Agents Md Improver

Agents Md Improver is an AI Engineering skill for Claude Code, published by waybarrios in opencode-power-pack.

482 stars39 forkson waybarrios/opencode-power-packAdded 2026/08/26+2% in starsRepository updated 2026/08/24

ai-agentsanthropicclaude-codecode-reviewcodexcodex-clideveloper-toolsgradiohuggingfacellm-toolsmachine-learningml-trainingopenai-codexopencodepipi-coding-agentpi-packagepluginsecurity-auditskills

Install in seconds

Install Agents Md Improver

Copy Agents Md Improver into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/waybarrios/opencode-power-pack/tree/main/skills/agents-md-improver ~/.claude/skills/agents-md-improver

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/waybarrios/opencode-power-pack.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/agents-md-improver/SKILL.md in waybarrios/opencode-power-pack
Installs to: ~/.claude/skills/agents-md-improver
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agents Md Improver does

Agents Md Improver audits AGENTS.md, CLAUDE.md, and related rules files for coverage, clarity, and freshness. Use it when project rules need review or targeted updates after code changes.

Agents Md Improver is cataloged under AI Engineering on DirSkills. Agents Md Improver comes from a repository tagged ai-agents, anthropic, claude-code, code-review and codex.

Documentation

README

Excerpt

AGENTS.md / CLAUDE.md Improver

Audit, evaluate, and improve project-rules files across a codebase to ensure the agent has optimal project context.

Read references/project-rule-resolution.md, resolved relative to this loaded SKILL.md directory and not the consuming project's CWD or working directory, before discovery or resolution analysis. Apply only the behavior for the target client and pinned version; do not collapse OpenCode startup, OpenCode lazy nested, and Claude Code resolution into one rule.

This skill can write to project-rules files. After presenting a quality report and getting user approval, it updates the files with targeted improvements.

Untrusted data boundary

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Agents Md Improver

What else does waybarrios publish alongside Agents Md Improver?
Agents Md Improver is one of 25 skills that DirSkills catalogs from waybarrios/opencode-power-pack, the repository it ships in. Its siblings there include AI Slop Rubric, AWS Context Discovery and Agentic Actions Auditor. Each one is a separate skill with its own page in this directory, installs the same way Agents Md Improver does, and is maintained by waybarrios in that same repository. The rest of the collection is listed on the waybarrios/opencode-power-pack page.
How does Agents Md Improver compare to other AI Engineering skills?
Agents Md Improver ranks #2200 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agents Md Improver against them. Open each page to compare what they document and how they install.