vault-review

vault-review is a skill for Claude Code from Evanciel/stellavault. It costs 68 tokens per session (372 once invoked), scanned A, original, MIT.

A daily knowledge-review assistant for a Stellavault, a personal notes collection. It finds notes that may be fading from memory and weakly connected areas of knowledge.

In plain words
What is it for?
Use it to choose two or three notes to revisit, identify one knowledge gap or missing connection, and suggest a concrete review action.
Why use it?
It turns a large notes collection into a short reminder of what deserves attention next.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the stellavault plugin — 3 skills, 1 MCP server shipped together

Good fit Use it to choose two or three notes to revisit, identify one knowledge gap or missing connection, and suggest a concrete review action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evanciel/stellavault/vault-review
Install

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.

Any agent
npx skills add Evanciel/stellavault --skill vault-review
Clone the repo
git clone --depth 1 https://github.com/Evanciel/stellavault

Made for: Claude Code.

Or install stellavault, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

agentmods badge for vault-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/evanciel/stellavault/vault-review/github.svg)](https://agentmods.dev/skills/evanciel/stellavault/vault-review)
Your own site
<a href="https://agentmods.dev/skills/evanciel/stellavault/vault-review"><img src="https://agentmods.dev/badge/skills/evanciel/stellavault/vault-review/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.

agentmods 80×15 button for vault-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/evanciel/stellavault/vault-review"><img src="https://agentmods.dev/badge/skills/evanciel/stellavault/vault-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.00372
Opus 5 $0.00034 $0.00186
Sonnet 5 $0.00014 $0.00074
Haiku 4.5 $0.00007 $0.00037

Measured 12d ago against content hash 939adce93f00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vault-review 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 12d 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.

plugins/stellavault/skills/vault-review/SKILL.md · 24 lines

What it actually says

Knowledge review (decay + gaps)

Turn Stellavault's memory model into a short, actionable review. This is the one thing a plain notes app cannot do: it knows what the user is about to forget.

Steps

  1. Call get-learning-path — it returns notes ranked by how close they are to being forgotten (FSRS retrievability).
  2. Call detect-gaps — weakly-linked or underdeveloped areas of the vault.
  3. Produce a compact review, in the user's language:
    • Revisit now (2-3 notes): title + one line on why it matters and what it connects to. Prefer notes that are both decaying AND central (linked from others).
    • One gap worth closing: a single concrete suggestion ("[[A]] and [[B]] cover the same system but aren't linked", "topic X has 5 fragments and no summary note").
  4. End with one question inviting action ("want me to pull up the first one?") — then stop. If the user picks a note, fetch it with get-document and summarize what they likely forgot.

Rules

  • Keep the whole review under ~15 lines. This is a nudge, not a report.
  • Read-only: never write, rename, or "fix" notes in this skill.
  • If both tools return nothing actionable, say the vault looks healthy in one line — do not pad.
Changes

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.

  1. 12d ago First seen · 24 lines · 68 tokens per session scan A 939adce93f00

Subscribe to this mod's changes

vault-review is a skill published in the GitHub repository Evanciel/stellavault (4 stars, last pushed 18d ago), licensed MIT. It adds 68 tokens to every session and 372 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.

Related

Other skills, from other repositories

cortex-memory

Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.

Fozikio/cortex-engine · 36 tokens

sibyl

Persistent memory and task coordination for this project. Invoke for any prompt about past work, project state, in-progress tasks, prior decisions, gotchas, or capturing a non-obvious learning. Also covers semantic search across project knowledge and external docs.

hyperb1iss/sibyl · 52 tokens

brainctl

Unified agent memory CLI — read, write, search, and maintain the shared memory spine (brain.db). Use for persistent cross-session memory, knowledge graph, event logging, decisions, affect tracking, and consolidation.

TSchonleber/brainctl · 45 tokens

learn

Batch knowledge ingestion from external sources (a folder, a codebase, a docs tree, a set of files). Plans the ingestion as a list of well-shaped nodes with reconciled keywords, shows the user the plan for approval, then executes idempotently. Triggered by /learn, "ingest this folder into memory", "porta questo codice…

AEndrix03/Graft · 124 tokens

graft

Persistent graph memory across conversations. The master skill — search BEFORE answering non-trivial questions, save AFTER solving non-obvious ones. Three companion skills handle the heavy lifting: /memoryze (save with smart granularity), /recall (escalating search query→retrieve→explore), /memory-audit (read-only…

AEndrix03/Graft · 116 tokens

graft-init

One-shot configurator that wires graft into a CLAUDE.md (global or project-local) so the agent uses the persistent memory consistently in every session. Asks the user 4 short questions (scope, caching, retrieve strategy, save strategy), then writes a … block into the chosen CLAUDE.md. Triggered by /graft-init…

AEndrix03/Graft · 119 tokens