compound

compound is a skill for Claude Code, Codex from thoreinstein/gemini-obsidian. It costs 42 tokens per session (413 once invoked), scanned A, original, ISC.

A workflow for finding ideas that recur in notes from several software projects and turning them into a shared note in an Obsidian vault. Obsidian is a note-taking app that can link related documents.

In plain words
What is it for?
Use it to scan project knowledge notes, group related ideas, draft a general engineering concept, get approval, and save the approved note with links to its sources.
Why use it?
It reduces repeated searching and rewriting when the same engineering lesson appears in multiple projects. It also keeps links to the original notes so the shared summary can be checked.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/thoreinstein/gemini-obsidian/compound
Any agent
npx skills add thoreinstein/gemini-obsidian --skill compound
Clone the repo
git clone --depth 1 https://github.com/thoreinstein/gemini-obsidian

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 compound

README.md
[![agentmods](https://agentmods.dev/badge/skills/thoreinstein/gemini-obsidian/compound.svg)](https://agentmods.dev/skills/thoreinstein/gemini-obsidian/compound)
Your own site
<a href="https://agentmods.dev/skills/thoreinstein/gemini-obsidian/compound"><img src="https://agentmods.dev/badge/skills/thoreinstein/gemini-obsidian/compound.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.00413
Opus 5 $0.00021 $0.00206
Sonnet 5 $0.00008 $0.00083
Haiku 4.5 $0.00004 $0.00041

Measured 5d ago against content hash d5e3b1e05af0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compound 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 5d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

  • compound — 100% identical, 0 lines differ
  • knowledge — 97% identical, 4 lines differ
skills/compound/SKILL.md · 46 lines

What it actually says

Compound Knowledge Promotion

Identify knowledge that has crystallized across multiple projects and promote it to a global Engineering/ note.

Workflow

  1. Scan project knowledge dirs — Call obsidian_list_notes with subfolder: "working". Filter results to paths matching working/*/knowledge/*.md.

  2. Semantic clustering — For each knowledge note path, call obsidian_rag_query with the note filename (without extension) as query, limit: 8. Track which notes appear in results from 2+ different projects — these are candidates.

  3. Read candidates — Call obsidian_read_note on shortlisted files. Look for shared definitions, patterns, or insights worth generalizing.

  4. Draft global note — Compose a new Engineering/<ConceptName>.md with:

    • Frontmatter: type: concept, created: <today>
    • Synthesized body (not copy-paste — rewrite for clarity)
    • ## Source Notes section with [[wikilinks]] back to originating notes
  5. Show draft to user — Present the proposed note content and path before creating. Ask for confirmation.

  6. Create on approval — Call obsidian_create_note with the approved content.

  7. Report cross-links — List which project knowledge notes should now add [[ConceptName]] to avoid re-discovering this knowledge next time.

Arguments

Optional topic hint: /compound authentication patterns

Tips

  • If obsidian_rag_query returns no results, suggest running /index first
  • If no notes appear in 2+ projects, report that and suggest manual promotion
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. 5d ago First seen · 46 lines · 42 tokens per session scan A d5e3b1e05af0

Subscribe to this mod's changes

compound is a skill published in the GitHub repository thoreinstein/gemini-obsidian (102 stars, last pushed 1mo ago), licensed ISC. It adds 42 tokens to every session and 413 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.

Related

Other skills, from other repositories

context-optimize

Skill "context-optimize" from Joonghyun-Lee-Frieren/oh-my-antigravity, covering purpose, trigger, workflow, output template and context health.

Joonghyun-Lee-Frieren/oh-my-antigravity · 0 tokens

compound

Extract lessons, patterns, and architectural truths to compound team knowledge.

thoreinstein/beads-workflow · 14 tokens

expert-librarian

An expert librarian that helps you organize, search, and synthesize your Readwise highlights and documents.

thoreinstein/readwise · 25 tokens

memory-management

This skill should be used when the user wants to "persist agent state", "remember past conversations", "short-term memory", "long-term memory", "session management", "vector database for agents", "agent memory", "context window management", "store user preferences", "recall previous interactions", "stateful agents"…

hajekim/agentic-design-patterns-extension · 418 tokens

qmd

Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…

breferrari/obsidian-mind · 142 tokens

neo4j-agent-memory-skill

Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…

neo4j-contrib/neo4j-skills · 223 tokens