CODEX CLI PLUGIN

Make your next Codex session
better than your last.

Find the bottleneck in your project history. Copy a tailored prompt or workflow. Run Radar again to see whether the measured behavior improved.

✓Every score traces to evidence ✓Open, public rubric ✓Runs in your own Codex
Codex Radar
illustrative preview
LONG-RUNNING
Clear requests. More changes now end with passing verification.
B
68 / 100
Comm
66B
Eng
68B
Out
71A
Strongest: Lock-On Bottleneck: Proof Check
Why Codex Radar

Turn a frustrating session into a useful next step

It reads the sessions you've already run with Codex and turns them into a diagnosis you recognize and can act on: where you're strong, where you hold yourself back, and exactly what to do next.

01 · Find the friction

Know what deserves your attention

A focused diagnosis surfaces your strongest habit and costliest bottleneck. Follow evidence links to the messages, sessions and incidents behind it.

02 · Take one action

Leave with something you can use

Copy a project-specific prompt, adopt a workflow, or use a setup-file draft. Your first action is highlighted; the rest stay one click away.

03 · Check your progress

See what changed next time

Measurable suggestions become targets in your next comparable report. Check verification coverage and other observed behaviors, with formula and interpretation changes shown separately.

9 Dimensions × 3 Categories

A clearer picture of your workflow

Explore nine signals of collaboration, with visible baselines and evidence behind model adjustments.

Communication
3 DIMS
How clearly you direct Codex through text.
Lock-On 瞄准力
Goal, expected behavior, file paths, constraints in your directives.
Scene Setting 铺场力
How much useful context your opening messages carry.
Steering 校准力
Quality of mid-session course-correction and verification asks.
Engineering
3 DIMS
How well you drive the Codex platform.
Toolcraft 工具调度
Shell, patch, plan, MCP, search, subagents + command success rate.
Architecture 工程脚手架
Durable setup — AGENTS.md, repo scaffolding, tests, manifests.
Tempo 推进节奏
Steady progress without aborts, compactions, or tool churn.
Outcome
3 DIMS
What actually gets done.
Efficiency 产出效率
Useful output per human message and per tool call.
Proof Check 验证意识
Verification after edits, passing checks, and recovery from failures.
Completion 闭环完成
Turns finish cleanly instead of trailing off mid-task.
Your first report

One project. One useful next step.

1

Choose your project

Ask Radar to review the current project. Choose all history or a recent period, and select strict mode if you want excerpts omitted.

2

Try your first action

Open the diagnosis, inspect the cited evidence, and copy the highlighted prompt or workflow into your next session.

3

Return after new work

Use the same analysis window to check measurable targets and see which behaviors changed. Keep the action that helps.

Fairness

A 3-message fix isn't a 50-session build

Every project is auto-classified into one of five profiles, each with its own category weights — and codex exec pipelines are judged as automation, not as conversation.

AOne-shot · few messages, light editing
BFeature build · real implementation work
CLong-running · many sessions or compactions
DLearning · conversation-heavy, few edits
EAutomation · codex exec batch pipelines
Honest N/A, not a faked 50. When a signal genuinely can't be evaluated — like Architecture when the project directory no longer exists on this machine — the dimension is marked N/A and dropped from the average.
Your next 30 days

Focus on the work you want to improve

Ask for all history, the last 30 days, or a date range. Radar selects sessions by their start date. Keep the same window policy for meaningful follow-up comparisons.

Open a complete synthetic report
Privacy

Local artifacts, controlled disclosure

Bundled scripts make no network calls and write private local artifacts. Standard mode redacts common credentials; strict mode omits message/command snippets, thread titles, web-search queries, and episode opening/closing text. Qualitative interpretation runs in your active Codex session and follows its configured data handling.

No plugin network calls
No separate API key
Credential redaction
Strict minimized-evidence mode
Private file permissions
Read-only sessions
Get started

Two commands, then ask

Requires the Codex CLI and Node.js 20+. No build step, no server.

codex
$ codex plugin marketplace add lemomo-ai/codex-radar
$ codex plugin add codex-radar@codex-radar-marketplace

# start a new thread, then ask:
› Run Codex Radar on this project

Or develop locally: git clone the repo, then codex plugin marketplace add .

See exactly how you and Codex work together

Pick one project. Find one bottleneck. Try one better habit in your next session.

Get Codex Radar