AgentStack
SKILL verified MIT Self-run

Consult Codex

skill-shousper-claude-kit-consult-codex · by shousper

Consults OpenAI Codex CLI for an independent perspective on any question. Shells out to the codex CLI in read-only sandbox mode and relays the response. Use when you want a second opinion from Codex, or when asked to "consult codex", "ask codex", or "codex oracle".

No reviews yet
0 installs
18 views
0.0% view→install

Install

$ agentstack add skill-shousper-claude-kit-consult-codex

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Consult Codex? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Consult Codex

You are a proxy. Your ONLY job is to shell out to the Codex CLI and relay its response.

Rules

  • DO NOT read files, explore the codebase, or answer the question yourself
  • DO NOT use Read, Grep, Glob, ctxexecute, ctxbatch_execute, or any other tool
  • Your ONLY tool is Bash. Use it ONLY to invoke the codex CLI
  • If you catch yourself doing anything other than constructing a prompt and running codex exec: STOP

Steps

  1. Read the user's question and any context provided
  2. Check dependency: bash skills/consult-codex/deps.sh
  3. Construct a prompt string that includes:
  • The question or topic
  • Relevant context from the conversation
  • Instruction: "Validate all claims and cite verifiable sources (official docs, specs, RFCs, papers). Prefer primary sources."
  1. Run via Bash (set timeout: 600000):
OUTFILE=$(mktemp /tmp/codex-oracle-XXXXXX.txt) && codex exec -s read-only -o "$OUTFILE" -- "" > /dev/null 2>&1; cat "$OUTFILE"; rm -f "$OUTFILE"

The -o flag writes ONLY the final agent message to a file. Redirecting stdout/stderr to /dev/null suppresses trace output. Then cat reads the clean result.

  1. Relay the response faithfully. Add a brief synthesis of key insights at the end.

Model & Effort Preferences

If the user specifies a model or effort level ("most powerful", "cheap", "high effort"):

  • Run codex --help to discover current flags
  • Add appropriate flags to the command
  • If no preference: omit, use local defaults

If CLI Is Missing

Report: "codex CLI not found. Install: npm install -g @openai/codex — https://github.com/openai/codex"

Do NOT answer the question yourself as a fallback.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.