codex-verify

codex-verify is a skill for Claude Code, Codex from Lykhoyda/ask-llm. It costs 94 tokens per session (1,455 once invoked), scanned A, original, MIT.

A skill for checking whether an AI assistant's claimed work matches the actual state of a repository. It uses read-only inspection and records which claims can or cannot be proven.

In plain words
What is it for?
Use it to verify edits, test results, generated files, or other claims made during a coding session.
Why use it?
It helps distinguish completed work from unsupported statements without changing project files.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ask-llm plugin — 18 skills, 9 agents, 5 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/lykhoyda/ask-llm/codex-verify
Any agent
npx skills add Lykhoyda/ask-llm --skill codex-verify
Clone the repo
git clone --depth 1 https://github.com/Lykhoyda/ask-llm

Made for: Claude Code, Codex.

Or install ask-llm, the plugin that ships this one along with the rest of its 18 skills, 9 agents, 5 hooks, 1 MCP server.

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.

agentmods badge for codex-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/lykhoyda/ask-llm/codex-verify.svg)](https://agentmods.dev/skills/lykhoyda/ask-llm/codex-verify)
Your own site
<a href="https://agentmods.dev/skills/lykhoyda/ask-llm/codex-verify"><img src="https://agentmods.dev/badge/skills/lykhoyda/ask-llm/codex-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,455 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00094 $0.01455
Opus 5 $0.00047 $0.00727
Sonnet 5 $0.00019 $0.00291
Haiku 4.5 $0.00009 $0.00145

Measured 4d ago against content hash b59542e05efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-verify scanned grade A with 0 findings 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/claude-plugin/skills/codex-verify/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Host adapters

Pi adapter

Apply only the portable contract in ../../agents/codex-verifier.md inline and call native ask-codex for focused claim checks. Do not claim an isolated verifier context.

Claude Code adapter

The existing detailed workflow below is the Claude Code adapter. Its Agent, MCP, hook, CLAUDE_PLUGIN_ROOT, and AskUserQuestion mechanics apply only on Claude Code; they do not override the Pi adapter above.

Codex Claim Verification

Prove or disprove what the assistant agent claims to have done in the current turn, independently. This is a trust check, not an issue hunt — separate from /codex-review.

Why this is separate from /codex-review

  • /codex-review looks for new bugs in the diff (issue hunt).
  • /codex-verify proves the assistant's claims against actual state (trust verification).

A single tool would dilute both contracts. The verifier is structurally narrowed by design: it does not propose fixes, does not list issues outside the assistant's claims, does not drift into "while I'm here let me also...". That narrowness is the feature — it forces every "verified" verdict to be backed by a deterministic tool output.

The two skills compose. Run both when you want both questions answered. Do not merge their outputs.

Instructions

Phase 1: Gather inputs

  1. Combine the diff:
    • git diff (unstaged changes)
    • git diff --cached (staged changes)
  2. If the diff is empty, stop and tell the user "no changes to verify."
  3. Capture the assistant's last message — the message in the prior turn where the assistant stated what it did. This is the source of claims to verify. Pass it through verbatim — do not summarize, do not paraphrase. The agent decomposes claims directly from this text.

Read the full file on GitHub · 111 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.

  1. 4d ago First seen · 111 lines · 94 tokens per session scan A b59542e05efe

Subscribe to this mod's changes

codex-verify is a skill published in the GitHub repository Lykhoyda/ask-llm (16 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,455 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

glossary-init

USE WHEN setting up a repo for AI-first work, when an agent hallucinates domain term meaning, or when user asks to bootstrap / extend the repo's domain glossary. Surfaces candidate terms by identifier frequency, asks the user for 1-sentence definitions, writes GLOSSARY.md at repo root. Idempotent — re-running adds new…

Filip-Podstavec/claude-leverage · 119 tokens

conventions-init

USE WHEN setting up a repo for AI-first work (after /init-repo), or when the context-surface hook should start feeding repo conventions to agents before edits. Drafts conventions.yml at repo root: per-kind casing (inferred from the code), a vague-name denylist seed, directory roles, and a hand-filled house-rules…

Filip-Podstavec/claude-leverage · 124 tokens

opik

This skill should be used when the user needs to add Opik tracing or integrations to their code, instrument an LLM application, or needs reference for Opik SDK usage (Python, TypeScript, REST API). Use for tasks like "add tracing", "instrument my code", "use trackopenai", "add OpikTracer", "what span types are…

comet-ml/opik-claude-code-plugin · 84 tokens

claude-rescue

Use when running under Codex CLI and stuck, wanting a second implementation or diagnosis pass, or handing a substantial task to Claude Code through a real Claude Code subprocess — a genuinely different reasoning system, not another Codex run. Not relevant outside Codex sessions.

patrickserrano/lacquer · 57 tokens

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

composio-community/awesome-claude-plugins · 61 tokens

swarm

Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…

Zintellix/Claude-Skills · 138 tokens