agentleFS
Sign inStart free
sd0xdevsd0xdev/sd0x-dev-flow/skills/codex-cli-review/SKILL.md

codex-cli-review

Skill192 starsChanged 36 days agoMITView on GitHub

Code review via Codex CLI with full disk access. Use when: deep review needing full codebase read, uncommitted change review. Not for: quick diff review (use codex-code-review), doc review (use doc-review). Output: severity-grouped findings + merge gate.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't need MCP's context persistence feature

    line 17
  2. Very specific:

    Only want to see diff without waiting for Codex exploration (use /codex-review-fast)

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Codex CLI Review Skill

Trigger

  • Keywords: codex cli review, cli review, script review

When to Use

  • Need Codex to independently explore the entire project (full disk read)
  • Don't need MCP's context persistence feature
  • Want to use Codex CLI's native review format

When NOT to Use

  • Need iterative review (use /codex-review-fast --continue)
  • Need to follow up with Codex (use MCP version)
  • Only want to see diff without waiting for Codex exploration (use /codex-review-fast)

Difference from MCP Version

FeatureCLI Version (this skill)MCP Version
Independent exploreFull disk readNeeds explicit instruction
Context persistenceNonethreadId
Iterative reviewEach run independent--continue
FormatCodex native formatCustom prompt format
Execution methodScript invocationMCP tool invocation

Workflow

┌─────────────────────────────────────────────────────────────────┐
│ Step 1: Check Changes                                           │
├─────────────────────────────────────────────────────────────────┤
│ git status --porcelain                                          │
│ No changes -> Early exit                                        │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│ Step 2: Execute Codex CLI                                       │
├─────────────────────────────────────────────────────────────────┤
│ codex review --uncommitted                                      │
│   -c 'sandbox_permissions=["disk-full-read-access"]'            │
│                                                                 │
│ Codex will independently:                                       │
│ - Read changed files                                            │
│ - Explore related dependencies                                  │
│ - Check existing tests                                          │
│ - Understand project structure                                  │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│ Step 3: Output Review Results                                   │
├─────────────────────────────────────────────────────────────────┤
│ Codex native format:                                            │
│ - Summary                                                       │
│ - Issues (Critical/Major/Minor/Suggestion)                      │
│ - Recommendations                                               │
└─────────────────────────────────────────────────────────────────┘

Script

bash skills/codex-cli-review/scripts/review.sh [options]

Options

ParameterDescription
--base <branch>Compare with specified branch
--title "<text>"Set review title
--prompt "<text>"Custom review instructions

I/O Contract

Input:

  • Git working directory with changes

Output:

  • Codex review report (stdout)
  • Exit code: 0 = success, non-0 = failure

Output

## Codex CLI Review Report
### Findings
#### P0/P1/P2
- [file:line] Issue → Fix recommendation
### Merge Gate
✅ Ready / ⛔ Blocked

Verification

  • Script executes without errors
  • Codex explored the project (file references visible in output)
  • Output includes issue classification

Examples

# Review uncommitted changes
/codex-cli-review

# Compare with main branch
/codex-cli-review --base main

# With title
/codex-cli-review --title "Feature: User Auth"

# Custom review instructions
/codex-cli-review --prompt "Focus on security and performance"

Related

Command/SkillDifference
/codex-review-fastMCP version, supports iterative review
/codex-reviewMCP version, includes lint + build
/codex-review-branchMCP version, reviews entire branch

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free