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.
npx agentmods add skills/thoreinstein/gemini-obsidian/compoundnpx skills add thoreinstein/gemini-obsidian --skill compoundgit clone --depth 1 https://github.com/thoreinstein/gemini-obsidianWrote 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/skills/thoreinstein/gemini-obsidian/compound)<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>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 | $0.00042 | $0.00413 |
| Opus 5 | $0.00021 | $0.00206 |
| Sonnet 5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00041 |
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.
What it actually says
Compound Knowledge Promotion
Identify knowledge that has crystallized across multiple projects and promote it to a global Engineering/ note.
Workflow
-
Scan project knowledge dirs — Call
obsidian_list_noteswithsubfolder: "working". Filter results to paths matchingworking/*/knowledge/*.md. -
Semantic clustering — For each knowledge note path, call
obsidian_rag_querywith the note filename (without extension) as query,limit: 8. Track which notes appear in results from 2+ different projects — these are candidates. -
Read candidates — Call
obsidian_read_noteon shortlisted files. Look for shared definitions, patterns, or insights worth generalizing. -
Draft global note — Compose a new
Engineering/<ConceptName>.mdwith:- Frontmatter:
type: concept,created: <today> - Synthesized body (not copy-paste — rewrite for clarity)
## Source Notessection with[[wikilinks]]back to originating notes
- Frontmatter:
-
Show draft to user — Present the proposed note content and path before creating. Ask for confirmation.
-
Create on approval — Call
obsidian_create_notewith the approved content. -
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_queryreturns no results, suggest running/indexfirst - If no notes appear in 2+ projects, report that and suggest manual promotion
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.
- 5d ago First seen · 46 lines · 42 tokens per session scan A d5e3b1e05af0
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.
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.
compound
Extract lessons, patterns, and architectural truths to compound team knowledge.
expert-librarian
An expert librarian that helps you organize, search, and synthesize your Readwise highlights and documents.
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"…
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…
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…