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/vm-updatenpx skills add owrede/vault-memory --skill vm-updategit 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 | $0.00098 | $0.01449 |
| Opus 5 | $0.00049 | $0.00724 |
| Sonnet 5 | $0.00020 | $0.00290 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
vm-update scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 3 | Fetch latest release tag from GitHub API | `curl https://api.github.com/repos/owrede/vault-memory/releases/latest`. Falls back to `VM_UPDATE_LATEST_VERSION` env var for testing / offline. | How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/vm-update — Upgrade the vault-memory Obsidian plugin
Out-of-band updater for installations that were sideloaded via vm-install.
Checks GitHub Releases for a version newer than what is on disk; if a newer
release is published, downloads + verifies it and swaps it into place
atomically.
When to invoke
- User runs
/vm-update(primary trigger) - User says "update vault-memory plugin", "upgrade vault-memory", "Plugin aktualisieren"
- After a new vault-memory v2.x release lands and the user wants to pick it up
Release prerequisites
IMPORTANT: This skill queries a hard-coded GitHub Releases endpoint. Before v2.0.0 (and any subsequent release) is published, the API returns 404 — the release artifacts referenced by this skill DO NOT exist yet. They will be published during Phase 8 release prep.
Required release artifacts (publisher checklist, same as vm-install):
| Asset | Purpose |
|---|---|
vault-memory-plugin-<version>.tar.gz |
Plugin tarball with manifest.json, main.js, styles.css, versions.json at the archive root |
manifest.sha256 |
Single-line SHA-256 hex digest of the tarball |
The release URL template is set via the RELEASE_URL_PLACEHOLDER constant
near the top of update.sh. The constant is marked with a # TODO: replace placeholder before publishing comment. The latest release lookup uses
https://api.github.com/repos/owrede/vault-memory/releases/latest; override
the tarball + checksum URLs at test time via VM_UPDATE_RELEASE_URL and
VM_UPDATE_SHA256_URL, and override the release-version lookup itself via
VM_UPDATE_LATEST_VERSION.
When to invoke
- User runs
/vm-update(primary trigger) - User says "update vault-memory plugin", "upgrade vault-memory", "Plugin aktualisieren"
- After a new vault-memory v2.x release lands
What this skill does
7 idempotent checkpoints mirroring vm-install, scoped to the update path.
| # | Checkpoint | Action |
|---|---|---|
| 1 | Discover Obsidian vault | Same logic as vm-install. Honors VAULT_PATH. |
| 2 | Read installed manifest.json.version |
Parse <vault>/.obsidian/plugins/vault-memory/manifest.json. If missing, abort with "Plugin not installed — run /vm-install first." |
| 3 | Fetch latest release tag from GitHub API | curl https://api.github.com/repos/owrede/vault-memory/releases/latest. Falls back to VM_UPDATE_LATEST_VERSION env var for testing / offline. |
| 4 | Compare versions (semver) | If installed >= latest → exit 0 with "Already up to date". |
| 5 | Download + verify SHA-256 | Same atomic flow as vm-install (download → checksum → mismatch aborts before extraction). |
| 6 | Atomic replace | Extract into .NEW, swap in via mv, delete .OLD. Failure leaves the prior install intact. |
| 7 | Prompt user to reload | Print: "Reload Obsidian (Cmd+R / Ctrl+R) or disable+enable the plugin in Settings → Community Plugins to pick up the upgrade." |
What ships with it
2 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.
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 · 112 lines · 98 tokens per session scan A c26324483dfe
vm-update is a skill published in the GitHub repository owrede/vault-memory (0 stars, last pushed 24d ago), licensed MIT. It adds 98 tokens to every session and 1,449 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.