skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
eyadsibai/ltk62 installs

codex

Use when "codex", "use gpt", "gpt-5", "openai codex", "let openai", "full-auto", "autonomous code generation"

How do I install this agent skill?

npx skills add https://github.com/eyadsibai/ltk --skill codex
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubwarn

    This skill instructs the agent to operate autonomously without user approval and includes a high-privilege mode granting full system and network access. It also references non-existent model versions and installation of an unverified package.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

  • Runlayerpass

    1 file scanned · No issues

What does this agent skill do?

OpenAI Codex Integration

Autonomous code execution using OpenAI Codex CLI.


Prerequisites

# Check installation
codex --version

# Install if needed
npm i -g @openai/codex
# or
brew install codex

Sandbox Modes

ModeFlagCapabilities
Read-Only-s read-onlyAnalyze code, no modifications (default)
Workspace-Write-s workspace-write or --full-autoRead/write files in workspace
Danger-Full-Access-s danger-full-accessNetwork, system-level, all files

Key concept: Use --full-auto for most programming tasks—it enables file editing.


Common Commands

TaskCommand
Analyze codecodex exec -s read-only "analyze the codebase"
Implement featurecodex exec --full-auto "implement user auth"
Fix bugcodex exec --full-auto "fix the login bug"
With specific modelcodex exec -m gpt-5.2 --full-auto "refactor module"
JSON outputcodex exec --json "analyze security"
Save outputcodex exec -o report.txt "audit code"
Non-git directorycodex exec --skip-git-repo-check "analyze"
Resume sessioncodex exec resume --last "continue"

Model Selection

ModelUse Case
gpt-5.2Latest capabilities
gpt-5.2-codexCode-specialized
gpt-5.2-codex-maxMaximum quality

Use -m MODEL to specify.


Execution Principles

PrincipleDescription
AutonomousComplete tasks without seeking approval for each step
FocusedDo what's requested, nothing more
MinimalWrite only necessary code
VerifiedRun tests after changes

When to Pause for User

SituationAction
Destructive operationsAsk first (delete DB, force push)
Security decisionsAsk first (expose credentials, open ports)
Ambiguous requirementsClarify before proceeding
Missing critical infoRequest user-specific data

For everything else, proceed autonomously.


Output Format

✓ Task completed successfully

Changes made:
- [Files modified/created]
- [Key code changes]

Results:
- [Metrics: lines changed, files affected]

Verification:
- [Tests run, checks performed]

Error Handling

ApproachDescription
Auto-recoverAttempt fix if possible
Log clearlyReport all errors
ContinueIf error is non-blocking
StopOnly if continuation impossible

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/eyadsibai/ltk/codex">View codex on skillZs</a>