$ ~/registry/skill/affaan-m-context-budget

SKILL

context-budget

Audit Claude Code context usage and get prioritized token-saving recommendations.

Stars

★ 243,958

Source

GitHub

Updated

2026-08-28

// securityLow risk

Prompt only, no code
Open source
Community-trusted· 244.0k

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "context-budget" skill from askskill:
1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/context-budget/SKILL.md
2. Save it as ~/.claude/skills/context-budget/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Inspect context bloat sources

Prompt

Audit context usage in the current Claude Code session across agents, skills, rules, MCP servers, and CLAUDE.md. Summarize estimated tokens by component type and identify the biggest consumers.

Expected

A context budget report with estimated usage by component type and the main sources of bloat.

Generate token-saving recommendations

Prompt

Based on the current setup, find redundant components, bloated descriptions, heavy agents, and excessive MCP tools, then prioritize optimization recommendations by expected token savings.

Expected

A prioritized optimization list describing each issue and the context space that could be reclaimed.

Assess room for more components

Prompt

Estimate the total context overhead and remaining context headroom in the current Claude Code session, then judge whether it is suitable to add more skills or MCP servers.

Expected

An evaluation of remaining context headroom and whether there is room to add more components.

// use cases

Diagnose slow Claude Code sessions

Developers or DevOps users can use it when sessions feel sluggish or output quality drops, auditing loaded components to find which agents, skills, rules, or MCP settings are causing context bloat.

Check capacity before adding components

When a team plans to add new skills, agents, or MCP servers, it can estimate current context headroom and help decide whether there is room to expand further.

Clean up redundant and low-value configuration

If many skills, agents, or rules were recently added, it can identify duplicate content, bloated descriptions, and components better activated on demand to help streamline the setup.

// docs

AI summary

The README describes how Context Budget analyzes token overhead across loaded Claude Code components, including agents, skills, rules, MCP servers, and CLAUDE.md files. It inventories files and configuration, estimates usage, classifies components by necessity, detects issues like bloated descriptions, redundant components, too many MCP tools, and verbose rules, then produces a context budget report with actionable optimization recommendations.

Show full docs ▾

Context Budget

Analyze token overhead across every loaded component in a Claude Code session and surface actionable optimizations to reclaim context space.

When to Use

Session performance feels sluggish or output quality is degrading
You've recently added many skills, agents, or MCP servers
You want to know how much context headroom you actually have
Planning to add more components and need to know if there's room
Running /context-budget command (this skill backs it)

How It Works

Phase 1: Inventory

Scan all component directories and estimate token consumption:

Agents (agents/*.md)

Count lines and tokens per file (words × 1.3)
Extract description frontmatter length
Flag: files >200 lines (heavy), description >30 words (bloated frontmatter)

Skills (skills/*/SKILL.md)

Count tokens per SKILL.md
Flag: files >400 lines
Check for duplicate copies in .agents/skills/ — skip identical copies to avoid double-counting

Rules (rules/**/*.md)

Count tokens per file
Flag: files >100 lines
Detect content overlap between rule files in the same language module

MCP Servers (.mcp.json or active MCP config)

Count configured servers and total tool count
Estimate schema overhead at ~500 tokens per tool
Flag: servers with >20 tools, servers that wrap simple CLI commands (gh, git, npm, supabase, vercel)

CLAUDE.md (project + user-level)

Count tokens per file in the CLAUDE.md chain
Flag: combined total >300 lines

Phase 2: Classify

Sort every component into a bucket:

Bucket	Criteria	Action
Always needed	Referenced in CLAUDE.md, backs an active command, or matches current project type	Keep
Sometimes needed	Domain-specific (e.g. language patterns), not referenced in CLAUDE.md	Consider on-demand activation
Rarely needed	No command reference, overlapping content, or no obvious project match	Remove or lazy-load

Phase 3: Detect Issues

Identify the following problem patterns:

Bloated agent descriptions — description >30 words in frontmatter loads into every Task tool invocation
Heavy agents — files >200 lines inflate Task tool context on every spawn
Redundant components — skills that duplicate agent logic, rules that duplicate CLAUDE.md
MCP over-subscription — >10 servers, or servers wrapping CLI tools available for free
CLAUDE.md bloat — verbose explanations, outdated sections, instructions that should be rules

Phase 4: Report

Produce the context budget report:

Context Budget Report
═══════════════════════════════════════

Total estimated overhead: ~XX,XXX tokens
Context model: Claude Sonnet (200K window)
Effective available context: ~XXX,XXX tokens (XX%)

Component Breakdown:
┌─────────────────┬────────┬───────────┐
│ Component       │ Count  │ Tokens    │
├─────────────────┼────────┼───────────┤
│ Agents          │ N      │ ~X,XXX    │
│ Skills          │ N      │ ~X,XXX    │
│ Rules           │ N      │ ~X,XXX    │
│ MCP tools       │ N      │ ~XX,XXX   │
│ CLAUDE.md       │ N      │ ~X,XXX    │
└─────────────────┴────────┴───────────┘

WARNING: Issues Found (N):
[ranked by token savings]

Top 3 Optimizations:
1. [action] → save ~X,XXX tokens
2. [action] → save ~X,XXX tokens
3. [action] → save ~X,XXX tokens

Potential savings: ~XX,XXX tokens (XX% of current overhead)

In verbose mode, additionally output per-file token counts, line-by-line breakdown of the heaviest files, specific redundant lines between overlapping components, and MCP tool list with per-tool schema size estimates.

Examples

Basic audit

User: /context-budget
Skill: Scans setup → 16 agents (12,400 tokens), 28 skills (6,200), 87 MCP tools (43,500), 2 CLAUDE.md (1,200)
       Flags: 3 heavy agents, 14 MCP servers (3 CLI-replaceable)
       Top saving: remove 3 MCP servers → -27,500 tokens (47% overhead reduction)

Verbose mode

…

View full docs ↗

// FAQ

What does this skill do?

It audits context window consumption in a Claude Code session across loaded components such as agents, skills, rules, MCP servers, and CLAUDE.md, then produces actionable token-saving recommendations.

What does it inspect?

According to the excerpt, it inventories component files and configuration, estimates token overhead, and flags issues such as oversized files, redundant content, too many MCP tools, and CLAUDE.md bloat.

How is it different from a general performance troubleshooting tool?

It focuses on Claude Code context budget rather than system resources or runtime performance. The goal is to find which prompts, rules, and tool configurations consume context window space and prioritize optimizations.