wezell/Codex Code Review & Actor

Run Codex to review a PR and post review comments

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
modeOperation mode: review | actnoreview
openai_api_keyOpenAI API key for the selected model providerno
openrouter_api_keyOpenRouter API key used for all routed model callsno
config_pathPath (relative to the consuming repo's checkout) to the in-repo OpenRouter model config file. Edit that file to swap review or act model — no code change required. Defaults to .openrouter-review.yml at the repo root.no.openrouter-review.yml
modelModel to use (e.g., gpt-5, gpt-4.1-mini)nogpt-5.4
reasoning_effortReasoning effort: minimal | low | medium | highnomedium
web_search_modeWeb search mode: disabled | cached | livenolive
debug_levelDebug verbosity: 0 (off), 1 (basic), 2 (trace)no1
dry_runIf '1', print payloads but do not post commentsno0
stream_agent_messagesIf '1', stream model output to logsno1
act_instructionsAdditional instructions for act mode (autonomous editing)no""
allowed_commenter_associationsComma-separated GitHub comment author_association values allowed to trigger act modenoMEMBER,OWNER,COLLABORATOR
additional_promptExtra reviewer instructions appended to the review prompt (verbatim)no""
extra_pip_argsAdditional pip arguments (e.g., --index-url)no""

no outputs