What is when-to-consult?

A guide for deciding when an AI assistant should consult the OVP knowledge vault and which vault tool to use. It covers searches, structured lookups, source-backed questions, citation checks, and operational checks.

Use it to choose between asking, searching, filtering, checking claims, reading themes, checking pipeline status, and diagnosing vault health.

It prevents using the wrong lookup method or presenting unsupported vault-based answers. It also explains when the vault should be skipped, such as for general knowledge or ordinary repository questions.

when-to-consult — Skill for Claude Code and Codex by fakechris

Install

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.

Any agent

npx skills add fakechris/obsidian_vault_pipeline --skill when-to-consult

Clone the repo

git clone --depth 1 https://github.com/fakechris/obsidian_vault_pipeline

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fakechris/obsidian_vault_pipeline/when-to-consult/github.svg)](https://agentmods.dev/skills/fakechris/obsidian_vault_pipeline/when-to-consult)

Your own site

<a href="https://agentmods.dev/skills/fakechris/obsidian_vault_pipeline/when-to-consult"><img src="https://agentmods.dev/badge/skills/fakechris/obsidian_vault_pipeline/when-to-consult/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fakechris/obsidian_vault_pipeline/when-to-consult"><img src="https://agentmods.dev/badge/skills/fakechris/obsidian_vault_pipeline/when-to-consult.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 339 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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00339
Opus 5	$0.00018	$0.00169
Sonnet 5	$0.00007	$0.00068
Haiku 4.5	$0.00004	$0.00034

Measured 2d ago against content hash 700d7e2ddcdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

when-to-consult 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 2d 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.

skills/when-to-consult/SKILL.md · 35 lines

What it actually says

When to Consult OVP

Use this skill to choose the right OVP MCP surface — or to skip the vault when it cannot help.

Prefer the vault (call MCP)

Need	Skill / tool
Natural-language answer with verified receipts	`ask`
Structured inventory (kind/tag/date/entity)	`find`
Keyword / phrase hunt	`search`
Audit a `[claim:…]` citation	`claim`
Wiki-style theme narrative	`theme-page`
Pipeline pulse	`status`
Health / index problems	`doctor`
Save a note into the vault safely	`capture-drop`

Answer without the vault

Pure coding / repo questions about this Rust workspace (use AGENTS.md, crates, tests)
General knowledge unrelated to the operator’s notes
When ask already returned honest empty coverage — do not fabricate vault citations

Hygiene

Set OVP_VAULT_ROOT (example: /path/to/your/vault); never embed secrets in MCP config
Run ovp2 mcp --vault-root "$OVP_VAULT_ROOT" (see root mcp.json)
After content changes, operators may need ovp2 index before search/ask quality recovers
Keep ops conventions in skills + docs/ops/; do not casually delete operator docs

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.

2d ago First seen · 35 lines · 36 tokens per session scan A 700d7e2ddcdb

Subscribe to this mod's changes

when-to-consult is a skill published in the GitHub repository fakechris/obsidian_vault_pipeline (163 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 339 once invoked, about $0.0002 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 2026-09-08.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens