codex — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited codex (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Delegate specific complex development tasks to OpenAI's Codex CLI when the user explicitly requests Codex, especially for tasks requiring advanced code generation capabilities.
This skill provides a safe and consistent workflow to:
codex exec or codex review in non-interactive mode for deterministic outputsThis skill complements existing capabilities by delegating complex programming tasks to Codex when requested, leveraging OpenAI's GPT-5.3-codex models for advanced code generation and analysis.
Use this skill when:
Typical trigger phrases:
Verify tool availability before delegation:
codex --versionIf unavailable, inform the user and stop execution until Codex CLI is installed.
references/cli-command-reference.mdcodex exec) for reproducible runs.danger-full-access sandbox or never approval policy without explicit user consent.codex review over codex exec.Before running Codex:
If scope is ambiguous, ask for clarification first.
Choose the appropriate model based on task complexity:
| Model | Best For | Characteristics |
|---|---|---|
| gpt-5.3-codex | Complex code generation, architectural design, advanced refactoring | Highest quality, slower, most expensive |
| o3 | Complex reasoning, distributed systems, algorithm design | Deep reasoning, analysis-heavy tasks |
| o4-mini | Quick iterations, boilerplate generation, unit tests | Fast, cost-effective, good for simple tasks |
Selection tips:
o4-mini for quick iterations and prototypinggpt-5.3-codex for production-quality code and complex refactoringo3 for tasks requiring deep reasoning or system designgpt-5.3-codex if uncertain (highest quality)Build a precise English prompt from the user request.
Prompt quality checklist:
Example transformation:
#### For Code Generation/Development Tasks
Preferred baseline command:
codex exec "<english-prompt>"Supported options:
-m, --model <model-id> for model selection (e.g., gpt-5.3-codex, o4-mini, o3)-a, --ask-for-approval <policy> for approval policy:untrusted: Only run trusted commands without approvalon-request: Model decides when to ask (recommended for development)never: Never ask for approval (use with caution)-s, --sandbox <mode> for sandbox policy:read-only: No writes, no network (safest for analysis)workspace-write: Allow writes in workspace, no network (default for development)danger-full-access: Disable sandbox (⚠️ extremely dangerous)-C, --cd <DIR> to set working directory-i, --image <FILE> for multimodal input (repeatable)--search to enable live web search--full-auto as convenience alias for -a on-request -s workspace-writeSafety guidance:
read-only sandbox for analysis-only tasksworkspace-write sandbox for code generation/refactoringon-request approval for development tasksnever approval only with explicit user consent for automated tasksdanger-full-access without explicit user approval and external sandboxingcodex resume --last to continue from previous sessions#### For Code Review Tasks
Use the dedicated review command:
codex review "<english-prompt>"The review command includes optimizations for code analysis and supports the same flags as codex exec.
Run the selected command via Bash and capture stdout/stderr.
Examples:
# Default non-interactive delegation
codex exec "Refactor this authentication module to use JWT with proper error handling"
# Explicit model and safe settings
codex exec "Review this codebase for security vulnerabilities. Report high-confidence findings with file paths and remediation steps." -m gpt-5.3-codex -a on-request -s read-only
# Code review with workspace write
codex review "Analyze this pull request for potential bugs, performance issues, and code quality concerns. Provide specific line references." -a on-request -s workspace-write
# Complex refactoring with working directory
codex exec -C ./src "Refactor these service classes to use dependency injection. Maintain all existing interfaces." -a on-request -s workspace-write
# With web search for latest best practices
codex exec --search "Implement OAuth2 authorization code flow using the latest security best practices and modern libraries"
# Multimodal analysis
codex exec -i screenshot.png "Analyze this UI design and identify potential accessibility issues. Suggest specific improvements with code examples."
# Full automation (use with caution)
codex exec --full-auto "Generate unit tests for all service methods with >80% coverage"When reporting Codex output:
Use this structure when returning delegated results:
## Codex Delegation Result
### Task
[delegated task summary]
### Command
`codex exec ...`
### Key Findings
- Finding 1
- Finding 2
### Generated Code/Changes
[summary of code generated or changes proposed]
### Suggested Next Actions
1. Action 1
2. Action 2
### Notes
- Output language from Codex: English
- Sandbox mode: [mode used]
- Requires user approval before applying code changescodex exec "Refactor this OrderService class to follow SOLID principles. Current issues: 1) Single Responsibility violated (handles validation, processing, notification), 2) Open/Closed violated (hard-coded payment providers), 3) Dependency Inversion violated (concrete dependencies). Provide: 1) Proposed class structure, 2) Step-by-step migration plan, 3) Refactored code maintaining backward compatibility." -m gpt-5.3-codex -a on-request -s workspace-writecodex exec "Perform a comprehensive security analysis of this authentication module. Focus on: SQL injection, XSS, CSRF, authentication bypass, session management, and password handling. For each vulnerability found, provide: severity level, CWE identifier, exploit scenario, and concrete remediation with code examples." -a on-request -s read-onlycodex exec --search "Design and implement a RESTful API for user management following REST best practices. Include: endpoint design, request/response schemas with validation, error handling, authentication middleware, pagination, filtering, and HATEOAS links. Use the latest industry standards and provide OpenAPI 3.0 specification."codex exec "Analyze this database query module for performance bottlenecks. Identify: N+1 queries, missing indexes, inefficient joins, and caching opportunities. Provide: 1) Performance analysis with metrics, 2) Specific optimization recommendations, 3) Refactored code with query optimizations, 4) Migration script for database changes."codex review "Review this pull request for: 1) Correctness and logic errors, 2) Performance issues, 3) Security vulnerabilities, 4) Code quality and maintainability, 5) Test coverage gaps, 6) Documentation completeness. Provide specific line references and actionable feedback." -a on-request -s read-onlycodex exec -i design-mockup.png -i current-implementation.png "Compare the design mockup with the current implementation. Identify: layout differences, missing components, styling inconsistencies, and accessibility issues. Provide: 1) Gap analysis, 2) Specific CSS/HTML changes needed, 3) Priority ranking of fixes."read-only for analysis, workspace-write for developmentgpt-5.3-codex for complex tasks, o4-mini for faster iterationscodex review for review tasks over codex exec--search for tasks requiring latest best practices or library versions-i for UI/UX analysis, diagram understanding, or visual debuggingdanger-full-access mode removes ALL security restrictions and should NEVER be used without external sandboxing (e.g., containers, VMs)never policy can execute destructive commands without confirmationdanger-full-access) block network access by default~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.