llm-wiki-loop: Skill for Claude Code

.claude/skills/wiki-lint/SKILL.md

wiki-lint is a skill for Claude Code from helicerat/llm-wiki-loop. It costs 58 tokens per session (669 once invoked), scanned A, original, MIT.

A skill for checking the health of a wiki, including its structure, freshness, sources, links, and claims.

In plain words
What is it for?
Running mechanical checks, auditing notes and claims, identifying orphan pages, and reporting conflicts or outdated information.
Why use it?
It finds broken links, missing fields, stale notes, contradictions, and evidence problems before they undermine the wiki. It does not change anything without confirmation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is helicerat/llm-wiki-loop's own configuration. It tells Claude Code how to work on llm-wiki-loop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki-loop configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/lint.py.

Reuse

Borrowing it

Nothing to install: this file belongs to helicerat/llm-wiki-loop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/helicerat/llm-wiki-loop/main/.claude/skills/wiki-lint/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/helicerat/llm-wiki-loop

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.

agentmods badge for wiki-lint

README.md
[![agentmods](https://agentmods.dev/badge/skills/helicerat/llm-wiki-loop/wiki-lint/github.svg)](https://agentmods.dev/skills/helicerat/llm-wiki-loop/wiki-lint)
Your own site
<a href="https://agentmods.dev/skills/helicerat/llm-wiki-loop/wiki-lint"><img src="https://agentmods.dev/badge/skills/helicerat/llm-wiki-loop/wiki-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.

agentmods 80×15 button for wiki-lint

Your own site · 80×15
<a href="https://agentmods.dev/skills/helicerat/llm-wiki-loop/wiki-lint"><img src="https://agentmods.dev/badge/skills/helicerat/llm-wiki-loop/wiki-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 669 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00669
Opus 5 $0.00029 $0.00334
Sonnet 5 $0.00012 $0.00134
Haiku 4.5 $0.00006 $0.00067

Measured 8d ago against content hash 8e60d5a01464, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wiki-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 8d 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.

.claude/skills/wiki-lint/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wiki-lint

Inward-facing. Asks whether the vault is honest with itself.

Start with the mechanical pass, which needs no model at all:

python scripts/lint.py

Then do the three checks a linter cannot do.

Mechanical, already covered by the script

Broken wikilinks, orphan pages, missing claim fields, invalid enum values, rules that sit below the replication bar, n that disagrees with the outcome log, snapshots without a date, stale snapshots, pointers without a target, inferred content over threshold.

Read its output before doing anything else. If it reports errors, they come first — a contradiction you reason about is worth less than a contract violation you can just fix.

What the script cannot see

Contradictions between pages

Two pages asserting incompatible things, where neither is wrong on its face. Write both, dated, and mark the conflict. Do not resolve it silently; the fact that the vault was uncertain is itself information, and reconciling it away destroys the record.

Claims that stopped being about anything

A claim can be perfectly formed, well sourced, and no longer connected to any decision. Its n will never move again because nothing you do tests it any more. Surface these — they are the pages that make a vault feel authoritative while carrying no weight.

Evidence that is thinner than it looks

The one the script cannot reach at all. Ask of each rule:

  • Do its three-plus outcomes come from genuinely independent runs, or from one window sliced into pieces? A narrow window is one run regardless of how many rows it produced
  • Did the outcomes vary enough for the claim to have been falsifiable at all?
  • Was the result judged against your own baseline, or against someone else's peak?

A rule built on one window wearing three hats is worse than no rule, because it blocks drafts with borrowed authority. Demote it and say so.

Fixing

Report first. Fix only what the user confirms.

Safe to fix mechanically once confirmed: broken links with an unambiguous target, missing cross-references for orphans (at most three per page), stub creation for wikilinks whose target does not exist, stale-marker injection.

Read the full file on GitHub · 79 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. 8d ago First seen · 79 lines · 58 tokens per session scan A 8e60d5a01464

Subscribe to this mod's changes

wiki-lint is a skill published in the GitHub repository helicerat/llm-wiki-loop (6 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 669 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 2026-08-31.

Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

overleaf-sync

A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens