link-audit

link-audit is a skill for Claude Code, Codex from thoreinstein/gemini-obsidian. It costs 54 tokens per session (402 once invoked), scanned A, original, ISC.

A tool for checking links in an Obsidian vault, a folder of linked Markdown notes. It finds broken wikilinks, notes with no incoming links, and optionally related notes.

In plain words
What is it for?
Use it to review broken links, find orphaned notes, group issues by source file, and suggest possible connections between notes.
Why use it?
It helps identify links that no longer work and notes that are disconnected from the rest of the vault.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review broken links, find orphaned notes, group issues by…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thoreinstein/gemini-obsidian/link-audit
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 thoreinstein/gemini-obsidian --skill link-audit
Clone the repo
git clone --depth 1 https://github.com/thoreinstein/gemini-obsidian

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.

agentmods badge for link-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/thoreinstein/gemini-obsidian/link-audit.svg)](https://agentmods.dev/skills/thoreinstein/gemini-obsidian/link-audit)
Your own site
<a href="https://agentmods.dev/skills/thoreinstein/gemini-obsidian/link-audit"><img src="https://agentmods.dev/badge/skills/thoreinstein/gemini-obsidian/link-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 402 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 $0.00054 $0.00402
Opus 5 $0.00027 $0.00201
Sonnet 5 $0.00011 $0.00080
Haiku 4.5 $0.00005 $0.00040

Measured 7d ago against content hash c280766d86a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

link-audit 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 7d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/link-audit/SKILL.md · 44 lines

What it actually says

Comprehensive audit of link health: broken wikilinks, orphaned notes, and semantic suggestions.

  1. Call obsidian_get_broken_links (optionally with subfolder argument).
  2. Present broken links grouped by originating file.
  3. For each, suggest: delete the link, create a stub note, or correct the target name.
  4. Offer to fix each with obsidian_replace_in_note (wrong name → correct name).

Phase 2 — Orphaned Notes

  1. Call obsidian_list_notes to enumerate all notes in scope.
  2. For each candidate orphan, call obsidian_get_backlinks.
  3. Notes with zero backlinks and not in Daily Notes/ are orphan candidates.
  4. Present orphan list with options: link from a relevant note, move to archive, or delete.

Phase 3 — Semantic Suggestions (Optional)

If the user asks for deeper suggestions:

  1. For each orphan, call obsidian_rag_query with the orphan title as query, limit: 5.
  2. If strong matches exist, suggest [[wikilink]] connections.

Arguments

Optional subfolder: /link-audit Engineering/

Tips

  • For large vaults, always scope to a subfolder first; a full-vault orphan scan is slow
  • Broken links in Daily Notes/ are usually harmless; offer to skip them
  • Never make edits without per-change user confirmation
  • Run /obsidian:index first if obsidian_get_broken_links seems incomplete
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. 7d ago First seen · 44 lines · 54 tokens per session scan A c280766d86a7

Subscribe to this mod's changes

link-audit is a skill published in the GitHub repository thoreinstein/gemini-obsidian (102 stars, last pushed 1mo ago), licensed ISC. It adds 54 tokens to every session and 402 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.