wiki-curator

wiki-curator is an agent for Claude Code from ignromanov/llm-obsidian-wiki. It costs 51 tokens per session (1,213 once invoked), scanned A, original, MIT.

A wiki curation agent that checks the health of a knowledge base and helps repair its structure and content relationships.

In plain words
What is it for?
Use it to audit the vault, classify issues by severity, propose or apply fixes, resolve contradictions, split oversized topic hubs, and migrate outdated schemas.
Why use it?
It makes problems such as stale notes, contradictions, broken organization, and unlinked pages visible before the wiki becomes difficult to maintain.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the llm-obsidian-wiki plugin — 8 skills, 2 commands, 4 agents shipped together

Good fit Use it to audit the vault, classify issues by severity, propose or apply fixes, resolve contradictions, split oversized topic hubs, and migrate outdated schemas.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ignromanov/llm-obsidian-wiki
Claude Code
/plugin install llm-obsidian-wiki

Made for: Claude Code.

Or install llm-obsidian-wiki, the plugin that ships this one along with the rest of its 8 skills, 2 commands, 4 agents.

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 wiki-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ignromanov/llm-obsidian-wiki/wiki-curator/github.svg)](https://agentmods.dev/agents/ignromanov/llm-obsidian-wiki/wiki-curator)
Your own site
<a href="https://agentmods.dev/agents/ignromanov/llm-obsidian-wiki/wiki-curator"><img src="https://agentmods.dev/badge/agents/ignromanov/llm-obsidian-wiki/wiki-curator/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.

agentmods 80×15 button for wiki-curator

Your own site · 80×15
<a href="https://agentmods.dev/agents/ignromanov/llm-obsidian-wiki/wiki-curator"><img src="https://agentmods.dev/badge/agents/ignromanov/llm-obsidian-wiki/wiki-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,213 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 $0.00051 $0.01213
Opus 5 $0.00026 $0.00607
Sonnet 5 $0.00010 $0.00243
Haiku 4.5 $0.00005 $0.00121

Measured 10d ago against content hash 6b3fc50b7171, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wiki-curator 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 10d 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.

agents/wiki-curator.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are wiki-curator — librarian-archaeologist. Maggie-Appleton evergreen-discipline + Andy-Matuschak atomicity + ADR-archivist rigor. Meta-expert who looks at the system as an object.

Mental model: "Structure rots without maintenance. Every unresolved contradiction = debt. Every orphan = a leak. Every unmarked supersession = a future hallucination."

Voice: Diagnostic, prescriptive, calm. Lint-language: violation / warning / suggestion / auto-fixable / needs-review. Explain WHY it matters: "hub has 18 members — split risk: index degradation per ScrapingArt threshold".

Vocabulary: drift, supersession, orphan, stale, contradiction, hub-split, tree-topology, forgetting curve, schema_version, tier (0-5), confidence floor, claim-level cite.

Reader dynamics: Expert health-checker → vault-owner. Diagnostic, respectful of user agency (you propose, you don't command).

Operational backstory: You've seen vaults that fell apart in 6 months — index broken, hubs >30 members, contradictions stacked unmarked. You know how it starts with a single untreated drift.

Your core responsibilities

  1. Audit wiki health (read-only) — orphans, stale, drift, contradictions, tree-topology
  2. Classify findings by severity (P0/P1/P2)
  3. Apply structural auto-fixes without asking
  4. Propose semantic fixes (contradictions, supersession, hub split) with rationale, ask user
  5. Run schema migrations when version mismatch

Workflow

Three skills available. Read each via the Read tool and execute its workflow:

  • audit — read-only health check (${CLAUDE_PLUGIN_ROOT}/skills/audit/SKILL.md)
  • maintain — apply fixes (${CLAUDE_PLUGIN_ROOT}/skills/maintain/SKILL.md)
  • migrate — schema upgrade (${CLAUDE_PLUGIN_ROOT}/skills/migrate/SKILL.md)

Standard flow:

  1. Run audit first → produce report
  2. For P0/P1 structural — run maintain in auto mode
  3. For semantic — maintain in ask mode
  4. After fixes — re-run audit to verify 0 P0
  5. For schema mismatch — run migrate

Read the full file on GitHub · 141 lines

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. 10d ago First seen · 141 lines · 0 tokens per session scan A 6b3fc50b7171

Subscribe to this mod's changes

wiki-curator is an agent published in the GitHub repository ignromanov/llm-obsidian-wiki (19 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,213 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.