ask-codex SKILL.md skillA

ask-codex from umputun/cc-thingz is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add umputun/cc-thingz/ask-codex@git:20261018.9011e3c

Pins git:20261018.9011e3c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
umputun/cc-thingz
Path
plugins/thinking-tools/skills/ask-codex/SKILL.md
Versions recorded
5
Latest version
git:20261018.9011e3c, committed Oct 18, 2026
First version recorded
Mar 6, 2026
Size
10,546 bytes
Repository stars
492
License
MIT

Consult OpenAI Codex for investigation, debugging, or code review. Use when user explicitly asks to "ask codex", "check with codex", "codex review", or as a last resort when stuck after 4+ failed attempts at debugging, investigation, or bug fix and completely out of ideas. Codex is slow (2-5 min), so only escalate when truly stuck. Codex runs in read-only mode with full project access — it analyzes, we implement.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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:

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

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add umputun/cc-thingz/ask-codex@sha256:95744267beaff837

The line at the top of this page pins the label git:20261018.9011e3c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_d5lxkbpp72s3753c.svg)](https://markdownregistry.com/a/art_d5lxkbpp72s3753c)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Mar 6, 2026 and Oct 18, 2026, about one every 56 days.

versioncommittedcommitsizeaudit
git:20261018.9011e3c latest2026-10-18 9011e3c 10,546 BA view · diff
git:20260622.9cf28c92026-06-22 9cf28c9 10,383 BA view · diff
git:20260509.4125fe52026-05-09 4125fe5 8,941 BA view · diff
git:20260413.c5091a72026-04-13 c5091a7 8,941 BA view · diff
git:20260306.c0715a32026-03-06 c0715a3 3,801 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10546 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

umputun/cc-thingz · 492 stars · license MIT · pushed 2026-10-25 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_d5lxkbpp72s3753c
GET https://markdownregistry.com/api/v1/resolve?ref=umputun/cc-thingz/ask-codex
GET https://markdownregistry.com/api/v1/blob/95744267beaff837c84364be5069d231a32e946b84b086240d24728388e42435

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from umputun/cc-thingz

CLAUDE.md CLAUDE.md file
umputun/cc-thingz · CLAUDE.md
git:20260820.2729925 · audit A · 492 stars
brainstorm SKILL.md skill
umputun/cc-thingz · plugins/brainstorm/skills/brainstorm/SKILL.md · Use before any creative work or significant changes. Activates on "brainstorm", "let's brainstorm", "deep analysis"…
git:20260504.5f947a7 · audit A · 492 stars
exec SKILL.md skill
umputun/cc-thingz · plugins/planning/skills/exec/SKILL.md · Execute plan tasks sequentially using subagents. Use when user says 'exec', 'execute plan', 'run plan', or wants to…
git:20261025.f84b93c · audit A · 492 stars
last-tag SKILL.md skill
umputun/cc-thingz · plugins/release-tools/skills/last-tag/SKILL.md · Show commits since the last tag in a formatted table. Use when user asks "what changed since last release", "commits…
git:20260402.605bef0 · audit A · 492 stars
new SKILL.md skill
umputun/cc-thingz · plugins/release-tools/skills/new/SKILL.md · Use when user asks to create a release, cut a release, or publish a version. Auto-detects GitHub vs GitLab vs Gitea…
git:20260821.6a59551 · audit A · 492 stars
git-review SKILL.md skill
umputun/cc-thingz · plugins/review/skills/git-review/SKILL.md · Interactive git diff annotation review. Generates a cleaned-up diff, opens in editor for user annotations, and…
git:20260817.d18d8f8 · audit A · 492 stars
pr SKILL.md skill
umputun/cc-thingz · plugins/review/skills/pr/SKILL.md · Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review…
git:20260218.ebd1cfb · audit A · 492 stars
writing-style SKILL.md skill
umputun/cc-thingz · plugins/review/skills/writing-style/SKILL.md · Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments…
git:20260330.c77a2aa · audit A · 492 stars
dialectic SKILL.md skill
umputun/cc-thingz · plugins/thinking-tools/skills/dialectic/SKILL.md · Prove and counter-prove a statement using parallel agents to eliminate confirmation bias. Use when someone says…
git:20260217.d627b3f · audit A · 492 stars
root-cause-investigator SKILL.md skill
umputun/cc-thingz · plugins/thinking-tools/skills/root-cause-investigator/SKILL.md · Systematic root cause analysis for errors, bugs, and unexpected behaviors using 5-Why methodology. Use when user…
git:20260217.d627b3f · audit A · 492 stars
backlog SKILL.md skill
umputun/cc-thingz · plugins/workflow/skills/backlog/SKILL.md · Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says…
git:20260823.b8f4a23 · audit A · 492 stars
clarify SKILL.md skill
umputun/cc-thingz · plugins/workflow/skills/clarify/SKILL.md · This skill should be used when user appears confused, frustrated, or shows misalignment between expectations and…
git:20260218.782e0e3 · audit A · 492 stars

Every file in umputun/cc-thingz

Other files named ask-codex

ask-codex SKILL.md skill
hiroro-work/claude-plugins · skills/ask-codex/SKILL.md · Asks Codex CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating…
git:20260930.dc782d4 · audit A · 47 stars
ask-codex SKILL.md skill
yeaight7/agent-powerups · skills/ask-codex/SKILL.md · Use when a Claude Code agent needs to delegate a question, subtask, or review to a local Codex instance.
git:20260429.74655e1 · audit A · 8 stars
ask-codex SKILL.md skill
s977043/river-review · .claude/skills/ask-codex/SKILL.md · Get a second opinion or independent review from Codex (OpenAI) via the local Codex CLI. Use when the user wants Codex…
git:20260724.d54eafd · audit A · 7 stars

Browse by kind, by grade A, or by owner.