Context Budget
Audits everything loaded into your Claude Code session and tells you where your context budget is going. Scans agents, skills, MCP servers, rules, and CLAUDE.md files, estimates token consumption for each, then ranks savings opportunities. Most useful when you've accumulated a bunch of components and sessions start feeling slow, or before adding more servers when you're not sure if you have headroom. The real insight here is that MCP tools are almost always the biggest culprit at roughly 500 tokens per tool schema, so a single bloated server can cost more than your entire skills directory. Run it after major changes to catch context creep before it becomes a problem.
- skills.sh installs
- 6.1K
- GitHub stars
- 300.3K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add affaan-m/ecc --skill context-budget --agent claude-codeInstalls into .claude/skills of the current project.
Files
Context Budget
Use the provider's native meter for live session usage. Keep the separate, estimated installation audit behind an explicit opt-in.
Default: Live Context
Treat an invocation with no audit request as a live-context request. This includes requests for the current window, remaining capacity, headroom, token usage, or a context breakdown.
For this default path:
- Do not call or use tools.
- Do not scan or read files.
- Do not run shell commands, provider CLIs, debug logging, or MCP discovery.
- Reply with only the native command and one short explanation.
Route by the active harness:
| Harness | Native command | Guidance |
|---|---|---|
| Codex CLI | /status | Shows current token usage and remaining context capacity. Use /statusline and enable Context stats plus Token counters for a persistent footer meter. |
| Codex app | /status | Shows current thread context usage and rate limits. |
| Claude Code | /context | Shows the live context breakdown. Use /context all for expanded items. |
| Other or unknown | None verified | State that ECC cannot read live provider state and ask which harness is active. |
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/affaan-m/ecc
- Category
- AI & Agent Building
- First seen
- Jul 14, 2026
More from affaan-m/ecc
All 263- Accessibility6.1K
- Nestjs Patterns6.1K
- Seo6.1K
- Django Security6.1K
- Git Workflow6K
- Python Testing6K
- Strategic Compact6K
- Design System6K
- Browser Qa6K
- Springboot Security6K
- Search First6K
- Nextjs Turbopack6K
- Brand Voice6K
- Jira Integration6K
- Laravel Tdd6K
- Fastapi Patterns6K
- Remotion Video Creation6K
- React Patterns5.9K
- Perl Security5.9K
- Kotlin Coroutines Flows5.9K
- React Performance5.9K
- Kotlin Patterns5.9K
- Architecture Decision Records5.9K
- Deployment Patterns5.8K
Recommended
More AI & Agent Building
jira-integrationaffaan-m/eccUse this skill when retrieving Jira tickets, analyzing requirements, updating ticket status, adding comments, or transitioning issues. Provides Jira API pattern6Kskills.sh installs
qianwen-textqianwen-ai/qianwen-ai[QianWen] Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate text, 5.9Kskills.sh installs
react-native-best-practicessoftware-mansion-labs/skillsSoftware Mansion's best practices for production React Native and Expo apps on the New Architecture. MUST USE before writing, reviewing, or debugging ANY code i5.9Kskills.sh installsreact-performanceaffaan-m/eccReact and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organi5.9Kskills.sh installsqianwen-model-selectorqianwen-ai/qianwen-ai[QianWen] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capab5.9Kskills.sh installs
ljg-readlijigang/ljg-skillsReading companion agent. Accompanies user through any text (books, articles, essays, papers, news) with translation, structural annotation, deep questioning, an5.8Kskills.sh installs