idea-discovery

idea-discovery is a command for Claude Code from eugeniughelbur/obsidian-second-brain. It costs 30 tokens per session (771 once invoked), scanned A, original, MIT.

A command for finding promising next projects or directions from ideas, unanswered project questions, and research notes in an Obsidian vault.

In plain words
What is it for?
Use it to identify several candidate directions, see the notes supporting each one, and choose a small next step.
Why use it?
It turns scattered notes into a short, explainable ranking instead of leaving you to decide what to work on from scratch.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the obsidian-second-brain plugin — 1 skill, 47 commands, 3 hooks shipped together

Good fit Use it to identify several candidate directions, see the notes supporting each one, and choose a small next step.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/eugeniughelbur/obsidian-second-brain/idea-discovery
About the project

obsidian-second-brain turns an Obsidian vault into persistent, searchable memory for Claude Code and other command-line coding agents, storing knowledge as linked Markdown notes. It is for developers, founders, writers, and researchers who want agents to retain project context across sessions. Its catalogue entries provide commands, hooks, a plugin, a skill, and instructions for capturing, finding, and maintaining that memory.

eugeniughelbur/obsidian-second-brain · 4,376 stars · on GitHub · eugeniughelbur.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/eugeniughelbur/obsidian-second-brain

Made for: Claude Code.

Or install obsidian-second-brain, the plugin that ships this one along with the rest of its 1 skill, 47 commands, 3 hooks.

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 idea-discovery

README.md
[![agentmods](https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/idea-discovery/github.svg)](https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/idea-discovery)
Your own site
<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/idea-discovery"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/idea-discovery/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 idea-discovery

Your own site · 80×15
<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/idea-discovery"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/idea-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 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 $0.00030 $0.00771
Opus 5 $0.00015 $0.00385
Sonnet 5 $0.00006 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 10d ago against content hash 1f03e1ef08d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

idea-discovery 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.

commands/idea-discovery.md · 28 lines

What it actually says

Use the obsidian-second-brain skill. Execute /idea-discovery:

Answers "what is worth doing next" from material already in the vault. Distinct from /obsidian-emerge (which names unstated patterns) and /obsidian-graduate (which promotes one chosen idea into a project) - this ranks several candidate directions so you can pick one.

  1. Gather candidate signals - list and grep exhaustively (see the anti-fabrication rule):
    • Ungraduated ideas in the ideas folder (resolved per references/folder-map.md - wiki-style wiki/concepts/, Obsidian-style Ideas/; status captured or exploring, not yet graduated).
    • Open questions in active project notes (Open Questions sections, unresolved decisions).
    • Orphan research notes in Research/ that no project links to.
  2. Rank the candidates by a simple, stated heuristic: recency (touched recently), pull (how many notes reference or depend on it), and momentum (does anything already build toward it). State the heuristic in the output so the ranking is auditable.
  3. For each of the top 3-5, write: the candidate, why now, the [[source notes]], and the smallest next step that would move it forward.
  4. Optionally suggest running /research [topic] on a candidate to pull external signal before committing, or /obsidian-graduate to promote one into a full project.
  5. Save the shortlist to the ideas folder resolved in step 1, as YYYY-MM-DD - discovery.md (type: synthesis, tagged [synthesis, thinking, idea-discovery]) with source links in frontmatter. Do NOT auto-graduate anything - this command only surfaces and ranks.

AI-first rule: Every note created or updated by this command MUST follow references/ai-first-rules.md - ## For future agent preamble, rich frontmatter (type, date, tags, ai-first: true, plus type-specific fields), recency markers per external claim, mandatory [[wikilinks]] for every person/project/concept referenced, sources preserved verbatim with URLs inline, and confidence levels where applicable. If that path does not resolve from your working directory, search upward for it; if you still cannot read it, say so before writing rather than producing a note that silently skips the rule. The vault is for future agent retrieval - not human reading.

Anti-fabrication: Rank only real candidates found in the vault - never invent an idea, an open question, or a research note to pad the shortlist. Enumerate the ideas folder, project Open Questions, and orphan research exhaustively rather than sampling. See the anti-fabrication and search-completeness hard rules in references/ai-first-rules.md.

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 · 28 lines · 30 tokens per session scan A 1f03e1ef08d1

Subscribe to this mod's changes

idea-discovery is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,376 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 771 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 2026-08-30.