Skip to content
Agentmart
Submit a tool

agentmd-optimizer

Scan the entire machine for CLAUDE.md, AGENTS.md, GEMINI.md, and other agent instruction files, then analyze them for token bloat, redundancy, staleness…

Skill by ildunari

IndexedLicense unknown
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/ildunari-agentmd-optimizer

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

Scan the entire machine for CLAUDE.md, AGENTS.md, GEMINI.md, and other agent instruction files, then analyze them for token bloat, redundancy, staleness, hierarchy conflicts, and drift. Produces a token-saving manifest with per-file recommendations and orchestrates sub-agent cleanup using cheap models as workforce. Use this skill whenever the user mentions optimizing instructions, reducing context tokens, cleaning up CLAUDE.md files, auditing agent configs, finding redundant instructions, or wants to slim down what gets loaded on every agent launch. Also use when the user says "my context is too big", "too many instructions", "tokens are expensive", or "clean up my instruction files". Works on any machine — no hardcoded paths.

Use cases: 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
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/agentmd-optimizer

What's inside

Skill name
agentmd-optimizer
Description
Scan the entire machine for CLAUDE.md, AGENTS.md, GEMINI.md, and other agent instruction files, then analyze them for token bloat, redundancy, staleness, hierarchy conflicts, and drift. Produces a token-saving manifest with per-file recommendations and orchestrates sub-agent cleanup using cheap models as workforce. Use this skill whenever the user mentions optimizing instructions, reducing context tokens, cleaning up CLAUDE.md files, auditing agent configs, finding redundant instructions, or wants to slim down what gets loaded on every agent launch. Also use when the user says "my context is too big", "too many instructions", "tokens are expensive", or "clean up my instruction files". Works on any machine — no hardcoded paths.
License
unknown
Instructions
325 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • name: "agentmd-optimizer" does not match folder "agentmd-optimizer.previous-canonical"

Files (5)

  • FEEDBACK.md
  • SKILL.md
  • analysis-guide.md · references/
  • delegation-guide.md · references/
  • discover_instructions.py · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from ildunari/skillshare

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 2, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/ildunari/skillshare
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from ildunari

Cite this page

agentmd-optimizer skill. Agent Mart. https://agentmart.dev/skills/ildunari-agentmd-optimizer (last updated 2026-10-24)