Hacktoberfest 2026: los issues que los mantenedores marcaron para octubre, abiertos y aptos para principiantes. Explorar issues de Hacktoberfest

perf: cut what reaches the orchestrator's context across plugin skills, hooks and agents

Abierto
  • ¿Algo no está bien?
#6,322 1 comentario 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 1 día

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
5/5
Tiempo estimado
Más de una semana
Aptitud para principiantes
22/100
Tipo de issue
Refactorización
Claridad
Bastante claro
Estado de actividad
Activo
Stack tecnológico
shell
Área
ai-infra-agents, performance, tooling

Línea de trabajo

This is a scan-and-cut program, not one patch: walk plugin orchestration paths for skills, hooks, agents, handoff/compaction/resume. Compare against the listed patterns (long skill bodies, verbose subagent returns like discovery:research’s file-pointer-plus-summary, per-turn hook text from context-guard and rate-limit-guard, large command output). Measure with /context-budget:audit and /harness-ops:observability plus session transcripts; file each concrete cut separately. Related: issue #6316 and the forthcoming context-guard 128K/250K band PR.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

needs-human needs-triage

Problem

Current long-context data says an orchestrating session degrades well before its window fills. Claude Opus 5 holds 91.3% on Context Arena's 8-needle MRCR at 128K but averages 45.7% across the full 1M window (https://contextarena.ai/?needles=8, fetched 2026-10-04). Practitioners put the start of degradation at about 125-150K tokens whatever the window size (Matt Pocock's AI Hero smart-zone entry, Geoffrey Huntley). context-guard now ships 128K/250K token bands on 1M windows to match.

An orchestrator that reads verbose output, re-reads large skill bodies or files, or relays subagent transcripts reaches those edges early and has to hand off or compact. Subagents and workflow agents are fine to use: each has its own window. The orchestrator's window is the scarce one.

Ask

Scan the plugins' orchestration paths and cut what reaches the orchestrator's context:

  • Skills that load long bodies or reference files the orchestrating session does not act on (progressive disclosure, smaller hubs).
  • Skills and agents whose subagent returns are verbose; they should return a file pointer plus a short summary, as discovery:research does.
  • Hook and mod text sent to the model on every turn or tool call (context-guard, rate-limit-guard, others): only what Claude acts on, in the fewest tokens.
  • Commands in skill bodies whose output is large (logs, diffs, listings) where a filter, a count or a subagent would do.
  • Handoff, compaction and resume flows that re-load more than the next step needs.

Measure before and after (/context-budget:audit, /harness-ops:observability, session transcripts), and file each concrete cut as its own change.

Related

  • #6316 (rate-limit and context-guard defaults)
  • The context-guard 128K/250K band change (PR to follow)

🤖 Generated with Claude Code

Lenguaje dominante
Shell
Estrellas
22
Forks
2
Merge medio
5 h 11 min
PR fusionados (30 d)
838

Preparar el entorno

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de melodic-software/claude-code-plugins

Todos los issues de melodic-software/claude-code-plugins

Issues similares

Más issues de Shell/Bash

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.