Cog Review
Testing & Qualitycog-reviewCog Review is an Agent Skill for testing & quality published in the replicate/cog repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Cog architecture and cross-cutting review guidelines
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/replicate/cog/blob/HEAD/.opencode/skills/cog-review/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/cog-review, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Cog architecture review guidelines
Cog packages ML models into production-ready containers. Use this skill for changes that cross language boundaries or touch core architecture.
Component overview
- CLI (Go):
cmd/cog/andpkg/-- builds, runs, and deploys models - Python SDK:
python/cog/-- predictor interface, types, HTTP/queue server - Coglet (Rust):
crates/-- prediction server inside containers (HTTP, worker management, IPC)
Key design patterns
Wheel resolution: The CLI discovers SDK and coglet wheels from dist/ at
Docker build time. Wheels are NOT embedded in the binary. Changes to build
artifacts need to account for this.
Dockerfile generation: pkg/dockerfile/ generates Dockerfiles from cog.yaml
config. Template injection and escaping matter here.
Config parsing: pkg/config/config.go parses cog.yaml. Schema is at
pkg/config/data/config_schema_v1.0.json. Changes must keep schema and Go
code in sync.
Two-process coglet: Parent process (HTTP server + orchestrator) and child worker process (Python predictor execution) communicate via IPC. Changes to the IPC protocol affect both Rust and Python code.
Compatibility matrix: CUDA/PyTorch/TensorFlow compatibility is managed in
tools/compatgen/. Framework version changes have wide blast radius.
Cross-cutting concerns
- VERSION.txt is the single source of truth for versioning.
Cargo.tomlmust match. - Changes to
python/cog/base_predictor.pyaffect all downstream model authors. - Changes to
docs/require runningmise run docs:llmto regeneratedocs/llms.txt. - CLI reference docs are auto-generated -- changes to
cmd/orpkg/cli/requiremise run docs:cli. - Integration tests in
integration-tests/use Go's testscript and need a built cog binary.
What to watch for
- Breaking changes to the predictor interface or cog.yaml schema
- Docker build changes that affect layer caching or build time
- IPC protocol changes without updating both Rust and Python sides
- Version bumps that miss one of the places VERSION.txt needs to match
- New ML framework versions without compatibility testing