paulrberg/oracle-codex
shelved/oracle-codex/SKILL.md
This skill should be used when the user asks to consult Codex/GPT for planning or code review, or wants a second opinion on code. Trigger phrases include "ask Codex", "consult Codex", "second opinion on code", "consult the oracle". NOT for implementation tasks.
$ install --global
skillsauthnpx skillsauth add paulrberg/agent-skills oracle-codexInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 6:32 AM35.5s5 files scanned
SKILL.md
- argument-hint:
- <query> [--reasoning <level>]
- disable-model-invocation:
- true
- name:
- oracle-codex
- user-invocable:
- true
- description:
- This skill should be used when the user asks to consult Codex/GPT for planning or code review, or wants a second opinion on code. Trigger phrases include "ask Codex", "consult Codex", "second opinion on code", "consult the oracle". NOT for implementation tasks.
Codex Oracle
Use OpenAI Codex CLI as a read-only oracle — planning, review, and analysis only. Codex provides its perspective; you synthesize and present results to the user.
Sandbox is always read-only. Codex must never implement changes.
Arguments
Parse $ARGUMENTS for:
- query — the main question or task (everything not a flag). Required — if empty, tell the user to provide a query and stop.
--reasoning <level>— override reasoning effort (low,medium,high,xhigh). Optional; default isxhigh.
Prerequisites
Run the check script before any Codex invocation:
scripts/check-codex.sh
If it exits non-zero, display the error and stop. Use the wrapper for all codex exec calls:
scripts/run-codex-exec.sh
Configuration
| Setting | Default | Override |
| --------- | ----------- | ------------------------------------------------ |
| Model | gpt-5.5 | Allowlist only (see references/codex-flags.md) |
| Reasoning | xhigh | --reasoning <level> or user prose |
| Sandbox | read-only | Not overridable |
Reasoning Effort
| Complexity | Effort | Timeout | Criteria |
| ---------- | -------- | -------- | ------------------------------------ |
| Simple | low | 300000ms | <3 files, quick question |
| Moderate | medium | 300000ms | 3–10 files, focused analysis |
| Complex | high | 600000ms | Multi-module, architectural thinking |
| Maximum | xhigh | 600000ms | Full codebase, critical decisions |
For xhigh tasks that may exceed 10 minutes, use run_in_background: true on the Bash tool and set CODEX_OUTPUT so you can read the output later.
See references/codex-flags.md for full flag documentation.
Workflow
1. Parse and Validate
- Parse
$ARGUMENTSfor query and--reasoning - Run
scripts/check-codex.sh— abort on failure - Use
xhighreasoning effort unless--reasoningoverrides it
2. Construct Prompt
Build a focused prompt from the user's query and any relevant context (diffs, file contents, prior conversation). Keep it direct — state what you want Codex to analyze and what kind of output you need. Do not implement; request analysis and recommendations only.
3. Execute
Invoke via the wrapper with HEREDOC. Set the Bash tool timeout per the reasoning effort table above.
EFFORT="<effort>" \
CODEX_OUTPUT="/tmp/codex-${RANDOM}${RANDOM}.txt" \
scripts/run-codex-exec.sh <<'EOF'
[constructed prompt]
EOF
For xhigh, consider run_in_background: true on the Bash tool call, then read CODEX_OUTPUT when done.
4. Present Results
Read the output file and present with attribution:
## Codex Analysis
[Codex output — summarize if >200 lines]
---
Model: gpt-5.5 | Reasoning: [effort level]
Synthesize key insights and actionable items for the user.
Related Skills
paulrberg/update-skills
testing
VerifiedTrustedCommunity
Use ONLY to check or update the project-scoped agent skills installed under .agents/skills so they match the current state of the repo. Do not trigger for creating, finding, or installing skills, or for README/AGENTS.md updates.
63SKILL.mdUpdated Jun 13, 2026
paulrberg/spreadsheets
testing
VerifiedTrustedCommunity
Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: inspect, clean, transform, dedupe, merge, validate, convert, recalc formulas, or create/fix spreadsheets. Do not trigger when tabular data is incidental.
63SKILL.mdUpdated Jun 11, 2026
paulrberg/diagram-monochrome
databases
VerifiedTrustedCommunity
This skill should be used when the user asks to create a monochrome technical diagram, schematic, or systems/architecture diagram in black-and-white line-art style. Trigger phrases include "create a diagram", "monochrome diagram", "systems diagram", "draw a schematic".
63SKILL.mdUpdated Jun 11, 2026
paulrberg/todo-archive
testing
VerifiedTrustedCommunity
Use only when explicitly asked to archive/prune/compact/roll over checked tasks from TODO.md into `.ai/todos/TODO_UNTIL_YYYY_MM_DD.md`, leaving unchecked tasks.
63SKILL.mdUpdated Jun 10, 2026