A checker for a Markdown knowledge base that looks for broken internal links, orphan pages, old pages, repeated terms, and possible contradictions. It produces a health report and can offer safe fixes when requested.

Use it to audit wiki pages, find links that lead nowhere, suggest new pages for recurring terms, detect possible conflicting descriptions, and optionally repair simple issues.

It helps find missing connections, stale information, and inconsistencies before they make the knowledge base harder to trust. Safe fixes can address selected structural problems.

lint — Command for Claude Code by elbalen/skopus

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.

Clone the repo

git clone --depth 1 https://github.com/elbalen/skopus

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/elbalen/skopus/lint/github.svg)](https://agentmods.dev/commands/elbalen/skopus/lint)

Your own site

<a href="https://agentmods.dev/commands/elbalen/skopus/lint"><img src="https://agentmods.dev/badge/commands/elbalen/skopus/lint/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/elbalen/skopus/lint"><img src="https://agentmods.dev/badge/commands/elbalen/skopus/lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 440 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00007	$0.00440
Opus 5.5	$0.00003	$0.00176
Sonnet 5.5	$0.00001	$0.00088
Haiku 4.5	$0.00001	$0.00044

Measured 1mo ago against content hash 76b74462d344, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

skopus/templates/commands/lint.md · 55 lines

What it actually says

/lint

Scan the wiki for integrity issues and report a health report with suggested fixes. Auto-fix safe cases on request.

No arguments.

Steps

Scan every .md file in wiki/ via Glob: wiki/**/*.md.
Extract all [[wikilinks]] from every page. Track source page and link target.
Build inbound link counts (excluding index.md).
Check each wikilink target resolves to an existing page.
Check updated: frontmatter dates. Flag pages older than 30 days.
Scan for repeated terms that don't have their own page yet (capitalized terms, technical terms appearing 3+ times).
Look for potential contradictions — same entity described differently across pages.

Print a health report:

📊 Wiki Health Report

Totals: Pages, Links, Words, Sources

❌ Broken wikilinks (N)
🏝️  Orphan pages (N)
🕸️  Stale pages (N)
📝 Suggested new pages (N)
⚠️  Potential contradictions (N)

Offer to auto-fix safe cases:
- Broken wikilinks → create stub pages OR remove links (user chooses)
- Missing index entries → add them automatically
Append lint results to log.md.
Git commit if any fixes were applied: lint: fix <N> <issue type>.

Rules

Report before fixing. Always show the full report first.
Auto-fixes are safe only. Creating stubs and updating index entries are safe. Deleting/merging require confirmation.
Stub pages get type: stub and a > ⚠️ Stub: needs content callout.
Don't flag pages created in the last 7 days as stale.
index.md is excluded from orphan/inbound counts.

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.

1mo ago First seen · 55 lines · 7 tokens per session scan A 76b74462d344

Subscribe to this mod's changes

lint is a command published in the GitHub repository elbalen/skopus (4 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 440 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.

Debugging

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

react-native

Command "react-native" from getsentry/toolkit, covering examples, also associate with a release and distribution(s), xcode build step (react-native xcode) and important notes.

getsentry/toolkit · 0 tokens

doctor

Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…

doncheli/don-cheli-sdd · 76 tokens

lint

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/lint

Steps

Rules

What this file has done since we first saw it

Other commands, from other repositories

qa-changes

react-native

doctor

doctor

auditar-cascading

http-service