lint

lint is a command for Claude Code from frankchu91/mindbase-llm-wiki. It costs 37 tokens per session (332 once invoked), scanned A, original, MIT.

A command that checks a MindBase project for problems in its knowledge pages. It looks for missing links, contradictions, outdated claims, and incomplete areas.

In plain words
What is it for?
Use it to run a project health check, find orphaned pages, detect contradictions and gaps, and suggest links between related pages.
Why use it?
It helps reveal information that is isolated, inconsistent, stale, or missing from the project.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents.

Part of the mb plugin — 1 skill, 12 commands, 5 agents, 1 hook, 1 MCP server shipped together

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/frankchu91/mindbase-llm-wiki/lint
Clone the repo
git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki

Made for: Claude Code.

Or install mb, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 5 agents, 1 hook, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lint

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankchu91/mindbase-llm-wiki/lint.svg)](https://agentmods.dev/commands/frankchu91/mindbase-llm-wiki/lint)
Your own site
<a href="https://agentmods.dev/commands/frankchu91/mindbase-llm-wiki/lint"><img src="https://agentmods.dev/badge/commands/frankchu91/mindbase-llm-wiki/lint.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 332 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 5.1 $0.00037 $0.00332
Opus 5 $0.00018 $0.00166
Sonnet 5 $0.00007 $0.00066
Haiku 4.5 $0.00004 $0.00033

Measured 6d ago against content hash 57936c4bafe2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

lint 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 6d 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.

apps/plugin/commands/lint.md · 31 lines

What it actually says

Health-check a MindBase project.

Arguments: $ARGUMENTS

Parse in order:

  • --project <id> or -p <id> flag → target project id.
  • First positional arg (if not a flag) → target project id (fallback).
  • If neither present → uses config.json currentProjectId.

Dispatch the curator sub-agent via the Task tool with subagent_type: "curator" and prompt:

Run wiki health check for project ${resolvedProjectId}.

The curator threads projectId through every MCP call (validate_structure, run_wiki_health, find_orphans, find_contradictions, find_gaps, suggest_links, append_log).

When the sub-agent returns, present its findings verbatim to the user (the formatting is already done).

Offer one of:

  1. "Want me to file a follow-up note for any of these?" → if yes, call /mb:contribute -p ${resolvedProjectId} for the chosen finding (preserve the same project).
  2. "Rebuild context to refresh stale data?" → if yes, dispatch builder with the same projectId.

Note: -p / positional does NOT change current project.

Examples:

  • /mb:lint → current project
  • /mb:lint -p ai-agents → lint ai-agents (current unchanged)
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. 6d ago First seen · 31 lines · 37 tokens per session scan A 57936c4bafe2

Subscribe to this mod's changes

lint is a command published in the GitHub repository frankchu91/mindbase-llm-wiki (95 stars, last pushed 12d ago), licensed MIT. It adds 37 tokens to every session and 332 once invoked, about $0.0002 per session on Opus 5. 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.