ask-llm-codex-verify SKILL.md skillA

ask-llm-codex-verify from lykhoyda/ask-llm is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lykhoyda/ask-llm/ask-llm-codex-verify@git:20261002.162238f

Pins git:20261002.162238f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lykhoyda/ask-llm
Path
packages/llm-mcp/skills/ask-llm-codex-verify/SKILL.md
Versions recorded
1
Latest version
git:20261002.162238f, committed Oct 2, 2026
Size
6,767 bytes
Repository stars
18
License
MIT

Verifies what the assistant claims to have done — proves the work against actual state using OpenAI Codex with a read-only tool surface. Use when the user asks to "verify with Codex", "check the assistant's claims", "did Codex actually do what it said", "verify this turn", "prove the work", or wants a trust check distinct from issue review. Different from `/codex-review`, which finds new issues.

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

<!-- PORTABLE-CONTRACT:START -->
## Portable contract

Capture the prior assistant message verbatim, decompose it into atomic claims, and verify those claims against actual repository state with a read-only Codex consultation where useful. This is claim verification, not issue hunting. Preserve the Report block, five-grade confidence ladder, parser fallback, and explicit unverifiable state.
<!-- PORTABLE-CONTRACT:END -->

## Host adapters

### Pi adapter

Apply the portable contract above inline and call native `ask-codex` for focused claim checks. Do not claim an isolated verifier context.

### Other hosts adapter

Codex, Cursor Agent, Antigravity, Grok Build, Gemini CLI and OpenCode get this skill from their skills folder, not from a plugin. Apply the portable contract above inline and use the Codex call from `../ask-llm-review/transport.md` for focused claim checks: `model: "gpt-6-astra"`, `reasoningEffort: "high"`, `sandbox: "read-only"`. Do not claim an isolated verifier context.

<!-- HOST-ADAPTER:CLAUDE-CODE:START -->
### Claude Code adapter
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add lykhoyda/ask-llm/ask-llm-codex-verify@sha256:797023d15c565a17

The line at the top of this page pins the label git:20261002.162238f, 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_gowy4d2a2lrby2vv.svg)](https://markdownregistry.com/a/art_gowy4d2a2lrby2vv)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 2, 2026.

versioncommittedcommitsizeaudit
git:20261002.162238f latest2026-10-02 162238f 6,767 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 (6767 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

lykhoyda/ask-llm · 18 stars · license MIT · pushed 2026-10-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gowy4d2a2lrby2vv
GET https://markdownregistry.com/api/v1/resolve?ref=lykhoyda/ask-llm/ask-llm-codex-verify
GET https://markdownregistry.com/api/v1/blob/797023d15c565a17ffdd29f930066a8670ac48e6e1d9d277d36aba1bbc961308

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 lykhoyda/ask-llm

AGENTS.md AGENTS.md file
lykhoyda/ask-llm · AGENTS.md
git:20261013.9e20d1f · audit A · 18 stars
llms-full.txt@apps/docs/public llms.txt file
lykhoyda/ask-llm · apps/docs/public/llms-full.txt
git:20261013.da481b2 · audit A · 18 stars
llms.txt@apps/docs/public llms.txt file
lykhoyda/ask-llm · apps/docs/public/llms.txt
git:20261013.9e20d1f · audit A · 18 stars
antigravity-review SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/antigravity-review/SKILL.md · Earlier name of the ask-llm-antigravity-review skill; use when the user invokes /antigravity-review.
git:20261002.162238f · audit A · 18 stars
ask-llm-antigravity-review SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/ask-llm-antigravity-review/SKILL.md · Get a second opinion from Google Antigravity (agy) on your current code changes. Analyzes staged/unstaged diffs and…
git:20261002.162238f · audit A · 18 stars
ask-llm-brainstorm-all SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/ask-llm-brainstorm-all/SKILL.md · Send a topic to all external providers (Gemini, Codex, Grok, Ollama, Antigravity) concurrently after the current host…
git:20261002.162238f · audit A · 18 stars
ask-llm-brainstorm SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/ask-llm-brainstorm/SKILL.md · Send a topic to an explicit multi-model panel, then synthesize findings with truthful provider, harness, and model…
git:20261002.162238f · audit A · 18 stars
ask-llm-codex-image SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/ask-llm-codex-image/SKILL.md · Generate an image via OpenAI's gpt-image-2 model through the Codex CLI. Use when user asks to "generate an image"…
git:20261002.162238f · audit A · 18 stars
ask-llm-codex-pair-ack SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/ask-llm-codex-pair-ack/SKILL.md · Acknowledge a codex-pair finding by its 16-character hash and a user-owned reason. Use when the user wants to suppress…
git:20261002.162238f · audit A · 18 stars
ask-llm-codex-pair-pause SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/ask-llm-codex-pair-pause/SKILL.md · Pause codex-pair for this project without removing `.codex-pair/context.md`. Writes the shared…
git:20261002.162238f · audit A · 18 stars
ask-llm-codex-pair-resume SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/ask-llm-codex-pair-resume/SKILL.md · Resume codex-pair for this project after a previous pause. Removes `.codex-pair/state/paused` and clears failure state…
git:20261002.162238f · audit A · 18 stars
ask-llm-codex-pair SKILL.md skill
lykhoyda/ask-llm · packages/llm-mcp/skills/ask-llm-codex-pair/SKILL.md · Pair with Codex using the host's supported lifecycle. On Claude Code and Pi, manages the proven opt-in per-edit review…
git:20261002.162238f · audit A · 18 stars

Every file in lykhoyda/ask-llm

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