A way to ask OpenAI Codex for a second opinion during investigation, debugging, or code review.

Use it to investigate an error, review code, debug a stubborn issue, or request Codex's opinion on a technical question.

It provides another analysis when a problem is difficult or your current debugging approaches have not worked.

ask-codex — Skill for Claude Code by umputun/cc-thingz

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add umputun/cc-thingz --skill ask-codex

Clone the repo

git clone --depth 1 https://github.com/umputun/cc-thingz

Made for: Claude Code.

Or install thinking-tools, the plugin that ships this one along with the rest of its 3 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/umputun/cc-thingz/ask-codex/github.svg)](https://agentmods.dev/skills/umputun/cc-thingz/ask-codex)

Your own site

<a href="https://agentmods.dev/skills/umputun/cc-thingz/ask-codex"><img src="https://agentmods.dev/badge/skills/umputun/cc-thingz/ask-codex/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/umputun/cc-thingz/ask-codex"><img src="https://agentmods.dev/badge/skills/umputun/cc-thingz/ask-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,501 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Excessive Agency · line 168
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00103	$0.02501
Opus 5.5	$0.00041	$0.01000
Sonnet 5.5	$0.00021	$0.00500
Haiku 4.5	$0.00010	$0.00250

Measured 2d ago against content hash 95744267beaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

ask-codex scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `${CODEX_MODEL:+--model=$CODEX_MODEL}` — the model comes from the user's `~/.codex/config.toml`; it is overridden only when `CODEX_MODEL` is set. Keep this expansion unquoted so it disappears when the variable is unset

plugins/thinking-tools/skills/ask-codex/SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask Codex

Consult OpenAI Codex as a second opinion for investigation, debugging, or review tasks.

Activation Triggers

Explicit:

"ask codex", "check with codex", "codex review"
"what does codex think", "get codex opinion"
"consult codex", "run codex on this"

Automatic (last resort — stuck detection):

4+ failed attempts at the same bug fix or investigation
completely out of ideas, all reasonable approaches exhausted
going in circles with no progress despite multiple different strategies

Workflow

Step 1: Check Availability

Run which codex to verify the CLI is installed. If not found, inform the user and stop.

Step 2: Build Context

Gather context from the current conversation:

What's the problem/question — summarize in 2-3 sentences
What we know — relevant files, error messages, behavior observed
What we tried — approaches attempted and why they failed (if applicable)
Specific question — what exactly codex should analyze or answer

Codex does NOT auto-load Claude Code's memory files — it only reads AGENTS.md. To give Codex the same project context Claude follows, prepend the memory-load preamble described in Step 3.

Step 3: Construct Prompt

Build a focused prompt. Do NOT dump entire files — codex has full project access and can read them itself. Provide file paths and line references so codex knows where to look.

Prepend a memory-load preamble. Codex auto-loads only AGENTS.md; it does NOT read Claude Code's memory files (CLAUDE.md, CLAUDE.local.md, .claude/rules/, ~/.claude/CLAUDE.md), so the project conventions Claude follows are invisible to Codex unless you tell it to read them. Prepend this line to the prompt:

First read these project guidance files if present: <ABS_HOME>/.claude/CLAUDE.md, CLAUDE.md, CLAUDE.local.md, .claude/rules/

Resolve <ABS_HOME> to the absolute home path (run echo $HOME, e.g. /home/<user>) and write the literal path — do NOT leave the string $HOME in the prompt. Whether $HOME expands depends on how the prompt is passed to Codex, and Codex may open the file with a non-shell tool that never expands it, so only a literal absolute path is reliable.
No @ prefix — @file is inert in codex exec (literal text, not an import).
The project-relative paths resolve against Codex's working directory; Codex skips any that don't exist.

Read the full file on GitHub · 261 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago Changed scan A → B 95744267beaf
1mo ago First seen · 261 lines · 103 tokens per session scan A 9fc88c763d14

Subscribe to this mod's changes

ask-codex is a skill published in the GitHub repository umputun/cc-thingz (487 stars, last pushed 2d ago), licensed MIT. It adds 103 tokens to every session and 2,501 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Claude Code Debugging claude-code-plugin marketplace plugin

smalltalk-debugger

Systematic debugging guide for Smalltalk (Pharo/Squeak) development. Provides expertise in error diagnosis (MessageNotUnderstood, KeyNotFound, SubscriptOutOfBounds, AssertionFailure), incremental code execution with eval tool, intermediate value inspection, error handling patterns (on:do: blocks), stack trace…

mumez/smalltalk-dev-plugin · 87 tokens

smalltalk-usage-finder

Class and method usage analyzer for Smalltalk (Pharo/Squeak). Provides expertise in understanding class responsibilities through class comments (getclasscomment), discovering usage patterns via references (searchreferencestoclass), finding example methods (exampleXXX patterns), analyzing method usage in context…

mumez/smalltalk-dev-plugin · 139 tokens

st-eval

Smalltalk code evaluator for Pharo or Squeak via MCP. Use when executing Smalltalk expressions, verifying object state or intermediate values, debugging code incrementally, checking the Smalltalk image connection, or running quick experiments.

mumez/smalltalk-dev-plugin · 49 tokens

structured-output

This skill should be used when the user mentions "structured output", "json mode", "tool schema", "function calling", "json parse error", "responseformat", "pydantic ai", "invalid json from the model", or "the model's JSON keeps breaking". It provides a methodology for getting reliably valid, schema-conformant…

sigistry/marketplace · 89 tokens

fhir-project-doctor

Inspect an HL7 FHIR, FSH/SUSHI, or Implementation Guide project for validator runtimes, FHIR package dependencies, cache state, version signals, privacy gates, and setup blockers. Use when FHIR validation cannot start, profiles or packages are missing, IG Publisher/Firely/HAPI/Records availability is unclear, or the…

sigistry/marketplace · 88 tokens

incident-response

This skill should be used when the user mentions "postmortem", "incident", "root cause analysis", "blameless", "severity", "SEV1", "on-call", "RCA", or "outage", or is writing up an incident. It provides a blameless postmortem methodology, a severity model, and reliability metric definitions.

sigistry/marketplace · 78 tokens

ask-codex