Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Agent Mdlint

ASecurity

Review AGENTS.md changes for Markdown defects, duplicated or conflicting instructions, and unintended semantic drift. Use when editing or reviewing agent instruction files, especially large rewrites or diffs that remove existing rules.

6 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agents

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/1/2026

$npx -y skills add CheckPickerUpper/skills --skill agent-mdlint --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agent Mdlint?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Agent Mdlint
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/checkpickerupper-agent-mdlint/badge)](https://www.skillsdirectory.com/skills/checkpickerupper-agent-mdlint)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: agent-mdlint
description: Review AGENTS.md changes for Markdown defects, duplicated or conflicting instructions, and unintended semantic drift. Use when editing or reviewing agent instruction files, especially large rewrites or diffs that remove existing rules.
---

# Agent MD Lint

Review the instruction file as a working contract, not as ordinary prose. Find structural defects and determine whether the change preserves the requested intent and the rules that still apply.

## Review the change

1. Establish the target file, the requested change, and its source of authority. Check whether the file is authored directly or generated from another source; when generated, inspect the owner and review the generated result without editing it as the source.
2. Read the complete before and after versions when available. Compare the diff and account for every removed or materially changed instruction. Do not assume a shorter file is better, or that a deletion was intentional just because the new text says the same topic differently.
3. Check Markdown structure: headings, lists, fences, blockquotes, frontmatter when used, blank lines, stray whitespace, duplicated passages, and text accidentally joined or detached from its intended section.
4. Check semantic integrity: duplicate statements with different meanings, contradictions, vague or untestable rules, lost scope qualifiers, altered permissions, and rules moved under a heading that changes their apparent scope.
5. For each material deletion or change, determine whether the request authorized it and whether the requirement is preserved elsewhere in the authoritative instructions. Report unexplained losses; do not silently restore, invent, or broaden policy.
6. If edits are authorized, correct the instruction file at its canonical source. Then reread the complete result and inspect the final diff for omissions, duplication, and unrelated changes.

## Report

Lead with whether the file is ready to use. For each issue, cite the exact heading or text and state the concrete effect: for example, an operating rule was removed, two statements now conflict, or a paragraph is detached by malformed Markdown. Separate confirmed defects from suggestions. If the diff is unavailable, say that semantic preservation could not be established and review the current file for internal defects only.

Do not turn a specific edit failure into a universal policy. Preserve the source document's existing intent unless the user asked to change it.

Attribution

CheckPickerUpperCheckPickerUpper
View sourceSee grades on GitHubMore from CheckPickerUpper →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →