worker-link-validator

worker-link-validator is an agent for Claude Code from anh-chu/llm-wiki-pm. It costs 30 tokens per session (563 once invoked), scanned A, original, MIT.

A subagent that checks a Markdown wiki for broken links, unused pages, missing index entries, and missing page metadata. A wikilink is a page reference written in the form [[page-name]].

In plain words
What is it for?
Use it to scan for invalid wikilinks, orphan pages with no incoming links, pages missing from index.md, and missing title, type, tags, or update fields.
Why use it?
It reveals structural problems in a wiki without modifying any pages, so links and navigation gaps can be fixed deliberately.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: model in frontmatter; mentions Claude Code.

Part of the llm-wiki-pm plugin — 8 skills, 5 agents, 4 hooks 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/anh-chu/llm-wiki-pm/worker-link-validator
Clone the repo
git clone --depth 1 https://github.com/anh-chu/llm-wiki-pm

Made for: Claude Code.

Or install llm-wiki-pm, the plugin that ships this one along with the rest of its 8 skills, 5 agents, 4 hooks.

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 worker-link-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-link-validator.svg)](https://agentmods.dev/agents/anh-chu/llm-wiki-pm/worker-link-validator)
Your own site
<a href="https://agentmods.dev/agents/anh-chu/llm-wiki-pm/worker-link-validator"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-link-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 563 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 5.1 $0.00030 $0.00563
Opus 5 $0.00015 $0.00282
Sonnet 5 $0.00006 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured 6d ago against content hash 8a68c806b9c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

worker-link-validator 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 6d 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/agents/worker-link-validator.md · 61 lines

What it actually says

You are a link validation worker. Scan the wiki for structural integrity issues. No fixes — just detection and reporting.

Capabilities

  • Read: Read any wiki page
  • Bash: Run grep, python3 backlinks.py
  • Glob: List files across wiki directories

Wiki Path Resolution

WIKI=$(cat .wiki-path 2>/dev/null | tr -d '[:space:]')
WIKI=${WIKI:-${CLAUDE_PLUGIN_OPTION_wiki_path:-${WIKI_PATH:-$(pwd)}}}
# CLAUDE_SKILL_DIR is injected by Claude Code at skill invocation time.
# It points to the root of the llm-wiki-pm repo (where scripts/ lives).

Checks to Run

  1. Broken wikilinks — for each [[slug]] found across all pages, verify $WIKI/entities/<slug>.md or $WIKI/concepts/<slug>.md or $WIKI/comparisons/<slug>.md exists
  2. Orphan pages — use backlinks.py to find pages with zero inbound links:
    python3 "${CLAUDE_SKILL_DIR}/scripts/backlinks.py" "$WIKI" --all-orphans
    
  3. Index gaps — pages in entities/concepts/comparisons/ not present in index.md
  4. Missing frontmatter — pages missing required fields: title, type, tags, updated

Output Format

Write full report to /tmp/wiki-link-report-<YYYYMMDD>.md:

# Link Validation Report — YYYY-MM-DD

## Broken Wikilinks (N)
- [[slug]] referenced in: page1.md, page2.md

## Orphan Pages (N)
- entities/foo.md — no inbound links

## Index Gaps (N)
- entities/bar.md — not in index.md

## Missing Frontmatter (N)
- concepts/baz.md — missing: updated, tags

Return ONLY: "OK: broken=<N>, orphans=<N>, index-gaps=<N>, frontmatter-issues=<N>. Full report: /tmp/wiki-link-report-<YYYYMMDD>.md"

Rules

  • Exclude _archive/ from broken link checks (archived pages are intentionally removed)
  • Exclude log.md, overview.md, index.md, _status.md from orphan checks (structural files)
  • Do not modify any files
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. 6d ago First seen · 61 lines · 30 tokens per session scan A 8a68c806b9c6

Subscribe to this mod's changes

worker-link-validator is an agent published in the GitHub repository anh-chu/llm-wiki-pm (6 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 563 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.

Related

Other agents, from other repositories

curator

Sub-agent dispatched by /mb:lint. Read-only — has Read + lint MCP tools but no Edit/Write/Bash. Surfaces orphans, contradictions, stale claims, gaps. Suggests fixes; doesn't apply them.

frankchu91/mindbase-llm-wiki · 49 tokens

migrator

One-time sub-agent that runs /mb:migrate. Has Bash (for atomic mv operations not yet wrapped in MCP) plus mindbasemigrate + mindbasevalidatestructure. Should be invoked exactly once per legacy project.

frankchu91/mindbase-llm-wiki · 48 tokens

builder

Sub-agent dispatched by /mb:build to synthesize context.md from sources/. Tool-restricted to MCP only — has no Edit/Write/Bash so cannot bypass atomic write pipeline.

frankchu91/mindbase-llm-wiki · 39 tokens

contributor

Sub-agent dispatched for substantive contributions (PDFs, URLs, long pastes). Reads source carefully, discusses takeaways with user, proposes structured plan, commits via MCP. Cannot bypass append-only contract.

frankchu91/mindbase-llm-wiki · 43 tokens

researcher

Sub-agent dispatched by /mb:research. Has WebFetch + WebSearch + Read + MCP researchsave + searchwiki tools. Cannot Edit/Write directly — research findings flow through mindbaseresearchsave (append-only to sources/research/).

frankchu91/mindbase-llm-wiki · 54 tokens

wiki-lint

Comprehensive wiki health check agent. Scans for orphan pages, dead links, stale claims, missing cross-references, frontmatter gaps, and empty sections. Generates a structured lint report. Dispatched when the user says "lint the wiki", "health check", "wiki audit", or "clean up". Context: User says "lint the wiki"…

eliransu/digital-brain · 137 tokens