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 asiridalugoda/autonomous-loop --skill luna-maxinggit clone --depth 1 https://github.com/asiridalugoda/autonomous-loopWrote 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/asiridalugoda/autonomous-loop/luna-maxing)<a href="https://agentmods.dev/skills/asiridalugoda/autonomous-loop/luna-maxing"><img src="https://agentmods.dev/badge/skills/asiridalugoda/autonomous-loop/luna-maxing/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/asiridalugoda/autonomous-loop/luna-maxing"><img src="https://agentmods.dev/badge/skills/asiridalugoda/autonomous-loop/luna-maxing.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 | $0.00084 | $0.01153 |
| Opus 5.5 | $0.00034 | $0.00461 |
| Sonnet 5.5 | $0.00017 | $0.00231 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
luna-maxing 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Luna-maxing
Overview
Tandem build: Claude orchestrates, Codex builds and reviews. Every line of product code, every fix and every review verdict comes from a Codex seat (codex exec -m gpt-5.6-luna, effort max). The Claude session plans, rules on ambiguities, dispatches, runs the local gates itself, and owns git and draft PRs. Nothing is pushed until the controller's own gates are green on that exact head AND the Codex review is clean.
REQUIRED SUB-SKILL: superpowers:subagent-driven-development (ledger, briefs, review packages, fix-loop discipline). This skill replaces its subagents with Codex seats.
Roles
| Seat | Who | Session |
|---|---|---|
| Orchestrator: plan, rulings, dispatch, gates, git, rebases without conflicts, draft PRs, ledger | Claude | this session |
| Implementer, fixer, conflict-resolving rebase job | Codex Luna max | implementer thread, resumed for fixes |
| Reviewer, scoped re-reviewer | Codex Luna max | fresh session every time |
The controller never edits product code. A controller "quick fix" skips review.
Quick reference
| Step | Tool |
|---|---|
| Dispatch a seat (background) | LUNA_WS=<ws> scripts/dispatch.sh NAME WORKTREE PROMPT (--resume THREAD for fixes) |
| Wait out a usage limit | scripts/wait-codex-reset.sh "<RESET_AT>" (background) |
| Local green | LUNA_WS=<ws> LUNA_GATES_PROFILE=profiles/<project>.sh scripts/gates.sh NAME WORKTREE BASE [args] |
| Prompt bodies | templates/implementer.md, reviewer.md, rereview.md |
| Prompt headers, fix round, rebase job, continuation | templates/headers.md, fix-round.md, rebase-job.md, continue.md |
| Constraints file (worked example), seed lessons | templates/constraints.md (examples/constraints-example-saas.md), templates/lessons.md |
| Gate profiles | profiles/example-fullstack.sh (full example), profiles/example-minimal.sh (template), profiles/autonomous-loop.sh (repository gate) |
| Setup, loop, stacking, failure playbook | reference.md |
What ships with it
17 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.
- examples/constraints-example-saas.md 4.9 KB
- profiles/autonomous-loop.sh 9.8 KB runs code
- profiles/example-fullstack.sh 5.4 KB runs code
- profiles/example-minimal.sh 563 B runs code
- reference.md 8.9 KB
- scripts/dispatch.sh 2.4 KB runs code
- scripts/gates.sh 1.4 KB runs code
- scripts/wait-codex-reset.sh 1.2 KB runs code
- templates/constraints.md 1.2 KB
- templates/continue.md 868 B
- templates/fix-round.md 1.2 KB
- templates/headers.md 2.5 KB
- templates/implementer.md 2.9 KB
- templates/lessons.md 1.7 KB
- templates/rebase-job.md 1.1 KB
- templates/rereview.md 1.3 KB
- templates/reviewer.md 3.5 KB
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 · 72 lines · 84 tokens per session scan A 43826221313c
luna-maxing is a skill published in the GitHub repository asiridalugoda/autonomous-loop (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,153 once invoked, about $0.0003 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 2026-09-16.
Other skills, from other repositories
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
review
Comprehensive security and correctness audit. Use for review, deep review, thermo nuclear, or thermonuclear requests and branch or PR diff audits.
git
Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.