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 skills add AlexAtmtit/custom-skills --skill codex-reviewgit clone --depth 1 https://github.com/AlexAtmtit/custom-skillsWrote 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/skills/alexatmtit/custom-skills/codex-review)<a href="https://agentmods.dev/skills/alexatmtit/custom-skills/codex-review"><img src="https://agentmods.dev/badge/skills/alexatmtit/custom-skills/codex-review/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/skills/alexatmtit/custom-skills/codex-review"><img src="https://agentmods.dev/badge/skills/alexatmtit/custom-skills/codex-review.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 | $0.00057 | $0.00686 |
| Opus 5 | $0.00028 | $0.00343 |
| Sonnet 5 | $0.00011 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
codex-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Review via Tmux
Overview
Launch OpenAI's Codex CLI in a tmux session and run the /review command to get a code review of uncommitted changes. The skill handles the full lifecycle: setup, command execution, waiting for completion (up to 60 minutes), capturing output, and cleanup.
Prerequisites
Before running, verify:
tmuxis installed and availablecodexCLI is installed and available
The Process
Step 1: Setup Tmux Session
SOCKET="${TMPDIR:-/tmp}/codex-review-$$.sock"
SESSION="codex-review-$$"
tmux -S "$SOCKET" new-session -d -s "$SESSION"
Step 2: Launch Codex and Send Commands
# Launch codex
tmux -S "$SOCKET" send-keys -t "$SESSION" "codex" Enter
# Wait for codex to initialize
sleep 5
# Type /review command
tmux -S "$SOCKET" send-keys -t "$SESSION" -l "/review"
# Press Enter to execute the /review command
tmux -S "$SOCKET" send-keys -t "$SESSION" Enter
# Wait for menu to appear
sleep 2
# Select option 2: Review uncommitted changes (no Enter needed)
tmux -S "$SOCKET" send-keys -t "$SESSION" -l "2"
Step 3: Wait for Completion
Poll every 60 seconds for up to 60 minutes:
wait_for_completion() {
local timeout=3600 interval=60 elapsed=0
while [ $elapsed -lt $timeout ]; do
output=$(tmux -S "$SOCKET" capture-pane -p -t "$SESSION" -S -100)
# Check for completion (shell prompt returned)
if echo "$output" | grep -qE '(❯|\$|>>>)\s*$'; then
return 0
fi
sleep $interval
elapsed=$((elapsed + interval))
done
return 1
}
wait_for_completion
Step 4: Capture Output
# Capture full pane output (last 500 lines)
tmux -S "$SOCKET" capture-pane -p -t "$SESSION" -S -500
Step 5: Cleanup
tmux -S "$SOCKET" kill-session -t "$SESSION"
rm -f "$SOCKET"
To Monitor Manually
If you want to watch the session while it runs:
tmux -S "$SOCKET" attach -t "$SESSION"
Detach with Ctrl+b d.
Success Criteria
- Codex review output is captured and displayed
- Tmux session is cleaned up
- No orphaned processes or sockets
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.
- 9d ago First seen · 103 lines · 57 tokens per session scan A d21f886bda5d
codex-review is a skill published in the GitHub repository AlexAtmtit/custom-skills (22 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 686 once invoked, about $0.0003 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…