Vision Agents is a toolkit for building real-time multimodal AI agents that watch, listen to, and understand video. Developers use it to combine video providers and models such as YOLO, Gemini, OpenAI, and Claude in applications with voice and vision interactions.
Borrowing it
Nothing to install: this file belongs to GetStream/Vision-Agents. 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/GetStream/Vision-Agents/main/.claude/skills/pr/SKILL.mdgit clone --depth 1 https://github.com/GetStream/Vision-AgentsWrote 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/getstream/vision-agents/pr)<a href="https://agentmods.dev/skills/getstream/vision-agents/pr"><img src="https://agentmods.dev/badge/skills/getstream/vision-agents/pr/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/getstream/vision-agents/pr"><img src="https://agentmods.dev/badge/skills/getstream/vision-agents/pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.00366 |
| Opus 5.5 | $0.00007 | $0.00146 |
| Sonnet 5.5 | $0.00003 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
pr 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 2mo 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
Pull Request (Vision-Agents)
Before creating
- Run
git log main..HEAD --oneline. If the branch contains more than one independent logical change, STOP and ask the user whether to split it before proceeding. - Run
uv run --no-sync dev.py check. Skip if the diff does not touch Python code (*.py) orpyproject.toml— e.g. docs-only,.gitignore,.github/, or.claude/changes. - Do not run integration tests locally, CI handles them.
- If the change is user-facing (public API break, new feature, bug fix), update
CHANGELOG.mdper the rules inCLAUDE.md.
Creating
- Always
gh pr create --draft. Push the branch first. - Follow
.github/pull_request_template.md. Read every commit on the branch, do not summarise from the latest commit alone. ## Whyis motivation + context.## Changes, if included, is high-level; never per-bullet justifications, those belong in## Why.- Link public GitHub issues inline within
## Why(e.g. "users reported X (#478)"), not as a trailingFixes #N. - Do not paste CI, lint, or tool output in the body.
- Do not hard-wrap paragraphs. GitHub renders each newline inside a paragraph as a visible line break, so a 72-column-wrapped paragraph becomes a staircase. Write each paragraph or bullet as one unbroken line; rely on the browser to soft-wrap. Only use newlines to separate paragraphs, list items, or block elements.
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.
- 2mo ago First seen · 23 lines · 17 tokens per session scan A c2fb8fe02ce6
pr is a skill published in the GitHub repository GetStream/Vision-Agents (8,193 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 366 once invoked, about $0.0001 per session on Opus 5.5. 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
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".