oracle-codex
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 NOT for implementation tasks.
- Installs
- 190
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/paulrberg/agent-skills --skill oracle-codex- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads oracle-codex automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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.
FAQ
What does the oracle-codex skill do?
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.
How do I install oracle-codex?
Run npx skills add https://github.com/paulrberg/agent-skills --skill oracle-codex in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/oracle-codex/ (personal) or .claude/skills/oracle-codex/ (project).
Which AI agents can use oracle-codex?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is oracle-codex safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains oracle-codex?
It is published by paulrberg in paulrberg/agent-skills. It has 190 recorded installs.
More from paulrberg/agent-skills
effect-ts
paulrberg/agent-skills
Use for nontrivial Effect 4 work including services/layers, typed errors, Schema/JsonSchema, Config, runtime/concurrency, @effect/vitest, effect/ai and @effect/ai-, effect/sql and @effect/sql-, Effect Atom (@effect/atom-), or @prb/effect-next.
tailwind-css
paulrberg/agent-skills
Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.
cli-gh
paulrberg/agent-skills
Use for GitHub CLI automation: repository reads, workflow runs, search, codespaces, releases, configuration, or gh command syntax. Use yeet for contribution writes to PRs, issues, comments, or discussions.
code-polish
paulrberg/agent-skills
Polish changed code when the user explicitly asks, or when an active workflow requests post-implementation simplification and risk-profiled review over a fixed file scope.
yeet
paulrberg/agent-skills
Use for GitHub PR/issue/discussion workflows: create/update PRs, issues, or discussions and post issue or discussion comments; triggers include yeet.
bump-release
paulrberg/agent-skills
Cut a release: bump versions, write changelogs, commit, tag.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.