A command that checks Claude Code plugin manifest files, which are JSON files describing a plugin and its metadata.

It is for validating files such as .claude-plugin/plugin.json against required fields, naming rules, semantic versioning, reserved words, and size limits.

It finds missing or invalid fields, naming problems, version errors, and oversized manifests before they cause issues.

plugins — Command by dotcommander

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/dotcommander/cclint/plugins

Clone the repo

git clone --depth 1 https://github.com/dotcommander/cclint

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,234 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01234
Opus 5	$0.00000	$0.00617
Sonnet 5	$0.00000	$0.00247
Haiku 4.5	$0.00000	$0.00123

Measured yesterday against content hash 31ab812489ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugins scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/reference/commands/plugins.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cclint plugins

Lint and validate plugin manifest files.

Usage

cclint plugins [flags]

Description

The plugins subcommand scans for and validates plugin manifest files in your Claude Code project. Plugins extend Claude Code with custom functionality and are defined via JSON manifests.

Supported File Patterns

**/.claude-plugin/plugin.json

What Gets Validated

Required fields: name, description, author.name
Version format: semver (major.minor.patch)
Name format: lowercase alphanumeric with hyphens, max 64 characters
Description quality: 50+ characters recommended
Reserved words: anthropic, claude are prohibited
File size limit: 5KB for optimal composition scoring

File Size Limit

Plugin manifests should stay under 5KB for optimal quality scoring.

Scoring Tiers

Size	Score	Grade
≤1KB	10/10	Excellent
≤2KB	8/10	Good
≤5KB	6/10	OK
≤10KB	3/10	Large (warning)
>10KB	0/10	Too large (error)

Rationale

Plugin manifests should be concise metadata files. Heavy documentation or configuration should be externalized to separate files (README, config files, etc.).

Example Violation Message

my-plugin/.claude-plugin/plugin.json:1
suggestion: Plugin manifest is 8KB. Best practice: keep plugin.json under 5KB
for optimal loading - move documentation to README.md.

Name Format Rules

Plugin names must follow these conventions:

Lowercase alphanumeric characters with hyphens
Maximum 64 characters
Cannot use reserved words: anthropic, claude

Example Valid Names

{
  "name": "my-plugin",
  "name": "github-integration",
  "name": "dbtools-postgres"
}

Example Violation Messages

# Invalid: reserved word
plugin.json:3
error: Name 'claude-helper' is a reserved word and cannot be used

# Invalid: exceeds character limit
plugin.json:3
error: Name exceeds 64 character limit (72 chars)

Read the full file on GitHub · 199 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 199 lines · 0 tokens per session scan A 31ab812489ed

Subscribe to this mod's changes

plugins is a command published in the GitHub repository dotcommander/cclint (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,234 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review Languages Writing and docs claude-code cli golang linter

plugins