gauthierdmn/Nominal Code Review

AI-powered code review for pull requests using Claude

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
anthropic_api_keyAnthropic API key (required when provider is 'anthropic')no""
openai_api_keyOpenAI-compatible API key (required when provider is 'openai', 'deepseek', 'groq', 'together', or 'fireworks')no""
google_api_keyGoogle API key (required when provider is 'google')no""
github_tokenGitHub token for posting review comments (defaults to github.token)yes
providerLLM provider for the reviewer (anthropic, openai, google, deepseek, groq, together, fireworks). Also the default for the explorer.noanthropic
imageDocker image to use. The default all-in-one image works with any provider; provider-specific variants are available for smaller footprint.noghcr.io/gauthierdmn/nominal-code:latest
modelReviewer model (e.g. claude-sonnet-4-20250514, gpt-4.1). Empty uses the provider's default.no""
max_turnsMaximum agentic turns for the reviewer. Empty uses the bundled default (8), 0 means unlimited.no""
explorer_providerExplorer sub-agent provider. Empty inherits from `provider`.no""
explorer_modelExplorer sub-agent model. Empty inherits from `model`. Useful for pairing a strong reviewer with a cheaper explorer.no""
explorer_max_turnsMaximum turns for explorer sub-agents. Empty uses the bundled default (32), 0 means unlimited.no""
promptCustom review instructions appended to the default reviewer prompt.no""
coding_guidelinesInline coding guidelines content. Appended to the reviewer system prompt.no""
coding_guidelines_filePath to a coding guidelines file (relative to repo root). Appended to the reviewer system prompt. Wins over `coding_guidelines` if both are set.no""
reviewer_system_promptInline reviewer system prompt that fully REPLACES the bundled prompt.no""
reviewer_system_prompt_filePath to a file whose contents fully REPLACE the bundled reviewer system prompt.no""
explorer_system_promptInline explorer sub-agent system prompt that fully REPLACES the bundled prompt.no""
explorer_system_prompt_filePath to a file whose contents fully REPLACE the bundled explorer system prompt.no""
language_guidelines_dirDirectory containing per-language guideline files (e.g. python.md). Overrides the bundled language guidelines.no""
inline_suggestionsWhether to render findings as inline code suggestions. Defaults to true; set 'false' to disable.no""
ignore_existing_commentsWhen 'true', skip fetching prior PR comments so they don't bias the review (useful for re-runs).no""
dry_runWhen 'true', run the full review pipeline but skip posting comments to the PR.no""

no outputs