Skip to main content
Glama

Lint steering files

lint_steering
Read-onlyIdempotent

Check agent steering files for valid frontmatter/YAML, required fields, unknown keys, length limits, broken links/imports, hidden characters, and conflicting rules; scan all allowed files without path.

Instructions

Check agent steering files: frontmatter on line 1 and valid YAML, required SKILL.md and subagent fields, unknown keys, length against vendor limits (CLAUDE.md 200 lines, SKILL.md 500 lines, 1,536-character skill listing, MEMORY.md 200 lines or 25 KB, AGENTS.md 32 KiB for Codex), broken relative links and @imports, invisible and bidirectional characters, hidden HTML comments with instructions, duplicate and contradictory-looking rules. With no path, lints every steering file under the allowed folder.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "lint_steering"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoOne file to lint
pathsNoSeveral files to lint
includeNoOpt-in scans beyond markdown: skills (scripts in skill folders), config (.claude/settings.json, MCP config files, .gitignore files, the first 4 KB of <uuid>.jsonl transcripts, and package.json and Makefile files for the dead-command rule), config-local (also .claude/settings.local.json). Off by default
trustRepoConfigNoLet the repo's own .asitisrc.json turn off, lower or ignore security findings. Off by default, so a cloned repo cannot hide its own hidden instructions or risky hooks; set it only for a repo you trust

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.4
    • changedInput schema / properties / include / description
      Previous value: -"Opt-in scans beyond markdown: skills (scripts in skill folders), config (.claude/settings.json, MCP config files, .gitignore files and the first 4 KB of <uuid>.jsonl transcripts), config-local (also .claude/settings.local.json). Off by default"New value: +"Opt-in scans beyond markdown: skills (scripts in skill folders), config (.claude/settings.json, MCP config files, .gitignore files, the first 4 KB of <uuid>.jsonl transcripts, and package.json and Makefile files for the dead-command rule), config-local (also .claude/settings.local.json). Off by default"
  2. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered by structured data. The description adds the default scan scope (all steering files when no path is given) but says nothing about result volume, ordering, or how findings are reported, and the security-relevant trustRepoConfig behavior is carried by the schema rather than the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the verb and resource, then a dense but well-organized enumeration of checks and vendor limits, closing with the zero-argument default. Every clause carries concrete information; nothing is redundant filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Checks and limits are thoroughly covered, but with no output schema the description never indicates what a finding looks like or how results are returned, which matters for a linter whose whole product is findings. Adequate for invocation, incomplete for interpreting results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and all four parameters are documented in the schema, including the opt-in include groups and the trustRepoConfig trust model. The description adds no parameter-level meaning beyond the default-path behavior, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb ('Check') plus resource ('agent steering files') followed by an enumerated list of what is validated, so the agent knows exactly what the tool inspects. It does not name or contrast with siblings such as find_steering_files or suggest_fixes, so the differentiation is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The final sentence gives one important usage rule: with no path, every steering file under the allowed folder is linted, which tells the agent it can call with zero arguments. There is no explicit when-to-use vs. when-not guidance and no pointer to a sibling for fixing findings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.