Skip to content
Agent Orchestration
Skill

/context-budget

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

BOOST
From plugin
loopkit
75553 skills1 agent4 commands2 MCP
Install
$ npx -y skills add Archive228/loopkit --skill context-budget --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/context-budget

Context preview

The summary Claude sees to decide when to auto-load this skill.

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

SKILL.md

context-budget.SKILL.md
name: context-budget
description: Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.
when_to_use: long session, huge file dump, agent forgetting earlier steps, accuracy dropping

Context Budget

More context is not better. Past a threshold, accuracy falls off a cliff (context rot).

  • **Don't dump whole files** — read the relevant function/section, not the 2000-line module.
  • **Summarize, don't accumulate** — replace a 200K-token transcript with a 4K recap of the load-bearing facts.
  • **Drop dead context** — once a sub-task is done, its detail leaves the window. Keep the decision, drop the trace.
  • **State on disk, not in context** — progress goes to a file the next turn re-reads, not into an ever-growing prompt.

A bloated standing context (CLAUDE.md) taxes every single turn. Trim weekly. If the agent is confidently wrong, suspect the context before the model.

Ships withloopkit

33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).

Get the whole plugin

Other skills on loopkit.