convez.ai
AgenteAutomaçãoIntermediário
fr1j0

bonk — Pattern-Interrupt para Claude Code

fr1j0/bonk

Interrompe loops ruins, audita contexto e reinicia limpo

Ver no GitHub
BomPluginScore · de 0 a 100

Agent que interrompe caminhos errados do Claude Code, audita assunções viciadas e reinicia a partir de um contexto limpo. Resolve o problema real: contexto poluído que o agente mantém reiterando. Ideal para longas sessões de coding onde o modelo se prende a decisões ruins anteriores.

Instalação

$npx convez-ai fr1j0/bonk

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
85%
Último commit
há 4 meses
Versão
v0.5.0
Issues abertas
2
Contribuidores
1

Casos de uso

  • Parar execução errada em sessões longas de Claude Code
  • Auditar assunções viciadas antes de reiniciar
  • Resetar contexto sem perder progresso de edições

Veredito

bonk é uma ferramenta cirúrgica para quem trabalha com Claude Code em projetos complexos. Resolve um problema real: contexto poluído que gera loops de más decisões. Requer disciplina no workflow (Esc + /bonk:it), mas economiza tempo em sessões longas.

README

A tradução para o português deste README ainda está na fila.


When the agent commits to a wrong path and keeps compounding it — defending the bad approach turn after turn — bonk halts it, audits what it's actually assuming, and (when the context is too far gone) restarts from a clean, verified problem statement re-derived by a fresh-context subagent.

The real problem usually isn't the model's reasoning — it's the polluted context it keeps conditioning on (stale assumptions, dead ends, its own prior commitments). bonk is about re-grounding that context, not scolding the model.

Install

In Claude Code:

/plugin marketplace add fr1j0/bonk
/plugin install bonk@bonk

Then use /bonk:it and /bonk:resume.

Usage ritual

bonk runs after you've stopped the agent (a slash command can't interrupt a running turn — only Esc can):

Esc            # stop the wrong-path execution immediately
(Esc Esc       # optional: rewind to undo bad edits
 or /rewind)
/bonk:it [hint] # re-ground on the clean state

Note: /rewind only undoes edits made by Claude's edit tools — not bash side-effects (rm/mv/generated files), which need git.

Note: run /bonk:it and /bonk:resume in the same project. The clean brief is saved under the repo root's .bonk/ (resolved via git, so any subdirectory of the repo works), but resuming from a different repo — or outside any repo, where it anchors to the working directory — won't find it.

Commands

  • /bonk:it [optional hint] — emits a Drift check report: what triggered it, a plain-language verdict (start over or keep going), the load-bearing assumptions ranked by confidence, and the context it's working from. On start over, a fresh-context subagent re-derives the approach blind to the bad turns; you approve, and it persists a clean brief.
  • /bonk:resume — after you /clear, rehydrates the clean brief into the fresh context and continues from the corrected approach.

Want to see the report format? Run bash plugins/bonk/scripts/preview-report.sh for a rendered sample.

Status

v0.4.1 shipped. See the design spec for the full design and the plan for how it was built; the report-format redesign covers the current Drift-check report.

Ver o original no GitHub

Bom para

Relacionados