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 lexbritvin/obsidian-skills-pack --skill obsidian-graph-auditgit clone --depth 1 https://github.com/lexbritvin/obsidian-skills-packWrote 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/lexbritvin/obsidian-skills-pack/obsidian-graph-audit)<a href="https://agentmods.dev/skills/lexbritvin/obsidian-skills-pack/obsidian-graph-audit"><img src="https://agentmods.dev/badge/skills/lexbritvin/obsidian-skills-pack/obsidian-graph-audit/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.
<a href="https://agentmods.dev/skills/lexbritvin/obsidian-skills-pack/obsidian-graph-audit"><img src="https://agentmods.dev/badge/skills/lexbritvin/obsidian-skills-pack/obsidian-graph-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00153 | $0.06177 |
| Opus 5 | $0.00077 | $0.03089 |
| Sonnet 5 | $0.00031 | $0.01235 |
| Haiku 4.5 | $0.00015 | $0.00618 |
Grade A, and why
obsidian-graph-audit scanned grade A with 1 finding 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 11d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find . -name "*.md" -not -path "./.obsidian/*" -not -path "./.trash/*" -not -path "./.claude/*" | wc -l Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Graph Audit
A diagnostic workflow for an Obsidian graph that feels tangled, overconnected, or visually noisy. Operates well on Kepano-style vaults (with categories: and topics: in frontmatter) but the patterns generalize.
This skill diagnoses and recommends. It does not silently apply fixes. The deliverable is a report — pain points, ranked by impact, with proposed actions the user can approve, modify, or skip. Mitigation scripts exist (later in this file) but only run after the user explicitly confirms a specific action. Color tweaks and filter changes are out of scope — see the obsidian-graph skill for styling.
When to use
User says:
- "Graph is a hairball / spaghetti / mess"
- "Too many connections, can't read it"
- "Why is X linked to Y? They aren't related"
- "Help me clean up the graph"
- "Find what's making the graph noisy"
- "What should I exclude from the graph?"
Prerequisites
The diagnostic one-liners below use rg (ripgrep), awk, find, and python3. All are common on macOS and Linux except rg, which usually requires brew install ripgrep or equivalent. If rg is not available, substitute grep -c (for counts) or grep -E (for patterns) — slightly slower on large vaults but otherwise equivalent.
Core insight
A node draws visual attention proportional to its degree (number of edges). High-degree nodes are one of:
- Real semantic hubs — coordinating concepts (epics, MOCs, topics-of-many-notes). Keep.
- Render-only hubs — accumulators of inbound links for view rendering (dashboards, log files with inline-fields). Remove from graph or convert.
- Mega-categories — categories used as "tag for files in this folder" rather than entity types. Refactor.
- Broken refs — placeholders, malformed wikilinks creating ghost nodes. Fix.
Audit's job is to classify each visible hub into one of those buckets.
Workflow
The audit is two phases: diagnose + recommend (steps 1–5), then act on confirmation (step 6). Never skip phase 1. Never run phase 2 without an explicit go-ahead from the user on the specific action.
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.
- 11d ago First seen · 410 lines · 153 tokens per session scan A 1639d33ac331
obsidian-graph-audit is a skill published in the GitHub repository lexbritvin/obsidian-skills-pack (2 stars, last pushed 6d ago), licensed MIT. It adds 153 tokens to every session and 6,177 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
code-understand
Build a ranked, citation-backed focus map of a codebase — the files and symbols an architecture actually hangs on — using CodeGraph when available and a dependency-free builtin (regex AST extraction + rg cross-file references) otherwise. Use this any time you (the coding agent) need to orient in an unfamiliar or large…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
report-issue-framework
File a bug or feature request against @cyanheads/mcp-ts-core when you hit a framework issue. Use when a builder, utility, context method, or config behaves contrary to the documented API — not for server-specific application bugs.
report-issue-local
File a bug or feature request against this MCP server's own repo. Use for server-specific issues — tool logic, service integrations, config problems, or domain bugs that aren't caused by the framework.
link-health
Use at the start of Link work when readiness is unclear, after installs or upgrades, and before repairs; verify health, inspect interrupted writes, back up, and repair generated indexes without MCP.