stop-that-shit — скилл для Claude Code и Codex
Скилл stop-that-shit держит агента в границах запроса: режим задачи, ступени Stop Ladder и отказ от перестраховки.
MIT ★ 4 050 обновлён 2026-10-27
/plugin marketplace add lennney/stop-that-shit
/plugin install stop-that-shit@stop-that-shitЧто делает stop-that-shit
Скилл задаёт сессии режим задачи: review, answer и monitor остаются чтением, change разрешает запрошенную работу и то, что из неё следует. Директива ставится первой непустой строкой промпта — в Claude это /stop-that-shit:stop-that-shit change -- Почини падающий тест конфига, в Codex $stop-that-shit change -- Почини падающий тест конфига. Дальше включается Stop Ladder: понять требуемый результат и гарантии, которые нельзя сломать, взять прямое решение из кода проекта или уже установленных зависимостей, расширяться только под названный пробел и закончить, когда штатные проверки подтверждают результат.
Сам скилл ничего не блокирует: он совещательный и поведение модели не гарантирует. Машинные границы дают хуки Guard, а они стартуют в режиме наблюдения unconfirmed — пока режим не включён явно, отказов от хоста не будет.
Служебные директивы status, runtime, explain evt_... и label evt_... correct|incorrect|inconclusive контракт задачи не меняют. Замок на файлы прописывается целиком: lock change files=src/config.cjs|test/config.test.cjs.
Какие задачи решает
- остановить расползание задачи, когда агент трогает лишние файлы
- решить, нужна ли ещё одна проверка или это перестраховка
- выйти из цикла повторной верификации одного и того же изменения
- зафиксировать список файлов, которые разрешено менять
- отделить чтение и ревью от правок кода
Примеры запросов агенту
- /stop-that-shit:stop-that-shit change -- Почини падающий тест конфига, другие файлы не трогай
- /stop-that-shit:stop-that-shit review -- Посмотри диф и перечисли находки, ничего не правь
- /stop-that-shit:stop-that-shit lock change files=src/config.cjs|test/config.test.cjs -- Починить это поведение
Как установить stop-that-shit
1Через маркетплейс плагинов
/plugin marketplace add lennney/stop-that-shit/plugin install stop-that-shit@stop-that-shitКоманда ставит плагин stop-that-shit целиком, со всеми его скиллами
2Через Skills CLI (Vercel)
npx skills add lennney/stop-that-shit --skill stop-that-shit -a claude-code3Вручную: положить файлы
~/.claude/skills/stop-that-shit/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/stop-that-shit/
1Через Skills CLI (Vercel)
npx skills add lennney/stop-that-shit --skill stop-that-shit -a codex2Вручную: положить файлы
.agents/skills/stop-that-shit/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add lennney/stop-that-shit --skill stop-that-shit -a cursor2Вручную: положить файлы
.cursor/skills/stop-that-shit/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install lennney/stop-that-shit codex-plugin/skills/stop-that-shit2Вручную: положить файлы
.github/skills/stop-that-shit/SKILL.md1Через Skills CLI (Vercel)
npx skills add lennney/stop-that-shit --skill stop-that-shit -a gemini-cli2Командой платформы
gemini skills install https://github.com/lennney/stop-that-shit --path codex-plugin/skills/stop-that-shitВручную: положить файлы
.devin/skills/stop-that-shit/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Claude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о stop-that-shit
Как установить stop-that-shit в Claude Code?
Подключите маркетплейс командой /plugin marketplace add lennney/stop-that-shit, затем поставьте плагин: /plugin install stop-that-shit@stop-that-shit.
Что делает stop-that-shit?
Держит агента в рамках запроса: включает режим задачи, ведёт по ступеням Stop Ladder и требует заканчивать, когда результат есть и проверки его подтверждают.
Обязательно ли ставить Guard, чтобы скилл работал?
Нет. Скилл работает и без хуков, но тогда это только указания. Guard добавляет машинные границы на поддерживаемых путях действий хоста и начинает с режима наблюдения unconfirmed.
Исходный текст
SKILL.md · MIT
--- name: stop-that-shit description: Complete requested work while preventing speculative defenses and scope creep. Use when considering extra hardening, reviewing possible overengineering, resolving repeated verification loops, following explicit task boundaries, or when the user invokes Stop That Shit. Ordinary use of validation, retries, or dependencies alone is not a trigger. license: MIT --- # Stop That Shit Meet the task's responsibilities in full. Let real needs drive complexity. This Skill is advisory and works without the Guard hooks. It cannot guarantee model behavior. When the Guard is installed, the same directives also provide machine-enforced boundaries on supported host action paths. ## Follow the Stop Ladder Apply this ladder when choosing an implementation, adding a mechanism, or extending verification. These are engineering decisions within normal work; they do not require a new checklist, proof file, or reviewing agent. 1. **Understand the current responsibility.** Establish the requested result, explicit boundaries, and existing guarantees the change must preserve. Use the request, later corrections, project requirements, and relevant code. Trace affected callers and failure paths before choosing a fix. Complete necessary caller, data, test, and documentation changes within that authority. A plan or an easier subset does not fulfill the requested result. 2. **Start with a direct solution.** Check suitable code already in the project, standard-library or platform features, and installed dependencies. Compare actual behavior, failure handling, and state lifetime. Proceed when a clear, maintainable option satisfies the responsibility; do not exhaust the ecosystem. 3. **Expand to close a concrete gap.** Identify the supported input, consumer, failure, or obligation the direct solution does not cover. Adapt or implement that missing behavior at the responsible layer. Existing support commitments count as current needs; hypothetical future flexibility alone does not. A larger diff is justified when it completes the affected flow. 4. **Judge defenses by their effect.** Identify what a mechanism detects and what its rejection, recovery, or diagnosis changes. Keep effective protection. Omit optional additions without a grounded purpose or additional value. Within the task scope, remove or narrow work shown to be redundant, unused, or too broad. Repair defenses that hide failures, duplicate side effects, or prevent legitimate work, even when the repair adds code. 5. **Verify the result and finish.** Use the project's intended checks for the affected behavior and guarantees. Honor explicit acceptance criteria and mandatory checks. Reuse evidence while it remains valid for the final state. Finish when the requested result exists, the required evidence supports it, and no known in-scope blocker remains. ## Resolve uncertainty without inventing work A supported trust boundary, failure mode, existing data, or applicable obligation can establish a need before an incident occurs. Preserve necessary validation, authentication, authorization, data integrity, recovery, compatibility, migration, and accessibility. Mechanism names and line counts do not determine whether protection is useful. New optional work without a purpose can wait. An existing protection whose role is unclear needs inspection of the relevant path before removal. Missing evidence is not proof that it is unnecessary. Adding a verifier solely to read a new optional manifest does not establish their value; trace the chain back to a task requirement or an existing guarantee. For example, a release consumer can make a checksum necessary. A TTL requirement can require more than an available cache provides. A catch that turns a failed read into a successful empty result can require repair. Choose from the actual contract and behavior in each case. Resolve ordinary choices from available context. Ask only for missing information that cannot be resolved from context and would materially change the result, authorization, or a choice that is hard to reverse. Do not request authorization already given. Wait for an operation before retrying it or starting work that depends on it. If a necessary check is blocked, repair the specific cause when feasible within the task and continue independent necessary work. Change methods when they can resolve the gap; an unrelated successful command cannot replace the missing evidence. Report an unresolved blocker accurately without claiming completion. ## Keep the deliverable focused Report the result and relevant verification. Include a tradeoff, warning, or limitation when requested or when it changes how the reader should interpret or use the result. Put required disclosure at the decision point. Keep internal process notes and unrequested cautionary prose out of the product; narrow or attribute uncertain claims instead of surrounding them with disclaimers. ## Respect the task mode - `review`, `answer`, and `monitor` are read-only unless the user authorizes a change. - `change` permits only requested work and necessary consequences. - Necessary work does not override an explicit file lock or a narrower action boundary. Explain a required boundary change before acting outside it. With Skill only, treat the mode as an instruction. With the Guard installed, use the host-native invocation form. Claude Code plugin: ```text /stop-that-shit:stop-that-shit change -- Fix the failing config test. /stop-that-shit:stop-that-shit review -- Review this diff. Report findings; do not edit. ``` Codex plugin or host-neutral directive at the start of a prompt: ```text $stop-that-shit change -- Fix the failing config test. $stop-that-shit review -- Review this diff. Report findings; do not edit. ``` Submit one directive on the first non-empty line, outside quotes and code blocks. Put task text after `--`, `: `, or a newline. Embedded examples do not set directive fields. Unknown fields or conflicting values leave the previous contract unchanged and require a corrected directive. An installed Guard begins in observation-only `unconfirmed` mode. Do not claim that an action was blocked unless an explicit mode armed the Guard and the Guard returned a host-specific denial. Even then, describe the host effect as unobserved. The following inspection commands do not change the current task contract. In Claude Code, pass the text after the namespaced slash command; in Codex, use the `$stop-that-shit` form shown below. ```text $stop-that-shit status $stop-that-shit runtime $stop-that-shit explain evt_... $stop-that-shit label evt_... correct|incorrect|inconclusive ``` Use a hard file lock only when the complete boundary is already known: ```text $stop-that-shit lock change files=src/config.cjs|test/config.test.cjs -- Fix this behavior. ``` The active delegation limit is a session control: ```text $stop-that-shit change agents=N -- Run the task. ``` `agents=N` limits reserved concurrent capacity. It defaults to unlimited, and `0` forbids new delegation. A batch that exceeds the limit is rejected atomically. Request parameters do not prove completion: the host must confirm that a call did not execute, joined all its children, or ended an associated run. Unknown results keep their existing capacity; session-end alone does not prove completion. Permitted unbounded or unversioned resume calls remain unresolved until matching terminal evidence arrives. With unresolved activity, finite Guard requires that evidence or a new host session. Migration preserves valid budgets including `0`. Lifecycle association uses explicit host identities, never event arrival order. Claude Code equivalent: ```text /stop-that-shit:stop-that-shit lock change files=src/config.cjs|test/config.test.cjs -- Fix this behavior. ``` Do not invent a file list to appear precise. Inspect proportionately and explain material expansion before acting. ## Finish Report the requested result, necessary consequences, and the evidence that makes the task complete. Do not add a final audit loop only to satisfy this Skill.
© Stop That Shit contributors · MIT · lennney/stop-that-shit