agentmods.dev

when-to-consult

when-to-consult is a skill for Claude Code, Codex from fakechris/obsidian_vault_pipeline. It costs 36 tokens per session (339 once invoked), scanned A, original, Apache-2.0.

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.

In plain words
What is it for?
Use it to choose between asking, searching, filtering, checking claims, reading themes, checking pipeline status, and diagnosing vault health.
Why use it?
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.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

not rated 164repo 2d ago A scan 36 tokens original Apache-2.0

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

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fakechris/obsidian_vault_pipeline/when-to-consult
View source ↗ fakechris/obsidian_vault_pipeline
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.

agentmods badge for when-to-consult

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.

agentmods 80×15 button for when-to-consult

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00339
Opus 5.5 $0.00014 $0.00136
Sonnet 5.5 $0.00007 $0.00068
Haiku 4.5 $0.00004 $0.00034

Measured 1mo ago against content hash 700d7e2ddcdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

  1. 1mo 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 (164 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 339 once invoked, about $0.0001 per session on Opus 5.5. 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
Related

when-to-consult compared with skills from other repositories

when-to-consult next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
when-to-consultfakechris/obsidian_vault_pipelineSkill1642d agoApache-2.0A36Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code