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 agentmods add agents/andrewcigan/vibe-dev-plugin/stuck-protocol-handlergit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWhat 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 | $0.00060 | $0.01583 |
| Opus 5 | $0.00030 | $0.00792 |
| Sonnet 5 | $0.00012 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00158 |
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.
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.
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.
- 2d ago First seen · 185 lines · 60 tokens per session scan A 64546dea747a
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.
Other agents, from other repositories
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).
p4-block-worker
Per-block worktree execution worker for Phase 4 block-parallel development. Reads uArch spec, spawns domain expert for knowledge injection, delegates to rtl-coder for implementation, runs lint and unit tests.
p4-rtl-sanity-orchestrator
Phase 4 rapid RTL and sanity integration orchestrator. Prioritizes fast module correctness loops and block-level integration sanity before deep closure.