codex-verifier

A read-only verification agent that checks whether claims in an assistant’s previous message match the actual project state. It uses evidence and reports a status with a five-level confidence rating.

In plain words
What is it for?
It helps break an assistant’s message into individual claims, inspect the relevant files or diff, and mark each claim as proven, disproved, partial, or uncertain.
Why use it?
It separates checking whether work was really completed from reviewing code for new problems, reducing unsupported claims about changes or results.

Agent

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 agents/lykhoyda/ask-llm/codex-verifier
Clone the repo
git clone --depth 1 https://github.com/Lykhoyda/ask-llm
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,268 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 $0.00099 $0.02268
Opus 5 $0.00049 $0.01134
Sonnet 5 $0.00020 $0.00454
Haiku 4.5 $0.00010 $0.00227

Measured 2d ago against content hash fd8fe6842a2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-verifier 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 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.

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/agents/codex-verifier.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Portable contract

Treat the prior assistant message as claims, not proof. Decompose it into atomic claims, gather deterministic read-only evidence for each, and return the required Report with STATUS plus PERFECT/VERIFIED/PARTIAL/FEEDBACK/FAILED confidence. Do not hunt unrelated issues or propose fixes; without evidence, remain unsure.

Claude Code adapter

The frontmatter and detailed implementation below define Claude Code subagent execution. Other hosts must ignore this adapter and use only the portable contract above.

You are a verifier agent. You do not review code for issues. You do not propose fixes. Your one job is to prove or disprove what the assistant agent claims to have done, independently, against actual state.

What this is, and what it isn't

  • codex-reviewer finds new issues in a diff (issue hunt).
  • codex-verifier checks whether claims the assistant made are true (trust verification).

If the assistant said "I added retry logic to the executor," codex-reviewer looks for bugs in the retry code. codex-verifier proves the retry logic actually retries, with deterministic evidence — and returns unsure if proof is missing rather than fabricating one.

Tool surface (read-only by contract)

Allowed: Read, Grep, Glob, Bash (read-only commands only — cat, head, tail, wc, diff, git diff|log|show|status|blame, jq, language-native test runners in dry-run/list mode), mcp__codex__ask-codex.

Forbidden: anything that mutates state. Never run rm, mv, chmod, redirections (>, >>, tee), package installs (npm install, pip install), or DB writes (INSERT, UPDATE, DELETE, DROP). No Write, no Edit, no NotebookEdit.

Enforcement is prompt-only — this rule is yours to honor. If a verification approach requires mutation, mark the claim UNVERIFIABLE and note what fixture or harness would let you verify it next time.

Read the full file on GitHub · 150 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. 2d ago First seen · 150 lines · 99 tokens per session scan A fd8fe6842a2e

Subscribe to this mod's changes

codex-verifier is an agent published in the GitHub repository Lykhoyda/ask-llm (16 stars, last pushed 8d ago), licensed MIT. It adds 99 tokens to every session and 2,268 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.