Cosmos3 Codebase Navigation
SkillFiles & storageUse when navigating the Cosmos3 integration in NPA or locating upstream Cosmos3 framework files, defaults, scripts, configs, recipes, and docs.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Cosmos3 Codebase Navigation skill
What this skill tells your AI
The instructions your AI receives, as published by nebius/nebius-physical-ai in skills/atomic/cosmos3-codebase-nav/SKILL.md and read by ahel’s review.
Source And Attribution
Adapted from NVIDIA cosmos-framework
skills/atomic/cosmos3-codebase-nav/SKILL.md.
Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. Used under OpenMDW-1.1.
See skills/LICENSE-NVIDIA-COSMOS3-OPENMDW-1.1 and
skills/NOTICE-NVIDIA-COSMOS3.
When To Use
Use this skill when the user asks where Cosmos3 setup, access checks, inference defaults, parser settings, workflows, or post-training configs live. Also use it when reviewing or modifying PRs that touch Cosmos3 support in NPA.
NPA Integration Map
Primary NPA files:
| Need | File |
|---|---|
| Cosmos3 access, fetch, redaction, parser config, inference arg builder | npa/src/npa/workbench/cosmos/cosmos3.py |
| Real Cosmos 3 generation runner (CLI/SDK/YAML share it) | npa/src/npa/workbench/cosmos/generate.py |
| Containerized runtime (framework pinned, no weights baked) | npa/docker/workbench/cosmos3/Dockerfile |
| Build-time proof the generate deps resolve for every mode | npa/docker/workbench/cosmos3/verify_env.py |
| Generate CLI / SDK | npa/src/npa/cli/workbench/cosmos3.py, npa/src/npa/sdk/workbench/cosmos3.py |
| Nano vLLM-Omni continuation and source-conditioned augmentation | npa/src/npa/workbench/cosmos/nano_video.py, npa/src/npa/workbench/cosmos/nano_video_augment.py |
| Nano augmentation artifact handoff and recovery | npa/src/npa/workbench/cosmos/nano_video_augment_client.py |
| Nano diffusion serving, routing and measured deployment recipe | npa/src/npa/workbench/cosmos/nano_video_server.py, npa/src/npa/workbench/cosmos/nano_video_router.py, npa/deploy/cosmos3-nano-video/README.md |
| Generate workflow | workflows/testing/cosmos3-generate.yaml |
| Human CLI commands for real workflows | npa/src/npa/cli/cosmos/__init__.py |
| SDK compatibility exports | npa/src/npa/workbench/cosmos/__init__.py, npa/src/npa/sdk/workbench/cosmos.py |
| Fetch workflow | workflows/testing/cosmos-fetch.yaml |
| Text-to-image H100 smoke workflow | workflows/testing/cosmos3-text-to-image.yaml |
| Unit tests for access, fetch, inference YAML, and skill artifacts | npa/tests/workbench/test_cosmos3_access.py |
CLI tests for check and fetch | npa/tests/cli/test_cosmos3_cli.py |
The agent-skill artifacts live in this repository under:
skills/atomic/cosmos3-setup/SKILL.mdskills/atomic/cosmos3-codebase-nav/SKILL.mdskills/atomic/cosmos3-env-troubleshoot/SKILL.mdskills/workflows/cosmos3-inference/SKILL.mdskills/workflows/cosmos3-post-training/SKILL.md
What Not To Look For
There is no supported Cosmos skill-display subcommand. Cosmos3 skills are not platform commands, job templates, or SDK callables. They are SKILL.md files for coding agents to read.
The retained Cosmos3 workflow YAMLs are real executable specs:
workflows/testing/cosmos-fetch.yamlworkflows/testing/cosmos3-generate.yamlworkflows/testing/cosmos3-text-to-image.yaml
Do not restore cosmos3-setup.yaml, cosmos3-codebase-nav.yaml,
cosmos3-env-troubleshoot.yaml, cosmos3-post-training.yaml, or retired raw
SkyPilot task templates as skill launchers unless the product direction changes
to a real executable workflow.
Upstream Cosmos Framework Map
When a task needs upstream package internals, inspect a clone of
https://github.com/NVIDIA/cosmos-framework.git.
Common upstream paths:
| Need | Upstream path |
|---|---|
| Sampling args, setup args, override models | cosmos_framework/inference/args.py |
| Per-modality defaults | cosmos_framework/inference/defaults/<mode>/sample_args.json |
| Inference script | cosmos_framework/scripts/inference.py |
| Training script | cosmos_framework/scripts/train.py |
| Ray serving presets | cosmos_framework/inference/ray/configs/latency.yaml, throughput.yaml |
| SFT recipe TOMLs | examples/toml/sft_config/<recipe>.toml |
| SFT launch shells | examples/launch_sft_<recipe>.sh |
| SFT schema | cosmos_framework/configs/toml_config/sft_config.py |
| Setup docs | docs/setup.md |
| Inference docs | docs/inference.md |
| Training docs | docs/training.md |
Navigation Routine
-
Start with
rgin NPA:rg -n "NPA_COSMOS3|Cosmos3|cosmos3-text-to-image|guardrails" npa -
If the answer depends on upstream behavior, inspect the upstream file rather than guessing from NPA wrappers.
For the Nano diffusion deployment, inspect the installed vLLM-Omni video parser and
Cosmos3OmniDiffusersPipeline; the framework inference argument map does not establish what that image accepts. The deployment README links the pinned implementation and records the effective transfer contract. -
Keep NPA and upstream responsibilities separate. NPA owns CLI/SDK wrappers, SkyPilot workflows, image defaults, and tests. NVIDIA's repo owns Cosmos3 framework semantics, inference arguments, recipes, and training internals.
-
When adding docs or tests, reference SKILL.md artifacts as repository files, not as commands.
Signals
- GitHub stars
- 28
- Forks
- 15
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
cosmos3-codebase-nav- Source
- github.com/nebius/nebius-physical-ai