result = subprocess.run( ["buzz", "messages", "send", "--channel", channel_id, "--content", "-", "--file", file_path], input=caption, text=True, env=env, capture_output=True, timeout=180, ) -
If Buzz rejects an MP4, diagnose the returned relay error:
-
moov atom not at front of file (not fast-start): first try remuxing:ffmpeg -y -v error -i input.mp4 -c copy -movflags +faststart output.mp4 -
media contains metadata or a non-canonical metadata channel: use Buzz Desktop's canonical sanitizer settings. A simple stream-copy remux is insufficient because FFmpeg may retain or add forbidden MP4 metadata structures. Fully re-encode exactly as follows:
-
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 108 lines · 31 tokens per session scan C c734ce31cd16
buzz-media-attachments is a skill published in the GitHub repository tonbistudio/buzz-skills (263 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,064 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.