Kontrol: Skill for Codex

.codex/skills/ralphie-muntz-loop/SKILL.md

ralphie-muntz-loop is a skill for Codex from B-A-M-N/Kontrol. It costs 63 tokens per session (1,456 once invoked), scanned A, original, MIT.

An event-driven review workflow for Kontrol ACP, where a coding agent submits work to a web interface and waits until a person sends feedback. ACP refers to the work-session system used by Kontrol.

In plain words
What is it for?
It helps agents submit changes, pause during human review, and continue when a review decision or feedback arrives.
Why use it?
It removes repeated status checks and timer-based polling while the agent is waiting for review.

Skill for Codex

Written for Codex: installed under .codex/.

This is B-A-M-N/Kontrol's own configuration. It tells Codex how to work on Kontrol 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 Kontrol configures →

Reuse

Borrowing it

Nothing to install: this file belongs to B-A-M-N/Kontrol. 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/B-A-M-N/Kontrol/main/.codex/skills/ralphie-muntz-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/B-A-M-N/Kontrol

Made for: Codex.

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 ralphie-muntz-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/b-a-m-n/kontrol/ralphie-muntz-loop/github.svg)](https://agentmods.dev/skills/b-a-m-n/kontrol/ralphie-muntz-loop)
Your own site
<a href="https://agentmods.dev/skills/b-a-m-n/kontrol/ralphie-muntz-loop"><img src="https://agentmods.dev/badge/skills/b-a-m-n/kontrol/ralphie-muntz-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 ralphie-muntz-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/b-a-m-n/kontrol/ralphie-muntz-loop"><img src="https://agentmods.dev/badge/skills/b-a-m-n/kontrol/ralphie-muntz-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.00063 $0.01456
Opus 5 $0.00032 $0.00728
Sonnet 5 $0.00013 $0.00291
Haiku 4.5 $0.00006 $0.00146

Measured 4d ago against content hash ff9c3352f692, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ralphie-muntz-loop 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 4d 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.

.codex/skills/ralphie-muntz-loop/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralphie Muntz Loop

"I'm learnin'!" — Ralphie Muntz, until Nelson says not to anymore.

Event-driven review rendezvous pattern for Kontrol's ACP. The CLI agent submits work to WebUI, the MCP tool call blocks server-side until the human reviews and commits feedback, then the agent continues with the verdict.

No polling. No busy loops. No 30-second timers.

The Pattern

CLI Agent                          Kontrol Server                    WebUI (Human)
    │                                    │                                │
    ├─ start_work_session ──────────────►│                                │
    ├─ [do work: edit, write, shell]     │                                │
    ├─ submit_for_review ───────────────►│                                │
    │   (workspace checkpoint captured) ├─ status: awaiting_review        │
    │                                    │                                │
    ├─ await_review_feedback ───────────►│  ← MCP call BLOCKS here        │
    │   (agent is parked)               │    (Promise, not polling)       │
    │                                    │                                │
    │                                    │         ◄── human reviews ─────┤
    │                                    │         ◄── clicks verdict ────┤
    │                                    │                                │
    │                                    ├─ feedback committed to DB      │
    │                                    ├─ ReviewWaiter.publish()        │
    │                                    ├─ waiter resolved               │
    │◄── feedback returned ──────────────│  ← MCP call UNBLOCKS           │
    │                                    │                                │
    ├─ if changes_requested:            │                                │
    │   read comments, apply fixes      │                                │
    │   submit_for_review ──────────────►│                                │
    │   await_review_feedback ──────────►│                                │
    │                                    │                                │
    ├─ if approved:                     │                                │
    │   finish, summarize               │                                │
    │                                    │                                │
    ├─ if rejected:                     │                                │
    │   stop                            │                                │

Read the full file on GitHub · 169 lines

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. 4d ago Changed ff9c3352f692
  2. 10d ago First seen · 169 lines · 63 tokens per session scan A 83f0b0951faa

Subscribe to this mod's changes

ralphie-muntz-loop is a skill published in the GitHub repository B-A-M-N/Kontrol (0 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 1,456 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens