Scan reports · CherryHQ/cherry-studio
code-mate-codex: scan report
Runs Codex CLI non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Codex or obtain a second coding-agent result. An automated scan of this public skill from CherryHQ/cherry-studio: security, token cost, spec and clarity, with every finding and its fix.
Verdict
CherryHQ/cherry-studio/resources/code-cli-skills/code-mate-codex at dac9b72
Spec 25 · Efficiency 19 · Clarity 21 · Security 17 (each out of 25)
Always loaded 48 tokens · on trigger 308 · on demand 0
sec/destructivewarn · SKILL.md:24Risky command; make sure the skill asks before running it.eff/body-lightwarn · SKILL.mdOnly ~308 tokens of guidance. Add the specifics an agent can't guess: thresholds, checklists, worked examples.clarity/outputwarn · SKILL.mdDoesn't say what the result should look like. Add an Output section.
Source
| Fact | Value |
|---|---|
| Repository | CherryHQ/cherry-studio |
| Skill folder | resources/code-cli-skills/code-mate-codex |
| Stars | 52,684 |
| License | AGPL-3.0 |
| Commit scanned | dac9b72 |
| Scanned | 2026-10-16 |
| Files | 1 |
ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.
Badge for the README
If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.
[](https://proskills.dev/reports/cherryhq-code-mate-codex)
Scanned alternatives on ProSkills
Skills in the ProSkills catalog that cover similar ground. Every one passes the same scanner before it ships.
- Grill MeFreeScan 100/1003 rules · Grill MeA relentless review of your plan.Loads when the user shares a plan or asks to build something non-trivial.
- Still to Loop$12Scan 100/1003 rules · AI ModelsA still becomes a seamless 4-second loop.Loads when the user wants to animate a still image.
- Grill Me Pro$9Scan 100/1004 rules · Grill MeEvery question answered for you. Ends in tickets.Loads when the user shares a plan or starts a non-trivial build.
More from CherryHQ/cherry-studio
| Skill | Scan | Grade |
|---|---|---|
| cherry-assistant-guide | 72/100 | C |
| cherry-browser | 91/100 | A |
| cherry-computer | 91/100 | A |
| cherry-electron-dev | 95/100 | A |
| cherry-regression-test | 92/100 | A |
| cherry-skill-marketplace | 85/100 | B |
| cherry-studio-feedback | 90/100 | A |
| cherry-tool-guide | 63/100 | D |
| claude-automation-recommender | 94/100 | A |
| code-mate-antigravity | 84/100 | B |
| code-mate-claude-code | 90/100 | A |
| code-mate-deepseek-harness | 90/100 | A |
Questions
- Is code-mate-codex safe to install?
- No critical findings, some security notes. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
- How was this score calculated?
- Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
- Is this report current?
- It was made from commit dac9b72 on 2026-10-16. If the skill has changed since, paste the new version into the scanner for a fresh score.
- I wrote this skill. Can I fix the score or have the page removed?
- Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.
Keep reading
Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.
Want a skill that already passes? Start with a free one.