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.
curl -O https://raw.githubusercontent.com/B-A-M-N/Kontrol/main/.codex/skills/nelson-wiggum-loop/SKILL.mdgit clone --depth 1 https://github.com/B-A-M-N/KontrolWrote 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/b-a-m-n/kontrol/nelson-wiggum-loop)<a href="https://agentmods.dev/skills/b-a-m-n/kontrol/nelson-wiggum-loop"><img src="https://agentmods.dev/badge/skills/b-a-m-n/kontrol/nelson-wiggum-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/b-a-m-n/kontrol/nelson-wiggum-loop"><img src="https://agentmods.dev/badge/skills/b-a-m-n/kontrol/nelson-wiggum-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 | $0.00028 | $0.01617 |
| Opus 5 | $0.00014 | $0.00809 |
| Sonnet 5 | $0.00006 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00162 |
Grade A, and why
nelson-wiggum-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 3d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nelson Wiggum Loop
"A-okay!" — Nelson Wiggum, the only voice that ends the loop.
The WebUI-side counterpart to ralphie-muntz-loop. The active WebUI model is
the reviewer, orchestrator, and inspector. The CLI coding agent is an optional
bounded worker. The loop is not complete until the WebUI signs off "A-okay"
via provide_review_feedback with verdict approve.
No polling. No busy loops. The WebUI's "A-okay" is the single completion criterion.
Topology (registry roles)
The agent registry makes the split explicit:
| Name | Role | Meaning |
|---|---|---|
cli-coding-agent |
agent |
The worker. Registers itself at runtime via POST /acp/agents/register. Executes tasks, submits work for review. |
webui |
reviewer |
The reviewer. Seeded by Kontrol as a well-known reviewer entry and the only signer of "A-okay". |
Kontrol is the broker that hosts the WebUI's reviewer tool
(submit_to_coding_agent) and the WebUI-facing ACP agent
(kontrol-submit-work-to-webui).
The Pattern
WebUI (Nelson) Kontrol Server CLI Coding Agent (Ralphie)
│ │ │
├─ submit_to_coding_agent ──────────►│ │
│ (task from the human) ├─ forward over ACP ─────────────►│
│ │ ├─ start_work_session
│ │ ├─ [do work: edit, shell, test]
│ │◄─ submit_for_review ───────────┤
│ │ (or kontrol-submit-work-to-webui via ACP) │
│ ├─ status: awaiting_review │
│◄── diff card + feedback form ──────┤ │
│ │ ├─ await_review_feedback (BLOCKS)
│ │ │
│ human reviews, clicks A-okay ───►├─ provide_review_feedback │
│ (verdict: approve) ├─ feedback committed │
│ ├─ waiter resolved ──────────────►│
│ │ ├─ finish, summarize
│ │ │
├── COMPLETION: only when WebUI says "A-okay" ────────────────────────┤
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.
- 3d ago Changed · +1 lines · -61 tokens per session a42f32694dd3
- 10d ago First seen · 154 lines · 89 tokens per session scan A 146e4b527a04
nelson-wiggum-loop is a skill published in the GitHub repository B-A-M-N/Kontrol (0 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 1,617 once invoked, about $0.0001 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
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…