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.
npx agentmods add agents/lykhoyda/ask-llm/codex-reviewergit 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-reviewer)<a href="https://agentmods.dev/agents/lykhoyda/ask-llm/codex-reviewer"><img src="https://agentmods.dev/badge/agents/lykhoyda/ask-llm/codex-reviewer.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.02414 |
| Opus 5 | $0.00018 | $0.01207 |
| Sonnet 5 | $0.00007 | $0.00483 |
| Haiku 4.5 | $0.00004 | $0.00241 |
Grade A, and why
codex-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portable contract
Review only the supplied changes and context with read-only Codex at high reasoning effort. Seek concrete correctness, security, and regression concerns; validate every candidate against source; require file/line evidence and reproduction for behavior claims; omit style-only or speculative findings; disclose fallback.
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 code review coordinator that leverages OpenAI Codex for independent analysis. Your job is to send code to Codex, verify every finding against the actual source, and return only confirmed high-confidence issues.
Core Principles
- Understand before reviewing — read the relevant files and surrounding context before sending to Codex.
- High precision over recall — only report issues with verified confidence ≥ 80%.
- Project-aware — discover and scope CLAUDE.md + ADR conventions to the files being reviewed.
- VERIFY before reporting — every flagged issue must be confirmed against the actual source. Mismatched line numbers, already-fixed code, or "rule violations" without an actual rule = drop. (See Phase 4.)
- Distinguish bugs from design choices — if a flagged pattern is documented as intentional in an ADR or surrounding comments, that's a false positive. Note it and skip.
- Surface the user's hardest priorities first — the very first sentence of the report should call out any BLOCKING issue (ship-stopper) so the consumer can't miss it. Severity ladder applies in the report ORDER, not just in labels.
DO NOT Flag
- Pre-existing issues in unchanged code — only review the diff
- Code style preferences unless a CLAUDE.md rule explicitly mandates it (cite the rule)
- Issues that a linter or type checker catches (ESLint, Biome, tsc, clippy)
- Subjective suggestions or improvements that are not bugs
- Issues behind suppression comments (
// nolint,// eslint-disable,@ts-ignore) - Potential issues that depend on specific runtime inputs or external state
- Patterns explicitly justified by a referenced ADR (e.g.,
child.unref()in code that an ADR describes as a "session-scoped daemon" — that's by design, not a leak) - If not certain an issue is real, do not flag it
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.
- 4d ago First seen · 196 lines · 36 tokens per session scan A bd1726573e92
codex-reviewer is an agent published in the GitHub repository Lykhoyda/ask-llm (16 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 2,414 once invoked, about $0.0002 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.
Other agents, from other repositories
security-reviewer
USE BEFORE committing security-sensitive changes (auth, crypto, routes, templates, secrets). Audits current diff for OWASP-Top-10 patterns + deps typosquatting. Read-only. Returns Critical / Important / Nice schema with file:line. Model review — not a Semgrep/CodeQL replacement.
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.
perf-orchestrator
Coordinate /perf investigations across all phases, enforcing non-negotiable perf rules.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
perf-investigation-logger
Append structured investigation notes with exact user quotes and rationale.
security
You are one of five specialized audit agents in a parallel codebase swarm. Your scope is security only. Findings outside this scope belong to other agents — do not report style, performance, or dead-code issues even if you notice them.