Agent-Skills.md

Agent Skills: Local Codex Review (pre-push)

Run the CI Codex PR review locally against this branch's unpushed work (committed + uncommitted) before pushing. Same policy, model and reasoning effort as the codex-pr-review GitHub action.

UncategorizedID: windmill-labs/windmill/local-review-codex

Repository

windmill-labs/windmill
windmill-labsLicense: NOASSERTION
18,2781,128

Install this agent skill to your local

pnpm dlx add-skill https://github.com/windmill-labs/windmill/tree/HEAD/.agents/skills/local-review-codex

Skill Files

Browse the full folder contents for local-review-codex.

Download Skill

Loading file tree…

.agents/skills/local-review-codex/SKILL.md

Skill Metadata

Name
local-review-codex
Description
Run the CI Codex PR review locally against this branch's unpushed work (committed + uncommitted) before pushing. Same policy, model and reasoning effort as the codex-pr-review GitHub action.

Local Codex Review (pre-push)

Runs the exact same review Codex performs in CI (.github/workflows/codex-pr-review.yml), but locally and scoped to work you have not pushed yet — so you catch what CI would flag before the PR exists. Use this before git push on a non-trivial change.

Correspondence with CI — identical:

  • Policy: REVIEW.md (severity triage, public-surface checklist, AGENTS.md compliance, test coverage).
  • Model: gpt-6.1-sol.
  • Reasoning effort: model_reasoning_effort="xhigh".
  • Output: markdown starting with ## Codex Review, findings tagged P0 / P1 / P2 with file:line.

Differences from CI — local-only:

  • Scope is the current branch vs main at the merge-base, including uncommitted changes (CI reviews a pushed PR diff).
  • Sandbox is read-only (CI uses danger-full-access on an ephemeral runner). Codex reads the diff and files but cannot modify your working tree.
  • Fresh context is inherent: codex exec is a separate cold process, so it does not anchor on the current chat session — the same reason local-review insists on a subagent.

Prerequisites

  • codex CLI >= 0.159.3 installed and authed via codex login or an OPENAI_API_KEY in the environment (which takes priority). Older CLIs reject the model with "requires a newer version of Codex"; run.sh checks the version up front. Upgrade with npm install --global @openai/codex@0.159.3 (may need sudo for a global install). This matches the pin in .github/workflows/codex-pr-review.yml — the CLI version is the same on both sides.
  • git fetch the base ref if it's stale, so the merge-base is accurate.

Run

bash .agents/skills/local-review-codex/run.sh          # review vs main (default)
bash .agents/skills/local-review-codex/run.sh <base>   # review vs a different base ref

Invoke with bash (or run the executable directly) — the script needs Bash for set -o pipefail; sh is Dash on Debian/Ubuntu and would fail. If main isn't a local branch (e.g. a fresh single-branch checkout), the runner falls back to origin/main automatically.

The script computes BASE_SHA = git merge-base HEAD <base>, feeds Codex REVIEW.md plus a diff context pointing at git diff <BASE_SHA> (which folds in uncommitted edits), and prints the review. It writes only temp files — nothing lands in the working tree.

Relaying the result

Print the Codex output verbatim. Do not re-summarize or filter it — the value of a cold Codex pass is surfacing what the current session would rationalize away. Then decide with the user whether to address findings before pushing.

For a Claude-native review instead, use local-review (branch-diff-reviewer subagent). This skill is the Codex counterpart; run both for independent perspectives.