A health-check guide for an LLM-Wiki, where pages are stored as linked Markdown documents. It checks structure, source history, outdated claims, contradictions, missing ownership information, and taxonomy problems.

Use it to check broken and orphaned links, missing provenance, stale or conflicting claims, protected sections, and category drift. It can create reports and suggest changes, while applying fixes requires explicit permission.

It helps find damage or loss of trust after importing many pages, changing the structure, or before a large reorganisation. Findings become a review queue instead of being silently rewritten.

wiki-lint — Skill for Claude Code and Codex by po4yka

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.

Any agent

npx skills add po4yka/llm-wiki-skills --skill wiki-lint

Clone the repo

git clone --depth 1 https://github.com/po4yka/llm-wiki-skills

Made for: Claude Code, Codex.

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/skills/po4yka/llm-wiki-skills/wiki-lint/github.svg)](https://agentmods.dev/skills/po4yka/llm-wiki-skills/wiki-lint)

Your own site

<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/wiki-lint"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/wiki-lint"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/wiki-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,107 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	$0.00047	$0.01107
Opus 5	$0.00023	$0.00553
Sonnet 5	$0.00009	$0.00221
Haiku 4.5	$0.00005	$0.00111

Measured 12d ago against content hash dc87f7cc2c17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/wiki-lint-core.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/wiki-lint/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki Lint

Goal

Detect structural decay, provenance gaps, stale claims and contradictions without silently rewriting truth.

When to use

The vault needs a structural or trust health check.
Before large refactors or after bulk ingestion.
A review queue should be generated from mechanical findings.

A filled final report ships in assets/worked-example.md.

Inputs

wiki/index.md
wiki/log.md
all wiki/**/*.md pages
_meta/taxonomy.md
_meta/schemas/*
optional git history

Write permissions

Allowed:

create reports under _agent/reports/;
append to wiki/log.md when a report is created;
propose patches;
fix trivial broken links only when the user explicitly asks for apply mode.

Not allowed by default:

resolve contradictions;
rewrite synthesis pages;
mark pages verified;
delete pages;
bulk-normalize frontmatter without a dry run.

Procedure

1. Run deterministic checks

node scripts/wiki-lint-core.mjs <vault-path>

The bundled script is read-only and prints a draft report covering the mechanical checks. Do not re-derive these by hand; re-run the script instead:

inventory: page counts by type/status, missing or malformed required frontmatter;
links: broken wikilinks and relative links, orphan pages, pages with no outbound links, duplicate titles, near-duplicate slugs;
provenance: generated or reviewed/verified factual pages without source_paths/source_urls, high-confidence pages with no source reference;
trust: ai_confidence < 0.70 without review_required: true, review_required: false on draft pages, verified pages past stale_after, ambiguous claim support outside review;
taxonomy: unknown types/statuses, tags missing from _meta/taxonomy.md, unused taxonomy tags.

Use --strict in CI to fail on critical/high findings.

2. Add judgement-only checks

The script cannot see these; check them manually:

pages changed since the last lint and pages without source backlinks in git history;
protected human sections changed by recent agent commits;
stale source hashes when available;
generated pages that cite only other generated pages;
pages missing from wiki/index.md that are likely important;
spelling-variant and overbroad tags beyond exact taxonomy mismatches.

Read the full file on GitHub · 139 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 139 lines · 47 tokens per session scan A dc87f7cc2c17

Subscribe to this mod's changes

wiki-lint is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 47 tokens to every session and 1,107 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 2026-08-31.

Claude Code Memory and context agent-skills ai-agents codex knowledge-management llm-wiki

wiki-lint

Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…

tboome33/obsidian-mcp-router · 119 tokens

save

File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…

tboome33/obsidian-mcp-router · 112 tokens

wiki-export

Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…

tboome33/obsidian-mcp-router · 129 tokens

wiki-query

Answer a question using ONLY the existing wiki vault as the knowledge base — no web search, no general LLM knowledge. Reads hot.md first (cheap recent context), then catalog.md to navigate, then drills into specific pages, then optionally semantic-searches the wiki, and synthesizes an answer with citations. Use when…

tboome33/obsidian-mcp-router · 129 tokens

wiki-fold

Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…

tboome33/obsidian-mcp-router · 125 tokens

wiki

Bootstrap or check a Karpathy-style "LLM wiki" structure inside an Obsidian vault — a self-maintaining knowledge base where pages reference each other and the LLM keeps it tidy. Sets up catalog.md (curated page catalog), journal.md (append-only operation history), hot.md (recent-context cache), and overview.md…

tboome33/obsidian-mcp-router · 134 tokens

wiki-lint

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Wiki Lint

Goal

When to use

Inputs

Write permissions

Procedure

1. Run deterministic checks

2. Add judgement-only checks

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

wiki-lint

save

wiki-export

wiki-query

wiki-fold

wiki