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 agents/googlicius/obsidian-steward/sub-agentsgit clone --depth 1 https://github.com/googlicius/obsidian-stewardWrote 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/agents/googlicius/obsidian-steward/sub-agents)<a href="https://agentmods.dev/agents/googlicius/obsidian-steward/sub-agents"><img src="https://agentmods.dev/badge/agents/googlicius/obsidian-steward/sub-agents.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 | $0.00000 | $0.00377 |
| Opus 5 | $0.00000 | $0.00188 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
Sub Agents 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
Sub-agents
Specialized sub-agents for spawn_subagent. Each agent is defined by a level-2 heading and a name: agent YAML fence directly below it.
YAML block (name: agent)
| Field | Required | Description |
|---|---|---|
name |
Yes | Must be agent |
id |
Yes | Unique agent id used when spawning |
description |
Yes | Short summary shown in the agent catalog |
instruction |
Yes | System prompt for the sub-agent worker |
model |
No | LLM override in provider:model format (e.g. google:gemini-2.5-flash) |
enabled |
No | false skips this agent; default true |
tools |
No | Default active tools for spawned jobs |
inactiveTools |
No | Default inactive tools the sub-agent may activate |
Only agent YAML fences are loaded. Other block types make the file invalid.
Image vision
name: agent
id: image_vision
description: Reads and analyzes images using a vision-capable model
model: google:gemini-2.5-flash
instruction: |
You are an image analysis agent in Obsidian Steward.
Your job is to read image files and answer questions about their visual content.
Use content_reading to load image files. Describe what you see accurately.
Stay focused on the delegated image task; keep responses concise.
tools:
- content_reading
inactiveTools:
- grep
- search
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 · 42 lines · 0 tokens per session scan A 6defdefcd34e
Sub Agents is an agent published in the GitHub repository googlicius/obsidian-steward (86 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 377 tokens. 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 agents, from other repositories
laravel-feature-builder
Use this agent when you need to implement new features in a Laravel application, including creating models, controllers, migrations, routes, views, and associated business logic. This agent should be used for building complete feature sets from requirements, extending existing functionality, or implementing new…
reweave-scanner
Identifies modules that need a reweave after neighboring modules were updated. Evaluates 5 triggers, prioritizes candidates, classifies reweave actions. Read-only — never edits files. Used by /process-transcripts.
knowledge-weaver
Discovers non-obvious connections between modules after transcript processing. Dual Discovery (index traversal + semantic search), Articulation Test, synthesis detection. Read-only. Used by /process-transcripts.
consistency-checker
Detects inconsistencies between new transcripts and existing wiki modules. Looks for contradictions, duplicates, outdated dates, missing wiki-links. Used by /process-transcripts.
transcript-analyzer
Analyzes transcripts from the vault backlog. Categorizes them, assigns prefix:value tags, extracts key information. Used proactively by /process-transcripts.
ceo-advisor
Strategic advisor to the vault owner, surfacing unknown unknowns from processed transcripts. Looks for warning signals, hidden opportunities, decision gaps, and trends. Run after the backlog is processed.