Skip to content
Agentmart
Submit a tool

context-budget

Token and context budget audit for agents, skills, rules, and MCP overhead.

Skill by JunMystery

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/junmystery-context-budget

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Token and context budget audit for agents, skills, rules, and MCP overhead. Use when sessions feel bloated or repeated references are wasting context.

Use cases: security, finance, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/context-budget

What's inside

Skill name
context-budget
Description
Token and context budget audit for agents, skills, rules, and MCP overhead. Use when sessions feel bloated or repeated references are wasting context.
License
MIT
Instructions
27 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Context Budget

Use this skill to reduce wasted context and identify bloat.

## Trigger

- Session quality degrades as context grows
- More agents, skills, or rules were added recently
- You want to know what should remain on-demand

## What to Apply

- Prefer on-demand load over always-loaded instructions.
- Identify overlapping docs and duplicate guidance.
- Keep root instruction files short.
- Move specialized guidance into task-specific files.

## Reference Files

- [SKILL-REFERENCE.md](../../SKILL-REFERENCE.md)
- [README.md](../../README.md)
- [ai-agent-standards/INDEX.md](../../ai-agent-standards/INDEX.md)

## Output Expectation

Report the biggest token savings first and separate always-loaded from on-demand content.

From JunMystery/AI-Agent-Standards, MIT.

More from JunMystery/AI-Agent-Standards

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 24, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/JunMystery/AI-Agent-Standards
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from JunMystery

Cite this page

context-budget skill. Agent Mart. https://agentmart.dev/skills/junmystery-context-budget (last updated 2026-10-24)