菜单
Launch OpenAI Codex/GPT as an independent agent for code review, verification, and precision analysis. Uses the codex CLI with full file system access, or the API for pure reasoning tasks.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Same-session deep-verification methodology. Chain-of-Verification with Saboteur / New Hire / Security Auditor personas. For gate-level cross-model verification that writes the prosecution doc, use /verify — which uses this skill's methodology as its payload.
End-to-end orchestrator for building a trading executor from data collection through live deployment. Use when the user asks to build an executor, create a new strategy, implement a trading system, or says 'build me an executor for X'. Also use when resuming an in-progress executor build — the skill reads the executor directory to determine current stage and picks up where it left off. Covers the full lifecycle: data collection, scoring, strategy promotion, and live deployment. Cross-model `/verify` is the single gate at PROMOTE and LIVE. This skill should be used for ANY new executor work in this repo, even partial tasks like 'add scoring to my executor' or 'wire up live mode'.
Launch Anthropic Claude as an independent agent for code review, verification, and reasoning. Uses the claude CLI with full file system access, or the API for pure reasoning tasks. Primarily for teams whose primary agent is Codex or Gemini and want a Claude read on the work.
Set up or repair codecontext adoption in a project. Use this whenever the user wants to add @context annotations to a repo, install the codecontext toolchain, update AGENTS.md guidance, improve agent workflows around decision capture, or audit whether an existing codecontext setup is coherent. Prefer this skill over vague "document the tool" work: it is specifically for making a repo actually usable with codecontext.
Create and maintain executor strategy overview presentations. Use when scaffolding a new executor, updating strategy documentation, or when the QA check requires a strategy-overview.marp.md file. Generates Marp slide decks with codePaths tracking for CI enforcement.
Launch Gemini as an independent agent for codebase analysis, planning, and large-context synthesis. Uses the gemini CLI with full file system access.
| description | Launch OpenAI Codex/GPT as an independent agent for code review, verification, and precision analysis. Uses the codex CLI with full file system access, or the API for pure reasoning tasks. |
| metadata | {"github-path":"skills/codex-oracle","github-ref":"refs/tags/v1.1.0","github-repo":"https://github.com/recallnet/recall-skills","github-tree-sha":"7dbb6d452598ed35afcdb55affda136bd1f32f0b"} |
| name | codex-oracle |
Launch OpenAI's models as an independent agent that can read the codebase, review diffs, and produce precise analysis. The codex CLI provides purpose-built commands for code review and general agentic tasks.
Key property: Codex runs as a separate process with zero knowledge of the current Claude conversation. It reads the codebase cold — different training data, different failure modes, different blind spots from both Claude and Gemini.
codex CLI installed: npm install -g @openai/codex, then codex login once.OPENAI_API_KEY in the
environment (e.g. exported from ~/.secrets/api-keys.sh or your shell rc).If the CLI is missing, the skill fails loudly — don't try to fake a review with another tool. Surface the prerequisite and stop.
gemini-oracle and claude-oracle for a three-way cross-check.codex review command reviews diffs with high precision.Minimal prompt. Codex explores the codebase or diff and forms its own conclusions. Maximum independence.
codex review --uncommitted 2>/dev/null
or
codex exec "Review this codebase for bugs, missed edge cases, and security issues. Be specific." -m gpt-5.4 2>/dev/null
Use when: You want to catch what Claude missed. The less framing you provide, the more independent the review.
Provide specific context and a focused question.
codex exec "Analyze the error handling in server/apiMiddleware.ts. Are there request paths that could hang without a timeout?" -m gpt-5.4 2>/dev/null
Use when: You have a specific concern and want a different model family's take.
The codex review command is purpose-built for reviewing code changes.
# Review all uncommitted changes (staged + unstaged + untracked)
codex review --uncommitted 2>/dev/null
# Review changes against a base branch
codex review --base main 2>/dev/null
# Review a specific commit
codex review --commit abc123 2>/dev/null
# Review with custom instructions
codex review --uncommitted "Focus on security vulnerabilities and race conditions" 2>/dev/null
# Review with a specific model
codex review --uncommitted -m gpt-5.4 2>/dev/null
# Codex explores the codebase and answers the question
codex exec "YOUR TASK" -m gpt-5.4 2>/dev/null
# Read from stdin
echo "YOUR TASK" | codex exec - -m gpt-5.4 2>/dev/null
For pure reasoning tasks where Codex doesn't need to read the codebase, use the API script directly:
# From anywhere — resolves relative to the skill install location.
# Project install: .claude/skills/codex-oracle/scripts/call-openai.sh
# Global install: ~/.claude/skills/codex-oracle/scripts/call-openai.sh
<skill-dir>/scripts/call-openai.sh "YOUR PROMPT" [model] [reasoning_effort]
Parameters:
prompt (required): The taskmodel (optional): Default gpt-5.4. See model guide below.reasoning_effort (optional): high (default). Options: xhigh, high, medium, low, nonecodex exec / codex review)| Model | Best For | Speed |
|---|---|---|
gpt-5.4 | Most capable, coding + reasoning + computer use (DEFAULT) | Medium |
gpt-5.4-pro | Premium tier, highest capability | Slow |
o3 | Deep reasoning, complex planning | Slow |
| Model | Best For | Speed | Cost |
|---|---|---|---|
gpt-5.4 | Most capable frontier model (DEFAULT) | Medium | High |
gpt-5.4-pro | Premium tier, highest capability | Slow | High |
gpt-5.3-codex | Specialized agentic coding | Medium | High |
gpt-5.3-codex-spark | Fast real-time coding (1000+ tok/s) | Fast | Medium |
o3 | Deep reasoning | Slow | High |
gpt-4o | Quick tasks, low cost | Fast | Low |
xhigh: Maximum depth. Critical decisions, complex architecture. (GPT-5.x only)high: Deep reasoning. Default.medium: Balanced.low: Quick answers.none: No extended reasoning.codex review --uncommitted 2>/dev/null
Simple. Codex sees the diff cold and reports what it finds. This is the highest-value pattern — a genuinely independent review from a different model family.
codex review --base main 2>/dev/null
Reviews everything on the current branch vs main.
codex exec "Read src/api/readiness.ts and its tests. Verify that every edge case in the scoring logic is covered. List any inputs that would produce incorrect scores." -m gpt-5.4 2>/dev/null
codex exec "Read the codebase architecture. Evaluate the data flow from GitHub API through to the UI. Identify any structural issues, unnecessary coupling, or scalability concerns." -m gpt-5.4 2>/dev/null
<skill-dir>/scripts/call-openai.sh "
## Task
Evaluate these two approaches to cache invalidation and recommend which is better for our constraints.
## Approach A
[description]
## Approach B
[description]
## Constraints
- 10k req/s, 90% reads
- Must handle concurrent writes
- Eventual consistency acceptable (< 5s)
" gpt-5.4 high
Codex Oracle is one of three peer CLI-based model oracles alongside gemini-oracle and claude-oracle. Each launches a different model family as an independent process.
/verify/verify is the single entry point for gate-level cross-model review. It owns the pairing rule (which oracle to pick based on the implementing agent's family), writes the prosecution doc, and handles the fix-and-re-review loop. Do not invoke this oracle directly from a gate flow — call /verify and it will pick and invoke the right oracle.
The pairing table lives inside /verify. It is not duplicated here.
When you invoke this oracle (either directly for an ad hoc cross-model check, or indirectly via /verify), the highest-signal prompt pattern is to hand it a specific in-repo skill as the checklist:
codex exec "Read the full text of .agents/skills/trade-path-audit/SKILL.md in the current repo and follow that protocol on the diff between main and HEAD. Produce the report format the skill specifies. Do not invent your own checklist — use the skill's." -m gpt-5.4 2>/dev/null
Common in-repo payloads:
/adversarial-verifier — Chain-of-Verification methodology with Saboteur / New Hire / Security Auditor personas./strategy-verification — scoring / statistical verification against replay integrity, capital adequacy, determinism./trade-path-audit — comprehensive retrofit audit.adversarial-trading.md — domain-specific trading attack checklist.This pattern keeps the methodology reproducible across model families — same protocol, different pretraining, genuinely different blind spots.
For quick, ad hoc cross-model reads outside the gate flow, the simplest pattern is still:
codex review --uncommitted 2>/dev/null
Codex sees the diff cold and reports what it finds. Use this when you don't need the prosecution-doc machinery.
codex not found: Install via npm install -g @openai/codex or check OpenAI's docs.OPENAI_API_KEY not set (API script): Add to ~/.secrets/api-keys.sh: export OPENAI_API_KEY='your-key-here'codex login to authenticate.codex review is the primary tool for code review. Don't craft manual review prompts when the built-in command exists.