skills

A command for checking skill definition files, which are instruction files that teach a coding agent a method or specialist workflow. It validates their names, front matter, structure, descriptions, length, and required sections.

In plain words
What is it for?
Run it with `cclint skills` to scan supported SKILL.md files in a Claude Code project. It checks locations such as `.claude/skills/**/SKILL.md` and `skills/**/SKILL.md`.
Why use it?
It catches malformed or overly large skill files before the agent relies on them. This helps keep skills discoverable and focused on core instructions.

Command

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/skills
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 1,031 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01031
Opus 5 $0.00000 $0.00515
Sonnet 5 $0.00000 $0.00206
Haiku 4.5 $0.00000 $0.00103

Measured 2d ago against content hash 27b92329bf8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills 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 2d ago.

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/skills.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cclint skills

Lint and validate skill definition files.


Usage

cclint skills [flags]

Description

The skills subcommand scans for and validates skill definition files in your Claude Code project. Skills contain methodology, patterns, and reference material for specialist domains.

Supported File Patterns

  • .claude/skills/**/SKILL.md
  • skills/**/SKILL.md

What Gets Validated

  • Filename must be SKILL.md
  • Frontmatter structure and required fields
  • Name format (agentskills.io compliance)
  • Line count limit (500 lines ±10% tolerance)
  • Description quality (third-person, trigger phrases)
  • Required sections (Quick Reference, Anti-Patterns)
  • Directory structure validation

Line Limit Rule

Skills must stay under ~550 lines (500 lines ±10% tolerance).

Rationale

Skills should contain core methodology only. Heavy documentation, schemas, or examples should be moved to a references/ subdirectory and loaded on demand.

Example Violation Message

my-skill/SKILL.md:600
suggestion: Skill is 600 lines. Best practice: keep skills under ~550
lines (500±10%) - move heavy docs to references/ subdirectory.

What To Do Instead

Extract heavy content to reference files:

# Core methodology in SKILL.md (<500 lines)

## Quick Reference

| User Question | Action |
|---------------|--------|
| Need detailed schema? | See [Schema Reference](references/schema.md) |

SKILL.md Naming Rule

Skill files must be named SKILL.md (case-sensitive).

Rationale

This naming convention is required by Anthropic's documentation standards for skill discovery and loading.

Example Violation Message

my-skill/skill.md:1
error: Skill file must be named SKILL.md

Quick Reference Requirement

Skills should include a Quick Reference section for semantic routing.

Rationale

The Quick Reference table acts as a semantic routing guide, helping Claude understand when to use the skill based on user questions or task context.

Read the full file on GitHub · 182 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.

  1. 2d ago First seen · 182 lines · 0 tokens per session scan A 27b92329bf8b

Subscribe to this mod's changes

skills is a command published in the GitHub repository dotcommander/cclint (16 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,031 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.