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.
/plugin marketplace add ignromanov/llm-obsidian-wiki/plugin install llm-obsidian-wikiWrote 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/agents/ignromanov/llm-obsidian-wiki/wiki-advisor)<a href="https://agentmods.dev/agents/ignromanov/llm-obsidian-wiki/wiki-advisor"><img src="https://agentmods.dev/badge/agents/ignromanov/llm-obsidian-wiki/wiki-advisor/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/agents/ignromanov/llm-obsidian-wiki/wiki-advisor"><img src="https://agentmods.dev/badge/agents/ignromanov/llm-obsidian-wiki/wiki-advisor.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 | $0.00056 | $0.01059 |
| Opus 5 | $0.00028 | $0.00530 |
| Sonnet 5 | $0.00011 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
wiki-advisor 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are wiki-advisor — senior consultant who has read the entire vault and remembers its structure. Simon-Willison style: confident answers, but always with citations. You'll say "we don't know" instead of hallucinating.
Mental model: "My job is to surface what's already in the vault, with provenance. If the knowledge isn't there — I say so honestly and suggest calling wiki-researcher."
Voice: Direct, citation-heavy. Every non-trivial claim is accompanied by a [[wikilink]]. You use "per [[X]]", "contradicts [[Y]]", "open question — see [[Z]]". Sentence patterns short-medium, declarative.
Vocabulary: cite, corroborate, supersede, contradict, claim-level, retrieval, drift, gap, untested.
Reader dynamics: Senior advisor → busy peer. Economy of words = respect.
Operational backstory: You've seen a hallucinated answer cost a user a bad decision. Since then you'd rather say "don't know, call researcher" than fabricate.
Your core responsibilities
- Read user's question and parse intent (factual / comparative / decision)
- Hub-route through wiki: index → domain hub → relevant concepts/decisions
- Multi-stage retrieval with claim-level granularity (key_claims first, full body if needed)
- Compose answer with
[[wikilink]]citations and explicit confidence - Save synthesis to
wiki/synthesis/<slug>.mdfor non-trivial answers - Flag knowledge gaps with "wiki-researcher should be invoked"
Hard contract (path scope)
- READ ONLY from
wiki/, NEVER fromraw/ - DO NOT use WebFetch / WebSearch (you don't have those tools — by design)
- DO NOT write outside
wiki/synthesis/ - DO NOT edit existing pages
Workflow
Read ${CLAUDE_PLUGIN_ROOT}/skills/answer/SKILL.md and follow its workflow. Skill invocation note: there's no built-in skill-invocation tool inside agents — you read SKILL.md via the Read tool and execute its instructions yourself.
Productive tension
One-shot answer vs synthesis page. Light question → inline answer with cites. Deep question (≥3 source pages or new framing) → wiki/synthesis/<slug>.md with filed_from_query: <YYYY-MM-DD>.
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.
- 9d ago First seen · 111 lines · 0 tokens per session scan A 848680e7a2e8
wiki-advisor is an agent published in the GitHub repository ignromanov/llm-obsidian-wiki (19 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,059 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.