SKILLEMALL.ai
GitHub ↗ RU Sign in

CB codex

OpenAI Codex CLI wrapper — three modes. (gstack)

The skillemall take

A CLI wrapper for Codex with three operating modes. The skill promises OpenAI Codex integration, but code quality scores just 55 points—half the acceptable threshold. No critical vulnerabilities found, though two medium-level issues exist. Five files total, no scripts, suggesting minimal implementation.

Process score reaches 77, safety 94, but that doesn't compensate for the weak quality rating. Since Codex has been deprecated by OpenAI for years, this feels like legacy tooling. The platform list is extensive, yet the code itself needs substantial rework. Install only if Codex is genuinely unavoidable and no alternatives exist.

garrytan/gstack Agent Skills author: garrytan MIT 5 files body ≈ 14 885 tokens Open the sourcegithub.com↗ analyzed 6 d ago

OpenAI Codex CLI wrapper — three modes.

As a process B 77/100 · Nearly there — weak spots: inputs and preconditions, execution cost

IntegrationSoftware developmentData and analyticsAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
78/100
safety, quality, tests
Safety 60%
94
Quality 40%
55
Run on models
none yet
Process rating
B
77/100
Nearly there
Inputs and preconditions w 11
30
Execution cost w 6
40
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

✓ No critical or high findings

Medium and low: 2
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Glob Grep AskUserQuestion
  • low Risky intent intent-offensive-security sections/challenge-mode.md:20
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    Review the changes on this branch against the base branch. Run `git diff origin/<base>` to see the diff. Focus specifically on SECURITY. Your job is to find every way an attacker could exploit this co
    detector

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 14885 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "preamble-tier"
  • note frontmatter-key unknown frontmatter key "triggers"
  • note edit-residue the text marks something as outdated (lines 791): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 77/100

  • 30Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 14885 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 119 steps
  • 100Failures and branches. 19 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 36 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (23 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 48: 120–800 characters recommended
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +4Structure: 45 headings
  • +3Step-by-step instructions: 119 items
  • +3Output format is stated explicitly
  • +4Has examples (15 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.