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/owrede/vault-memory/helpnpx skills add owrede/vault-memory --skill helpgit clone --depth 1 https://github.com/owrede/vault-memoryWhat 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 | $0.00053 | $0.00600 |
| Opus 5 | $0.00026 | $0.00300 |
| Sonnet 5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
help 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/vmem:help — vmem command surface
vmem is the local-first agentic-memory layer for Obsidian. The marketplace plugin exposes the following verbs:
| Verb | What it does |
|---|---|
/vmem:install |
One-call install of vault-memory in this vault (CLI + Obsidian plugin + example contracts). Walks 9 idempotent checkpoints. |
/vmem:health |
Read-only diagnostic — checks CLI version, Ollama, configured models, every vault DB's integrity, uncommitted WAL state, and the MCP smoketest. PASS/WARN/FAIL per dimension. |
/vmem:reindex |
Rebuild the vector index for the current vault. Full re-index by default; pass --incremental for fast catch-up. |
/vmem:help |
(You are here.) |
Common workflows
| User intent | Command |
|---|---|
| First time setting up vault-memory in a vault | /vmem:install |
| Obsidian plugin shows "CLI not found" or "Could not load stats" | /vmem:install (re-runs the seeder for data.json and [plugin] enabled) |
| Memory tools disappeared after a system update | /vmem:health to diagnose, then /vmem:install if needed |
| Search returns stale results after large note import | /vmem:reindex --incremental |
| Switching embedding models or recovering from corrupt DB | /vmem:reindex (full) |
| Upgrade from v1.0.0 → v2 | /vmem:install — detects the older version, offers backup + destructive-confirmed upgrade path |
Related (in agent context, not slash surface)
After /vmem:install and a Claude Code restart, the agent has access to the mcp__vault-memory__* tool family:
mcp__vault-memory__search_hybrid— semantic + BM25 + RRFmcp__vault-memory__read_note/write_note/update_frontmattermcp__vault-memory__list_backlinks/list_forward_links- v2-only: typed-edge graph (
expand,cluster), briefs, task contracts
How to execute
This is an informational skill — print the table above and stop. No script side-effects.
bash "$CLAUDE_PROJECT_DIR/.claude/skills/help/help.sh"
Or just render the markdown table inline.
What ships with it
1 file 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.
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.
- yesterday First seen · 45 lines · 53 tokens per session scan A 56f068294dfa
help is a skill published in the GitHub repository owrede/vault-memory (0 stars, last pushed 23d ago), licensed MIT. It adds 53 tokens to every session and 600 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…