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.
git clone --depth 1 https://github.com/Lykhoyda/ask-llmWrote 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.
[](https://agentmods.dev/agents/lykhoyda/ask-llm/codex-verifier)<a href="https://agentmods.dev/agents/lykhoyda/ask-llm/codex-verifier"><img src="https://agentmods.dev/badge/agents/lykhoyda/ask-llm/codex-verifier/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.
<a href="https://agentmods.dev/agents/lykhoyda/ask-llm/codex-verifier"><img src="https://agentmods.dev/badge/agents/lykhoyda/ask-llm/codex-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00099 | $0.02461 |
| Opus 5.5 | $0.00040 | $0.00984 |
| Sonnet 5.5 | $0.00020 | $0.00492 |
| Haiku 4.5 | $0.00010 | $0.00246 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 152 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-reviewerfinds new issues in a diff (issue hunt).codex-verifierchecks 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, mcp__plugin_ask-llm_codex__ask-codex, mcp__ask-llm__ask-llm.
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.
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.
- 1mo ago Changed · +2 lines 4f264d1a2298
- 1mo ago First seen · 150 lines · 99 tokens per session scan A fd8fe6842a2e
codex-verifier is an agent published in the GitHub repository Lykhoyda/ask-llm (18 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 2,461 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other agents, from other repositories
runtime-verifier
Use after a completed change when acceptance criteria must be exercised through the real user-facing, CLI, service, browser, filesystem, or integration boundary. Do not use to implement fixes or when the change is incomplete.
e2e-tests-engineer
Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.
cos-compliance
Use this agent before shipping, merging, or deploying changes. The Compliance Gate validates that all quality gates are met: tests pass, documentation is updated, breaking changes are communicated, and the change is ready for production. Context: User wants to merge a feature branch user: "I think this PR is ready to…
tester
Testing specialist for unit tests, integration tests, test coverage analysis, and TDD workflows. Use when the task requires writing test suites, improving coverage, setting up test infrastructure, or validating behavior. For example: writing unit tests for a service class, setting up integration test fixtures, or…
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
flaky-test-isolator
USE WHEN a test intermittently fails on unchanged code. Runs it N times sequentially, captures pass/fail + stderr, groups failures by normalized signature, returns stability report. Read-only — never modifies code or installs deps. For statistical signal across runs, not one-shot diagnosis.