AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Validate All

skill-pdugan20-claudelint-validate-all · by pdugan20

Runs comprehensive claudelint validation on all Claude Code project files. Use when user asks to "check everything", "run all validators", "full audit", "validate my entire project", or "what's wrong with my config". Validates CLAUDE.md, skills, settings, hooks, MCP servers, and plugin manifests.

No reviews yet
0 installs
15 views
0.0% view→install

Install

$ agentstack add skill-pdugan20-claudelint-validate-all

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-pdugan20-claudelint-validate-all)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Validate All? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Validate Claude Code Project

Runs claudelint check-all to validate all Claude Code project files including CLAUDE.md, skills, settings, hooks, MCP servers, and plugin manifests.

Usage

claudelint check-all $ARGUMENTS

Options

Available flags:

  • --verbose - Show detailed validation output
  • --warnings-as-errors - Treat warnings as errors
  • --explain - Show detailed explanations and fix suggestions
  • --format - Output format: stylish, json, compact (default: stylish)
  • --config - Path to custom config file
  • --fast - Fast mode: skip expensive checks
  • --color / --no-color - Control color output

Examples

Example 1: Plugin won't load after changes

User says: "I just updated my CLAUDE.md and added a new skill, but now my plugin isn't loading" What happens:

  1. Skill runs claudelint check-all
  2. Finds CLAUDE.md exceeds 50KB (blocking issue)
  3. Finds new skill has wrong capitalization in allowed-tools
  4. Shows both issues need fixing before plugin will load

Result: User identifies why plugin broke and fixes both issues

Example 2: Pre-commit validation failed

User says: "My git pre-commit hook is failing but I don't know which validator is the problem" What happens:

  1. Skill runs claudelint check-all --verbose
  2. Shows validate-mcp failed: invalid transport type "sse" (deprecated)
  3. Shows validate-hooks passed, validate-skills passed, etc.
  4. Points to specific .mcp.json file and line number

Result: User fixes the one failing validator (MCP config) and commit succeeds

Example 3: After npm install, verify everything still works

User says: "I just upgraded claude-code-lint, make sure I didn't break anything" What happens:

  1. Skill runs claudelint check-all
  2. Detects new rules flagging previously-allowed patterns
  3. Shows deprecation warnings for old syntax
  4. Suggests migration path for deprecated features

Result: User knows what needs updating after version upgrade

Command Examples

Basic validation:

claudelint check-all

Verbose output with explanations:

claudelint check-all --verbose --explain

JSON output for CI/CD:

claudelint check-all --format json

Use custom config:

claudelint check-all --config .claudelintrc.custom.json

Treat warnings as errors (strict mode):

claudelint check-all --warnings-as-errors

What Gets Validated

The validate skill checks:

  1. CLAUDE.md files - File size, imports, frontmatter, sections
  2. Skills - SKILL.md schema, naming, documentation, security
  3. Settings - settings.json schema, permissions, environment variables
  4. Hooks - hooks.json schema, events, commands
  5. MCP Servers - .mcp.json schema, transport config, variables
  6. Plugins - plugin.json schema, semantic versioning, references

Exit Codes

  • 0 - No errors or warnings
  • 1 - Warnings found (or warnings treated as errors)
  • 2 - Errors found or fatal error (invalid config, crash)

For troubleshooting, see [common issues](./references/common-issues.md). For customization, see [configuration](./references/configuration.md).

See Also

  • [validate-cc-md](../validate-cc-md/SKILL.md) - Validate only CLAUDE.md files
  • [validate-skills](../validate-skills/SKILL.md) - Validate only skills
  • [validate-settings](../validate-settings/SKILL.md) - Validate only settings
  • [format-cc](../format-cc/SKILL.md) - Format Claude files with prettier/markdownlint

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.