agentleFS
Sign inStart free
EndikaEndika/eskills/skills/context-budget/SKILL.md

context-budget

Skill0 starsChanged 57 days agoMITView on GitHub

Use when context feels heavy or you've added skills, agents, MCP servers, or memory and want a token-consumption audit of the whole setup with a prioritized trim list.

54 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-payment-x402, openclaw-persona-forge and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TironFoxSkill

    agent-payment-x402

    Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.

    Also in 6 projects that use this

  • TironFoxSkill

    openclaw-persona-forge

    为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。

    Also in 5 projects that use this

  • loulanyueSkill

    nuxt4-patterns

    Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.

    Also in 9 projects that use this

  • renepfSkill

    orch-pipeline

    Shared orchestration engine for the orch-* skill family. Defines the gated Research-Plan-TDD-Review-Commit pipeline, the size classifier, the agent map, and the two human gates that the orch-* operation skills delegate to. Not usually invoked directly.

    Also in 4 projects that use this

  • Exploration-labsSkill

    token-budget-advisor

    Proactive token budget assessment and task chunking strategy. Use this skill when queries involve multiple large file uploads, requests for comprehensive multi-document analysis, complex multi-step workflows with heavy research (10+ tool calls), phrases like "complete analysis", "full audit", "thorough review", "deep dive", or tasks combining extensive research with large output artifacts. This skill helps assess token consumption risk early and recommend chunking strategies before beginning work.

    Also in 11 projects that use this

  • loulanyueSkill

    santa-method

    Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.

    Also in 8 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before adding more — to know if there's headroom.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

context-budget

Overview

Audit what's eating my Claude Code context — skills, MCP servers, the CLAUDE.md chain, and my growing memory — and produce a prioritized list of what to trim. The point is keeping the whole setup lean, not just the pack. It was the first skill past the original 10-skill cap (the make check cap has been raised since, one skill at a time), justified by token economy being a recurring concern.

When to use

  • Context feels heavy / output quality slips, or /context shows a big always-on chunk.
  • I've added skills, agents, or MCP servers, or MEMORY.md keeps growing.
  • Before adding more — to know if there's headroom.

The key model: always-on vs on-demand

  • Always loaded (every turn): skill description lines, MCP tool schemas, the CLAUDE.md chain, and MEMORY.md (the memory index). This is the real budget — trim here first.
  • On-demand (only when invoked): a skill's SKILL.md body, an agent's prompt. Cheap — a long body costs nothing until it runs, so don't optimize bodies.

How it works

1. Inventory

  • Skills: make details (or claude plugin details <plugin>) for the pack's projected token cost; note each description length (always-on).
  • MCP servers: count servers and tools (~500 tokens of schema per tool, always-on). Flag servers with many tools, or that just wrap a CLI I already have (gh, git, supabase).
  • CLAUDE.md + memory: size of the CLAUDE.md chain and MEMORY.md + memory/*.md. The memory index is always-on, so its growth is a direct context tax.
  • Agents: description length (loads on every spawn) and body size.

2. Classify each component

  • Always needed → keep.
  • Sometimes needed (domain-specific, rarely triggered) → lazy-load / disable until used.
  • Rarely needed / redundant / overlapping → remove.

3. Detect the usual bloat

  • Skill/agent description over ~30 words (an always-on tax on every turn).
  • MCP over-subscription (tools I never call, or CLI-wrapper servers).
  • MEMORY.md entries that are stale, duplicated, or no longer true → prune them.
  • CLAUDE.md verbosity that should be a rule or a memory instead.

4. Report

Total always-on overhead, a breakdown by component (skills / MCP / CLAUDE.md / memory / agents), the headroom left, and a prioritized trim list — biggest always-on saving first.

Output

A short report plus the top 3 trims by always-on tokens saved. Act on the always-on items first; on-demand bodies are not the problem.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free