Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/richfrem/agent-plugins-skillsnpx agentmods add skills/richfrem/agent-plugins-skills/managing-obsidian-vaultsWrote 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/richfrem/agent-plugins-skills/managing-obsidian-vaults)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/managing-obsidian-vaults"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/managing-obsidian-vaults/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.
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/managing-obsidian-vaults"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/managing-obsidian-vaults.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00102 | $0.01369 |
| Opus 5.5 | $0.00041 | $0.00548 |
| Sonnet 5.5 | $0.00020 | $0.00274 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
managing-obsidian-vaults 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Obsidian Vaults
Read the matching workflow before acting. Run commands from this skill's folder.
Use explicit vault/wiki roots; set AGENT_MEMORY_PROJECT_ROOT for the consumer project.
Contents
Interaction · Constraints · Workflow · Quick start · Verification
Interaction
Treat slash-invocation arguments as supplied requirements; do not ask for them again.
For vault/wiki setup, read guided setup; for combined layers, read Super-RAG setup, including when wiki is not selected. Run the conversation here: reuse known choices, ask one unresolved question per turn, preview changes, merge existing config and validate only selected layers. Continue sibling skill modes inline with shared answers and scope; never launch a setup agent. Explicit note/query operations go directly to their modes.
Constraints
- Never move raw source content. Confirm external directory scans before discovery.
- Preview initialization with
--validate-only; preserve existing project configuration. - Notes/Bases require lossless YAML, staged atomic writes, locking and concurrent-edit checks.
- Preserve Base view definitions. Validate Canvas nodes/edges and generate unique IDs.
- Distinguish links from embeds; graph traversal is read-only and respects cache invalidation.
- Merge multi-source concepts; preserve node frontmatter, raw-source manifests and
meta/agent-memory.json. Wiki distillation emitssummary.md,bullets.md,deep.md. - Start queries at summary level, expand only as needed. Lint writes reports, not concept edits.
- Use configured low-cost cloud CLIs for wiki distillation/lint; never silently use local models.
- Vector retrieval is optional: explicitly supply its query script through
AGENT_MEMORY_VECTOR_QUERY, or delegate to managing-vector-db if installed.
Workflow
| Request | Read first |
|---|---|
| Initialize vault / register sources | Setup, onboarding |
| Markdown, wikilinks, embeds, callouts | Markdown |
| Read/create/update/append notes | Note operations |
| Read/update Base rows and cells | Bases |
| Create/edit Canvas nodes and edges | Canvas |
| Forward/backlinks, orphans, graph | Traversal |
| Build/synthesize concept wiki | Build, guide |
| Distill wiki's three summary layers | Distill, guide |
| Query summaries, bullets or full nodes | Query, guide |
| Structural audit / semantic lint | Lint, guide |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/config.yaml.template 556 B
- assets/templates/raw-sources.json.example 862 B
- assets/templates/wiki-node.template.md 410 B
- evals/evals.json 23 KB
- evals/legacy/obsidian-bases-manager/evals.json 692 B
- evals/legacy/obsidian-bases-manager/results.tsv 301 B
- evals/legacy/obsidian-canvas-architect/evals.json 731 B
- evals/legacy/obsidian-canvas-architect/results.tsv 301 B
- evals/legacy/obsidian-graph-traversal/evals.json 706 B
- evals/legacy/obsidian-graph-traversal/results.tsv 301 B
- evals/legacy/obsidian-init/evals.json 667 B
- evals/legacy/obsidian-init/results.tsv 301 B
- evals/legacy/obsidian-markdown-mastery/evals.json 652 B
- evals/legacy/obsidian-markdown-mastery/results.tsv 301 B
- evals/legacy/obsidian-query-agent/evals.json 767 B
- evals/legacy/obsidian-rlm-distiller/evals.json 685 B
- evals/legacy/obsidian-vault-crud/evals.json 638 B
- evals/legacy/obsidian-vault-crud/results.tsv 301 B
- evals/legacy/obsidian-wiki-builder/evals.json 732 B
- evals/legacy/obsidian-wiki-linter/evals.json 1.5 KB
- evals/README.md 569 B
- evals/results.tsv 73 B
- evals/task-success.json 3.5 KB
- references/acceptance-criteria.md 2.9 KB
- references/architecture-background.md 2.8 KB
- references/dependencies.md 1.7 KB
- references/interactive-setup.md 7.0 KB
- references/interactive-stack-setup.md 5.6 KB
- references/kepano-analysis-summary.md 1.7 KB
- references/obsidian-bases-manager-acceptance-criteria.md 628 B
- references/obsidian-bases-manager-fallback-tree.md 787 B
- references/obsidian-bases-manager.md 2.1 KB
- references/obsidian-canvas-architect-acceptance-criteria.md 645 B
- references/obsidian-canvas-architect-fallback-tree.md 836 B
- references/obsidian-canvas-architect.md 1.9 KB
- references/obsidian-graph-traversal-acceptance-criteria.md 690 B
- references/obsidian-graph-traversal-fallback-tree.md 877 B
- references/obsidian-graph-traversal.md 2.2 KB
- references/obsidian-init-acceptance-criteria.md 650 B
- references/obsidian-init-fallback-tree.md 1.1 KB
- references/obsidian-init.md 2.0 KB
- references/obsidian-markdown-mastery-acceptance-criteria.md 700 B
- references/obsidian-markdown-mastery-fallback-tree.md 889 B
- references/obsidian-markdown-mastery.md 2.2 KB
- references/obsidian-query-agent.md 1.8 KB
- references/obsidian-rlm-distiller.md 1.8 KB
- references/obsidian-vault-crud-acceptance-criteria.md 833 B
- references/obsidian-vault-crud-fallback-tree.md 1.1 KB
- references/obsidian-vault-crud.md 2.2 KB
- references/obsidian-vault-onboarding-guide.md 3.7 KB
- references/obsidian-wiki-builder.md 1.8 KB
- references/obsidian-wiki-linter.md 1.7 KB
- references/resource-index.md 4.3 KB
- references/safety-learnings.md 2.7 KB
- references/wiki-builder-guide.md 2.7 KB
- references/wiki-distillation-guide.md 1.7 KB
- references/wiki-linting-guide.md 2.1 KB
- references/wiki-query-guide.md 2.1 KB
- requirements.in 32 B
- requirements.txt 463 B
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 · 81 lines · 102 tokens per session scan A baa28f42a485
managing-obsidian-vaults is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 1,369 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-24.
Other skills, from other repositories
ap-sweeper
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
knowledge-graph-management
Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph.
context-recovery
Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram, Signal, and other supported channels.
iwe-restore
A recovery skill that restores an agent’s saved memory and instruction files from an exocortex backup when moving to a new computer or workspace. It shows what it found and asks for confirmation before copying files.
a2wave-memory
Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.
memory-patterns
Persistent memory patterns for moflo agents — session memory, long-term knowledge, pattern learning, and cross-session context via moflo's node:sqlite + HNSW vector store. Use when building stateful agents or assistants that need to remember across runs.