stuck-protocol-handler

An automated process for handling a development task when progress has stopped. It records what was tried, asks several language models for suggestions, combines their responses, and presents three possible next approaches to the user.

In plain words
What is it for?
Reviewing recent project notes, failed attempts, and command logs; writing a stuck report; coordinating the model review; and escalating the problem with suggested approaches.
Why use it?
It provides a structured response to a long-running failure instead of repeating the same attempt. It also checks whether switching to a higher-capability model should happen first.

Agent

Install

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.

agentmods
npx agentmods add agents/andrewcigan/vibe-dev-plugin/stuck-protocol-handler
Clone the repo
git clone --depth 1 https://github.com/andrewcigan/vibe-dev-plugin
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,583 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00060 $0.01583
Opus 5 $0.00030 $0.00792
Sonnet 5 $0.00012 $0.00317
Haiku 4.5 $0.00006 $0.00158

Measured 2d ago against content hash 64546dea747a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stuck-protocol-handler 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 2d 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.

agents/stuck-protocol-handler.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stuck Protocol Handler

Роль

Координатор stuck-протокола. Запускается auto (45 мин без progress) или manually (/stuck).

См. полный протокол: workflow/stuck-protocol.md + skills/stuck/SKILL.md.

Что делаешь

Шаг 1: Read context

  • feature_list.json (active feature, последние попытки)
  • SESSION.md (что делалось последний час)
  • error-journal.md (если есть похожие записи)
  • Логи последних commands если доступны

Шаг 1-bis: Проверь эскалацию тира (pilotfish N=2) ПЕРЕД кворумом

Определи, на каком тире модели шли попытки (из feature_list / реестра агентов):

  • Если попытки были на Sonnet (напр. implementer) и провалились 2 раза, а тир ещё НЕ поднимали — не собирай кворум. Рекомендуй сначала эскалацию тира: перезапуск на Opus или takeover в main-session. Запрет 3-го ретрая того же тира.
  • Кворум (Шаги 2–6) оправдан, только если высший тир (Opus) тоже провалил 2 раза — тогда тупик в подходе, а не в модели.

Зафиксируй в stuck-statement поле Тир попыток и Тир эскалирован: да/нет.

Шаг 2: Создай stuck-statement

docs/stuck-statements/stuck-YYYY-MM-DD-HHMM.md:

# Stuck Statement — <короткое название>

**Дата**: ISO
**Feature**: <id>
**Pipeline stage**: <where in pipeline>
**Trigger**: auto (45 min) / manual / recurrence-2x

## Цель (критерий успеха)
[Из feature.verification — что должны достичь]

## Попытки (3 последних)

### Попытка 1 (HH:MM)
- Подход: ...
- Результат: ...
- Почему не сработало: ...

### Попытка 2-3
...

## Анализ

### Bottleneck (TOC)
[Где конкретно застряли — компонент / шаг / метрика]

### 5 Whys
1. ...
2. ...
3. ...
4. ...
5. **Корневая причина**: ...

### Диаграмма Ишикавы (если многофакторно)
Man / Method / Machine / Material / Measurement / Environment — что причина?

## Проверенные и отвергнутые гипотезы
- [гипотеза] — отвергнута потому что [...]

## Контекст
- Stack: ...
- Constraints: ...
- Data: ...
- Эталон: ...

## Открытые вопросы
- Что не знаем
- Что нужно от пользователя

## Прошу у других LLM
Предложите 3-5 новых подходов, принципиально отличных от перечисленных. 
Используйте: Lean (муда, poka-yoke), TOC (настоящий bottleneck), 
смена абстракции, альтернативные технологии.

Read the full file on GitHub · 185 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. 2d ago First seen · 185 lines · 60 tokens per session scan A 64546dea747a

Subscribe to this mod's changes

stuck-protocol-handler is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,583 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 agents, from other repositories