context-budget

Included with Lifetime

$97 forever

Analyze and report what is consuming the 200K context window. Use when the user says /context-budget, "what's eating my context", "how much context am I using", or wants to optimize token usage.

General

What this skill does


# Context Budget: Audit Context Window Consumption

**EXECUTE this skill now.** Follow the workflow steps below using the provided $ARGUMENTS. Do NOT describe, summarize, or explain this skill — run it.

## Constants

- `CONTEXT_LIMIT`: 200,000 tokens
- `CLAUDE_DIR`: `C:/Users/gurusharan.gupta/.claude`
- `REGISTRY_DIR`: `C:/Users/gurusharan.gupta/Agents/Claude Code`

## Workflow

### Step 1: Scan Always-Loaded Components

These are loaded in every session:

1. **Global CLAUDE.md** — read `~/.claude/CLAUDE.md`, count words × 1.3
2. **Project CLAUDE.md** — check for CLAUDE.md in the current working directory if present

### Step 2: Scan Installed Skills

List all installed skills and their sizes:
```bash
wc -w ~/.claude/skills/*/SKILL.md 2>/dev/null
```

Note which have `context: fork` (safe — only final output enters main ctx) vs those without (full content enters main ctx on trigger).

### Step 3: Scan MCP Servers

Read `~/.claude/.mcp.json` if it exists. Each active MCP server contributes tool definitions to the context. Estimate 200-500 tokens per MCP server for tool schema overhead.

### Step 4: Scan Memory Files

Check for auto-memory files:
```bash
ls ~/.claude/projects/*/memory/*.md 2>/dev/null | head -20
```
Count words × 1.3 for any that exist.

### Step 5: Scan Active Plugins

List enabled plugins from `~/.claude/settings.json`. Estimate 100-300 tokens per plugin for description overhead.

### Step 6: Produce Report

Output:

```
## Context Budget Report

**Context Limit:** 200,000 tokens

### Always-Loaded Components
| Component | Est. Tokens | Notes |
|-----------|-------------|-------|
| Global CLAUDE.md | <n> | Always loaded |
| Project CLAUDE.md | <n> / N/A | If present |
| Memory files | <n> | Auto-memory entries |
| **Subtotal** | **<n>** | |

### Skills (on-trigger)
| Skill | Est. Tokens | context:fork? | Risk |
|-------|-------------|---------------|------|
| <skill> | <n> | Yes/No | Low/High |
...

### MCP Servers (tool schema overhead)
| Server | Est. Tokens |
|--------|-------------|
| <name> | ~200-500 |
...

### Active Plugins
| Plugin | Est. Tokens |
|--------|-------------|
...

### Summary
- **Always-loaded baseline:** <n> tokens (<n>% of limit)
- **Highest-risk skills (no context:fork):** <list>
- **MCP overhead:** <n> tokens across <count> servers

### Top 3 Optimizations
1. <highest-impact action> — saves ~<n> tokens
2. <second action> — saves ~<n> tokens
3. <third action> — saves ~<n> tokens
```

Files: 1

Size: 2.7 KB

Complexity: 11/100

Category: General

Source: https://github.com/ingpoc/skills/tree/main/context-budget

Related in General

modeling-omnistudio-epc-catalog

Included

Salesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).

Generalscripts

relationship-science-coach

Included

Use this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.

Generalscripts

building-sf-integrations

Included

Salesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).

Generalscripts

venue-templates

Included

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

Generalscripts

let-fate-decide

Included

Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.

Generalscripts

net-ops

Included

Cross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.

Generalscripts