Skip to content
SkillModel-led8,077 tokens in use

wiki-status

Audit an Obsidian wiki: what is ingested, what changed since, which pages are hubs and bridges, whether maintenance has converged and what each job costs.

3,792 stars on the repository MIT LicenseAr9av/obsidian-wiki · skills/wiki-status
pip install obsidian-wiki
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing wiki-status costs

70tokens idle
8,077tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size7/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 291

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

This skill reports the state of an Obsidian wiki that agents maintain. In its default mode it compares your sources and agent history against the ingest manifest, lists new, modified and deleted sources, estimates the token footprint of the vault and ends with a ranked What to Do Next list.

Three further modes cover structure and upkeep. Insights mode runs a graph analyser to find anchor pages, bridges, clusters and surprising links and writes _insights.md. Equilibrium mode checks whether lint, dedup, cross-linking and tag audits would still change anything. Costs mode reads the per-job cost report.

What You Get

  • A status report with page and source counts, visibility tally, new, modified and deleted sources, and an append or rebuild recommendation
  • A token footprint table by tier with index-only and typical query estimates and a warning threshold
  • A ranked What to Do Next list of up to six items: staged pages, _raw files, stale core pages, orphans, synthesis opportunities, source delta and lint
  • An _insights.md file with anchor pages, bridge pages, cluster cohesion, surprising connections, tier suggestions and questions worth asking
  • An equilibrium report that names deviating and converged maintenance skills and flags ones that keep undoing each other
  • A cost table per job with verdicts for jobs that spend without output or fail

Common Use Cases

  • Deciding whether to append the new sources or rebuild the wiki
  • Finding the hub and bridge pages that hold a vault together
  • Checking whether lint, dedup and cross-linking have all gone quiet
  • Seeing which scheduled wiki jobs cost more than they produce

What Makes It Unique

The skill covers the whole life of a vault in one place: ingest delta, graph shape, maintenance convergence and spend. The equilibrium mode treats maintenance skills as players sharing a vault and reports when one keeps reintroducing the work another clears. It also marks LLM-based counts as estimates and recommends changes without applying them.

Under The Hood

The agent loads the SKILL.md and the shared llm-wiki skill for config. It reads the vault’s manifest and pages, and scans your document folders and your Claude and Codex history folders under your home directory for the source inventory. It runs the obsidian-wiki command line for graph analysis, lint and cost reports, and the qmd command when a QMD collection is set. It writes _insights.md and log lines in the vault, and otherwise only reads. It does not fetch web pages or call remote services.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers