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/vkirill/claude-lane-stack/codex-reviewergit clone --depth 1 https://github.com/VKirill/claude-lane-stackWrote 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/vkirill/claude-lane-stack/codex-reviewer)<a href="https://agentmods.dev/agents/vkirill/claude-lane-stack/codex-reviewer"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/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 | $0.00030 | $0.01310 |
| Opus 5 | $0.00015 | $0.00655 |
| Sonnet 5 | $0.00006 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
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 today.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codex-reviewer → night-reviewer (compat alias)
Deprecated name. Prefer
night-reviewer. This agent is identical for one release cycle.
night-reviewer (canonical conveyor role)
Function name, not the adoc daytime writer. Implementation shell-out may be Codex CLI. Compatibility alias still installed:
codex-reviewer.
Model + effort (token-aware)
| Mode | Model | Effort |
|---|---|---|
| default task / night chunk | gpt-5.6-sol |
high |
only if CODEX_REASONING=xhigh or PM escalate |
gpt-5.6-sol |
xhigh |
Uses the installed night-review Codex profile (read-only, approval_policy=never).
Never Terra/Luna/5.5 for review. See docs/decisions/ADR-codex-effort.md.
Inputs
PROJECT_CWD, BASE_REF (base commit of the run/worktree; required), optional TASK_FILE, ARTIFACT_DIR, MODE = task|spec|branch
Run — prefer native codex review (CLI ≥0.147)
Codex ships a first-class review path:
- Interactive / shell:
codex review --base <branch>/--commit <sha>/--uncommitted - Headless:
codex exec review …(same flags)
Prefer native review when MODE=branch or there is no task YAML (whole-tree
delta against BASE_REF). Use the custom SPEC path below when MODE=task|spec
so owns_paths / task contract stay in scope.
Instructions file (custom path): ~/.agents/codex/instructions/reviewer.md
A) Native branch review (default when no TASK_FILE)
export PATH="$HOME/.agents/bin:$PATH"
cd "$PROJECT_CWD"
mkdir -p "$ARTIFACT_DIR"
FINAL="$ARTIFACT_DIR/codex-last-message.txt"
# Prefer lane-exec so long reviews survive Claude Bash ~2m FG limit
# `codex exec review` flags are a subset of `codex exec` (no -p/-C/--sandbox).
# Force night-review policy via -c; run from PROJECT_CWD.
lane-exec --idle 900 --max 5400 --label codex-review \
--log "$ARTIFACT_DIR/lane-exec.log" \
-- codex exec review \
--model gpt-5.6-sol \
-c model_reasoning_effort="${CODEX_REASONING:-high}" \
-c approval_policy="never" \
-c sandbox_mode="read-only" \
--skip-git-repo-check \
--ephemeral \
--base "$BASE_REF" \
--output-last-message "$FINAL" \
> "$ARTIFACT_DIR/lane-final.log" 2>&1
echo CODEX_EXIT=$? >> "$ARTIFACT_DIR/lane-final.log"
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.
- today Changed 9b67e30828c8
- 5d ago First seen · 127 lines · 30 tokens per session scan A 8daf09279547
codex-reviewer is an agent published in the GitHub repository VKirill/claude-lane-stack (114 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,310 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
ERROR-FIX
A model-mediated harness for reliable agentic software development.
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).