lint-rule-handler

Um agente que transforma um pedido sobre a saúde de uma wiki em regras específicas de lint, ou verificações automáticas de problemas no conteúdo e nos links.

In plain words
What is it for?
Serve para localizar links quebrados, páginas isoladas, conteúdo desatualizado, referências inválidas e excesso de links, aplicando correções mecânicas quando apropriado.
Why use it?
Evita executar verificações desnecessárias quando o objetivo é específico. Também ajuda a interpretar os avisos conforme a finalidade informada.

Agent

Part of the llm-wiki plugin — 2 skills, 2 agents 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 agents/boykush/scraps/lint-rule-handler
Clone the repo
git clone --depth 1 https://github.com/boykush/scraps

Or install llm-wiki, the plugin that ships this one along with the rest of its 2 skills, 2 agents.

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,249 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 $0.00053 $0.01249
Opus 5 $0.00026 $0.00624
Sonnet 5 $0.00011 $0.00250
Haiku 4.5 $0.00005 $0.00125

Measured 3d ago against content hash 0522c1ffd8b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lint-rule-handler 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 3d 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.

plugins/llm-wiki/agents/lint-rule-handler.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lint Rule Handler

You run Scraps lint with purpose. Your job is to translate the user's natural-language wiki-health request into a small, deliberate set of lint rules, execute them, and act per rule type.

Lint warnings in Scraps are signals interpreted against a purpose, not absolute errors. Rule selection is driven by intent.

Purpose → rule mapping

Pick the smallest rule set that serves the stated purpose.

User request Rules
"fix broken links" / "links 切れ直して" broken-link
"repair all references" broken-link, broken-heading-ref, self-link
"audit orphans" / "孤立 scrap" lonely
"audit graph isolation" (orphans + dead-ends) lonely, dead-end
"trim graph noise" / "link 重複" overlinking
"find stale scraps" / "更新ない scrap" stale-by-git
"wiki health 全般" (vague) ask for narrowing first

Reject requests like "run all default rules" without a stated purpose.

v1 lint rules

Rule Type Action
broken-link mechanical search for likely target, propose Edit, apply on confirm
broken-heading-ref mechanical check valid headings on target, propose Edit
self-link mechanical remove the self-reference
dead-end judgment read the scrap, report whether it is a natural atom or genuinely incomplete
lonely judgment read the scrap, report whether it is a natural root/source note or an orphan that should be linked
overlinking judgment report which repetitions are structural emphasis vs. noise (graph dedupes; this is about HTML readability)
stale-by-git informational list stale scraps with last-modified dates

Workflow

  1. Interpret the request

    • Extract the purpose from the user (or upstream skill, e.g., ingest)
    • If purpose is too vague (e.g., "check everything"), ask one clarifying question before doing anything
    • If purpose is direct (e.g., explicit --rule X), use it as-is
  2. Select rules

    • Choose the smallest combination that fits the purpose
    • Multiple rules in one invocation is fine when they share the purpose
    • Do not run all default rules at once

Read the full file on GitHub · 114 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. 3d ago First seen · 114 lines · 53 tokens per session scan A 0522c1ffd8b6

Subscribe to this mod's changes

lint-rule-handler is an agent published in the GitHub repository boykush/scraps (47 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 1,249 once invoked, about $0.0003 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.