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 AuroraPixel/ai-native-harness-skill --skill review-loopgit clone --depth 1 https://github.com/AuroraPixel/ai-native-harness-skillWrote 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/aurorapixel/ai-native-harness-skill/review-loop)<a href="https://agentmods.dev/skills/aurorapixel/ai-native-harness-skill/review-loop"><img src="https://agentmods.dev/badge/skills/aurorapixel/ai-native-harness-skill/review-loop/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/aurorapixel/ai-native-harness-skill/review-loop"><img src="https://agentmods.dev/badge/skills/aurorapixel/ai-native-harness-skill/review-loop.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 | $0.00130 | $0.05058 |
| Opus 5.5 | $0.00052 | $0.02023 |
| Sonnet 5.5 | $0.00026 | $0.01012 |
| Haiku 4.5 | $0.00013 | $0.00506 |
Grade C, and why
review-loop scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
"$(find ~/.claude/plugins/cache -path "*/review-loop" -type d 2>/dev/null | head -1)" \ Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
"$(find ~/.claude/skills -path "*/review-loop" -type d 2>/dev/null | head -1)" \ This is a copy
100% identical to review-loop — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Loop — Cross-LLM Iterative Code Review
Spawns a peer reviewer (Codex, Claude, or Gemini) to independently review your code changes. The host agent evaluates findings, implements accepted fixes, and re-submits for peer re-review. Iterates until both agents agree on the final code state.
Key: You (the human) do NOT need to participate. Watch progress via .review-loop/<session>/rounds.json and summary.md.
Compatibility note: rounds.json keeps the historical field name claude_actions for backward compatibility. In Codex-hosted runs, that field still stores the host agent's decisions and code changes.
Prerequisites
- Required:
gitCLI - Peer (one of):
codexCLI (codex --version),claudeCLI (claude --version), orgeminiCLI (gemini --version) - Optional:
ghCLI (for PR scope detection)
Configuration
Defaults
| Setting | Default | Options |
|---|---|---|
peer_reviewer |
codex |
codex, claude, gemini |
max_rounds |
5 |
1–10 |
timeout_per_round |
600 |
seconds |
scope_preference |
auto |
auto, diff, branch, pr |
read_only |
false |
true = report-only, no code changes |
The peer reviewer always runs with local repository access.
Read-only mode (read_only: true): Peer reviews code and the host agent evaluates findings, but NO code changes are made. Output is a findings report only — no fix commits, no code evolution loop. Useful when review-loop is used as a sensor by other skills (e.g., the bundled harness skill's Evaluator Tier 2). In read-only mode, Phase 2 (Code Evolution Loop) is skipped entirely — after Round 1 findings are evaluated, the loop goes directly to Phase 3 report generation with all findings classified as reported (not accepted/rejected).
Override via project config
Create .review-loop/config.json in the project root to override defaults:
{
"peer_reviewer": "gemini",
"max_rounds": 8
}
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 500 lines · 130 tokens per session scan C d828f40219e5
review-loop is a skill published in the GitHub repository AuroraPixel/ai-native-harness-skill (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 130 tokens to every session and 5,058 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). It is 100% identical to review-loop, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…