lint

A health check for an LLM wiki, a knowledge base made from linked Markdown pages. It reports invalid page metadata, broken links, pages with no incoming links, outdated pages, missing backlink sections, and missing source references.

In plain words
What is it for?
Use it before reviewing or publishing a wiki to check page metadata, link integrity, orphan pages, freshness, backlinks, and source attribution.
Why use it?
It finds structural and maintenance problems that are easy to miss when a wiki grows. The report identifies the affected file and, for broken links, its line number.

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/doneyli/claude-code-plugins/lint
Clone the repo
git clone --depth 1 https://github.com/doneyli/claude-code-plugins
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00027 $0.00514
Opus 5 $0.00014 $0.00257
Sonnet 5 $0.00005 $0.00103
Haiku 4.5 $0.00003 $0.00051

Measured yesterday against content hash 217bdd682b14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

llm-wiki/commands/lint.md · 61 lines

What it actually says

Lint the wiki in the current directory. Output a report grouped by check type.

For each .md file under wiki/ (skip wiki/log.md):

  1. Frontmatter validation

    • YAML frontmatter exists between --- markers
    • Required fields: title, type, created, last_updated
    • confidence ∈ {high, medium, low} if present
    • ttl matches ^\d+d$ or is null
    • created / last_updated match YYYY-MM-DD
  2. Link integrity

    • Every [[wikilink]] resolves to an existing wiki page
    • Report broken links with file:line
  3. Orphans

    • Count inbound [[references]] to each page
    • Pages with 0 inbound (except wiki/index.md) are orphans
    • Exception: synthesis pages linked from wiki/index.md
  4. Backlinks section audit

    • Every page has a ## Backlinks heading (warn if missing)
  5. Staleness

    • last_updated + ttl < today → stale
    • Skip pages with ttl: null
  6. Source attribution

    • Pages with type ∈ {entity, concept, theme, capability, narrative, client, pattern} have non-empty sources:
    • Synthesis and comparison pages may have empty sources:

Output format:

=== Frontmatter ===
✗ wiki/entities/foo.md: missing required field 'type'

=== Links ===
✗ wiki/concepts/bar.md:15: broken link [[nonexistent]]

=== Orphans ===
⚠ wiki/themes/lonely.md: 0 inbound links

=== Staleness ===
⚠ wiki/entities/old.md: stale (last_updated 2025-01-01, ttl 90d)

=== Attribution ===
✗ wiki/entities/foo.md: type 'entity' requires non-empty sources:

=== Summary ===
N errors, M warnings (K pages checked)

If there are errors, suggest specific fixes — but do NOT auto-fix unless the user asks. Just report.

Do not invent issues. If the wiki is clean, print Healthy — 0 errors, 0 warnings.

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. yesterday First seen · 61 lines · 27 tokens per session scan A 217bdd682b14

Subscribe to this mod's changes

lint is a command published in the GitHub repository doneyli/claude-code-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 514 once invoked, about $0.0001 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 2026-08-31.