agentmods.dev

clients: Skill for Claude Code

.claude/skills/cubic-loop/SKILL.md

cubic-loop is a skill for Claude Code from daytona/clients. It costs 104 tokens per session (3,308 once invoked), scanned C, original, no licence file.

An iterative code-review workflow that runs AI reviews, fixes reported problems, and reviews the code again. It has separate limits for local work before a pull request and for an already-open pull request.

In plain words
What is it for?
Use it to improve code before opening a pull request or to work through review comments on an existing one.
Why use it?
It turns review findings into repeated fix-and-check cycles and reports issues that remain after the allowed iterations.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is daytona/clients's own configuration. It tells Claude Code how to work on clients itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clients configures →

not rated 16repo yesterday C scan 104 tokens custom licence
View source ↗ daytona/clients daytona.io
Reuse

Borrowing it

Nothing to install: this file belongs to daytona/clients. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/daytona/clients/main/.claude/skills/cubic-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/daytona/clients

Made for: Claude Code.

Wrote 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.

agentmods badge for cubic-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/daytona/clients/cubic-loop/github.svg)](https://agentmods.dev/skills/daytona/clients/cubic-loop)
Your own site
<a href="https://agentmods.dev/skills/daytona/clients/cubic-loop"><img src="https://agentmods.dev/badge/skills/daytona/clients/cubic-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.

agentmods 80×15 button for cubic-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/daytona/clients/cubic-loop"><img src="https://agentmods.dev/badge/skills/daytona/clients/cubic-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.03308
Opus 5.5 $0.00042 $0.01323
Sonnet 5.5 $0.00021 $0.00662
Haiku 4.5 $0.00010 $0.00331

Measured yesterday against content hash 2ae9994f21dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

cubic-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 yesterday.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://cubic.dev/install | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://cubic.dev/install | bash
.claude/skills/cubic-loop/SKILL.md · 338 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

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.

  1. yesterday First seen · 338 lines · 104 tokens per session scan C 2ae9994f21dd

Subscribe to this mod's changes

cubic-loop is a skill published in the GitHub repository daytona/clients (16 stars, last pushed yesterday), with no licence file. It adds 104 tokens to every session and 3,308 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-05.

Code reviewagentic-workflowaiai-agentsai-runtimeai-sandboxescode-execution
Related

cubic-loop compared with skills from other repositories

cubic-loop next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cubic-loopdaytona/clientsSkill16yesterdaynoneC104Claude Code
agent-code-review-swarmruvnet/rufloSkill81kyesterdayMITA22Claude Code
agent-code-analyzerruvnet/rufloSkill81kyesterdayMITA19Claude Code
revdiffumputun/revdiffSkill945yesterdayMITA250Claude Code
revdiff-planumputun/revdiffSkill945yesterdayMITA84Claude Code
code-review-pipelinea5c-ai/babysitterSkill1.9k5d agoMITA28Claude Code
code-review-patternsa5c-ai/babysitterSkill1.9k5d agoMITA33Claude Code