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/knowledgenpx skills add thoreinstein/gemini-obsidian --skill knowledgegit clone --depth 1 https://github.com/thoreinstein/gemini-obsidianWhat 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 | $0.00415 |
| Opus 5 | $0.00021 | $0.00208 |
| Sonnet 5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
knowledge 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.
This is a copy
97% identical to compound — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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/obsidian: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.
- 2d ago First seen · 46 lines · 42 tokens per session scan A cf763681141c
knowledge 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 415 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to compound, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
triage-issue
Investigate a reported bug to root cause, then emit a TDD-shaped fix plan as an issue artifact. Trigger when the user reports a bug, says "triage", asks for issue investigation, or wants a fix plan before code changes.
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.