AGENTS.mdA
AGENTS.md from nvidia-ai-blueprints/video-search-and-summarization is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add nvidia-ai-blueprints/video-search-and-summarization/AGENTS.md@git:20261022.44eb6dcPins git:20261022.44eb6dc in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- nvidia-ai-blueprints/video-search-and-summarization
- Path
AGENTS.md- Versions recorded
- 9
- Latest version
- git:20261022.44eb6dc, committed Oct 22, 2026
- First version recorded
- Aug 24, 2026
- Size
- 5,385 bytes
- Repository stars
- 1,968
- License
- Apache-2.0
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# AGENTS.md How to drive a VSS deployment from this repository, VSS CLI is the recommended approach to interact with a deployed VSS blueprint. **Looking for a capability rather than the CLI?** [`skills/`](skills/) holds the build, deploy and operational skills — deploy a profile, build a vision stack, search the archive, ask about a video, manage alerts, generate a report. [`skills/README.md`](skills/README.md) lists them; each `SKILL.md` says when to use it and when not to. Human contributor guidance — licensing, DCO, file headers — is in [CONTRIBUTING.md](CONTRIBUTING.md). What the blueprint *is* is in [README.md](README.md). Neither is repeated here. ## The `vss` CLI ### Setup The skills call `vss` from `PATH`. The OpenClaw and Hermes harness images (`.openclaw/Dockerfile`, `.hermes/Dockerfile`) ship it; anywhere else, install it from the same checkout as the skills you run, so the CLI and the skills are one version: ```bash uv tool install ./libs/vss/cli # from the checkout root vss --version ``` `libs/vss` is the library's own workspace and the agent stack is not in it, so the install is NAT-free by construction. Do not run `vss` through `docker exec` …
Read the whole file at its exact version.
How to install
mdr add nvidia-ai-blueprints/video-search-and-summarization/AGENTS.md@sha256:17554172606dfabdThe line at the top of this page pins the label git:20261022.44eb6dc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_kitafddtotwsldfe)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Aug 24, 2026 and Oct 22, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261022.44eb6dc latest | 2026-10-22 | 44eb6dc | 5,385 B | A | view · diff |
| git:20261013.d5283cc | 2026-10-13 | d5283cc | 5,200 B | A | view · diff |
| git:20260923.4c432f2 | 2026-09-23 | 4c432f2 | 5,162 B | A | view · diff |
| git:20260923.302e11a | 2026-09-23 | 302e11a | 4,954 B | A | view · diff |
| git:20260918.0224c97 | 2026-09-18 | 0224c97 | 4,984 B | A | view · diff |
| git:20260914.256ae38 | 2026-09-14 | 256ae38 | 4,945 B | A | view · diff |
| git:20260826.46a10af | 2026-08-26 | 46a10af | 5,154 B | A | view · diff |
| git:20260826.136bb60 | 2026-08-26 | 136bb60 | 7,873 B | A | view · diff |
| git:20260824.05857c1 | 2026-08-24 | 05857c1 | 7,879 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (5385 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
nvidia-ai-blueprints/video-search-and-summarization · 1,968 stars · license Apache-2.0 · pushed 2026-11-07 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_kitafddtotwsldfe GET https://markdownregistry.com/api/v1/resolve?ref=nvidia-ai-blueprints/video-search-and-summarization/AGENTS.md GET https://markdownregistry.com/api/v1/blob/17554172606dfabd943cb7e92720788a35398a2badcbb0ebc72721238e0af3f2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.
More from nvidia-ai-blueprints/video-search-and-summarization
Every file in nvidia-ai-blueprints/video-search-and-summarization