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.
npx skills add thoreinstein/gemini-obsidian --skill link-auditgit clone --depth 1 https://github.com/thoreinstein/gemini-obsidianWrote 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.
[](https://agentmods.dev/skills/thoreinstein/gemini-obsidian/link-audit)<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>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 | $0.00054 | $0.00402 |
| Opus 5 | $0.00027 | $0.00201 |
| Sonnet 5 | $0.00011 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- link-audit — 86% identical, 12 lines differ
What it actually says
Vault Link Audit
Comprehensive audit of link health: broken wikilinks, orphaned notes, and semantic suggestions.
Phase 1 — Broken Links
- Call
obsidian_get_broken_links(optionally withsubfolderargument). - Present broken links grouped by originating file.
- For each, suggest: delete the link, create a stub note, or correct the target name.
- Offer to fix each with
obsidian_replace_in_note(wrong name → correct name).
Phase 2 — Orphaned Notes
- Call
obsidian_list_notesto enumerate all notes in scope. - For each candidate orphan, call
obsidian_get_backlinks. - Notes with zero backlinks and not in
Daily Notes/are orphan candidates. - 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:
- For each orphan, call
obsidian_rag_querywith the orphan title as query,limit: 5. - 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:indexfirst ifobsidian_get_broken_linksseems incomplete
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.
- 7d ago First seen · 44 lines · 54 tokens per session scan A c280766d86a7
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.
Other skills, from other repositories
context-optimize
Skill "context-optimize" from Joonghyun-Lee-Frieren/oh-my-antigravity, covering purpose, trigger, workflow, output template and context health.
compound
Extract lessons, patterns, and architectural truths to compound team knowledge.
expert-librarian
An expert librarian that helps you organize, search, and synthesize your Readwise highlights and documents.
memory-management
This skill should be used when the user wants to "persist agent state", "remember past conversations", "short-term memory", "long-term memory", "session management", "vector database for agents", "agent memory", "context window management", "store user preferences", "recall previous interactions", "stateful agents"…
neo4j-agent-memory-skill
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…
context-degradation
Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash.