Agent skill

Claude Md Budget

by jgravelle in jgravelle/jcodemunch-mcp

How to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation.

Custom licenceAuto-check passedAgent Workflows

Install Claude Md Budget

skills CLI
$ npx skills add jgravelle/jcodemunch-mcp --skill claude-md-budget -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jgravelle/jcodemunch-mcp claude-md-budget --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jgravelle/jcodemunch-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/claude-md-budget .claude/skills/claude-md-budget && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
claude-md-budget
GitHub stars
2.8k
Token cost
~426 tokens
SKILL.md length
191 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Custom licence

At a glance

How to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation.

  • Works in 6 steps: Measure sections by heading and sort by… → A rotation is TWO edits: the release… → What is derivable leaves, what is not… → …
  • Tasks that involve Agent instruction files
  • Calls git

What it does

Claude Md Budget is an agent skill from jgravelle/jcodemunch-mcp. How to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation. Load in /release step 6 and before any CLAUDE.md rotation or split.

Its SKILL.md is about 430 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. It works with Model Context Protocol. The repository describes itself as: Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP…

When your agent uses it

  • Tasks that involve Agent instruction files

Example prompts

  • “/claude-md-budget”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Measure sections by heading and sort by size BEFORE choosing what
  2. A rotation is TWO edits: the release moves out of Current State AND
  3. What is derivable leaves, what is not stays: a description
  4. Rotated text goes to ISSUE-HISTORY.md verbatim; ask what lesson
  5. The target must be tracked: git check-ignore the path before
  6. Never raise the Floor to make room; never delete a warning-marked rule.

What it can do on your machine

Read from SKILL.md and the folder at commit 970c457. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claude Md Budget loads about 426 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 191 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~426

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 191 words (~426 tokens).

“Authority: CLAUDE.md Maintenance Practice 5 (the rules), ISSUE-HISTORY.md § "Practice 5 forensics (rotated 2026-09-26)" (the measurements behind them), tests/test_claude_md_size.py, tests/test_claude_md_rotation.py, tests/test_key_files_split.py, tests/test_cli_env_split.py; the Floor is claude_md.max_chars (uv run python -m harness check claude_md.max_chars).”

— opening of SKILL.md by jgravelle, Custom licence
name
claude-md-budget

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/claude-md-budget of jgravelle/jcodemunch-mcp.

Open the folder on GitHubat commit 970c457

Compare with similar skills

Claude Md Budget next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Claude Md Budget compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Md Budget this skilljgravelle/jcodemunch-mcp2.8k—~426Automated safety check: PassCustom licence
Agent Setup Health Audittw93/Waza7.2k—~5.2kAutomated safety check: NotesMIT
Semantix GuideGnosil/semantix821—~2.1kAutomated safety check: PassMIT
Working With Claude Code Docsobra/superpowers-developing-for-claude-code142—~1.5kAutomated safety check: PassNone
Agnixagent-sh/agnix445—~874Automated safety check: PassApache-2.0
Claude Docs Consultantcentminmod/my-claude-code-setup2.7k—~959Automated safety check: PassMIT

Similar skills

  • Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.

    7.2k GitHub stars~5.2k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Semantix Guide

    Gnosil/semantix

    Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project…

    821 GitHub stars~2.1k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Working With Claude Code Docs

    obra/superpowers-developing-for-claude-code

    Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.

    142 GitHub stars~1.5k tokensUpdated 10 mo ago
    Agent WorkflowsAuto-check passed
  • Agnix

    agent-sh/agnix

    A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.

    445 GitHub stars~874 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Claude Docs Consultant

    centminmod/my-claude-code-setup

    Consult official Claude Code documentation from code.claude.com using selective fetching.

    2.7k GitHub stars~959 tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Clawmem

    yoloshii/ClawMem

    ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring…

    210 GitHub stars~7.5k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from jgravelle/jcodemunch-mcp

All 10 skills in this repo
  • Release

    jgravelle/jcodemunch-mcp

    Publishing a jMunch release (jcodemunch-mcp, jdocmunch-mcp, jdatamunch-mcp, jragmunch-cli), reviewing/merging/closing PRs, and responding to the community.

    2.8k GitHub stars~6.5k tokensUpdated today
    Auto-check passed
  • Benchmark Methodology

    jgravelle/jcodemunch-mcp

    Rules for measuring or quoting any benchmark number in this repo.

    2.8k GitHub stars~438 tokensUpdated today
    Auto-check passed
  • Observatory

    jgravelle/jcodemunch-mcp

    Context for the jcodemunch-observatory weekly scorecard — what it tracks, the Monday 06:00 UTC cron, why scores must be pulled live rather than transcribed, the NestJS grade story, and the…

    2.8k GitHub stars~782 tokensUpdated today
    Auto-check passed
  • PR Description

    jgravelle/jcodemunch-mcp

    The PR title and body template, and the rules for any comment drafted for a reporter or contributor.

    2.8k GitHub stars~409 tokensUpdated today
    Auto-check passed
  • Changelog Format

    jgravelle/jcodemunch-mcp

    The shape of a CHANGELOG.md entry and heading in this repo. An agent skill from jgravelle/jcodemunch-mcp.

    2.8k GitHub stars~320 tokensUpdated today
    Auto-check passed
  • Mechanism Not Instance

    jgravelle/jcodemunch-mcp

    The two questions that separate a fix for the reported spelling from a fix for the property.

    2.8k GitHub stars~332 tokensUpdated today
    Auto-check passed

Categories

Questions about Claude Md Budget

What does Claude Md Budget do?

How to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation. Claude Md Budget is an agent skill from jgravelle/jcodemunch-mcp.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation.

When should I use Claude Md Budget?

Claude Md Budget fits situations like: tasks that involve Agent instruction files.

How do I install Claude Md Budget in Claude Code?

Run `npx skills add jgravelle/jcodemunch-mcp --skill claude-md-budget -a claude-code`. Or copy the skill folder (.claude/skills/claude-md-budget in jgravelle/jcodemunch-mcp) into .claude/skills/claude-md-budget in your project. Claude Code loads it when a task matches its description.

How do I install Claude Md Budget in Codex?

Run `npx skills add jgravelle/jcodemunch-mcp --skill claude-md-budget -a codex`. Or copy the skill folder (.claude/skills/claude-md-budget in jgravelle/jcodemunch-mcp) into .agents/skills/claude-md-budget in your project. Codex loads it when a task matches its description.

Can I use Claude Md Budget in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jgravelle/jcodemunch-mcp --skill claude-md-budget -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-md-budget, .gemini/skills/claude-md-budget, .github/skills/claude-md-budget and .opencode/skills/claude-md-budget in your project.

What does Claude Md Budget need to run?

Going by SKILL.md and its folder, Claude Md Budget needs the command-line tools its instructions call (git). Our summary lists: Python 3.

Does Claude Md Budget access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Claude Md Budget safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Claude Md Budget use?

Claude Md Budget has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Claude Md Budget use?

About 426 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claude Md Budget?

Skills that share tags, products or a category with Claude Md Budget: Agent Setup Health Audit (tw93/Waza, 7.2k stars), Semantix Guide (Gnosil/semantix, 821 stars), Working With Claude Code Docs (obra/superpowers-developing-for-claude-code, 142 stars) and Agnix (agent-sh/agnix, 445 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Md Budget?

jgravelle (a GitHub user) maintains it in jgravelle/jcodemunch-mcp, which has 2,754 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 11, 2026.

Source: jgravelle/jcodemunch-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.