Borrowing it
Nothing to install: this file belongs to dgraziosi/foundation. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dgraziosi/foundation/main/.agents/skills/vault-health/SKILL.mdgit clone --depth 1 https://github.com/dgraziosi/foundationWrote 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/dgraziosi/foundation/vault-health)<a href="https://agentmods.dev/skills/dgraziosi/foundation/vault-health"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/vault-health/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/dgraziosi/foundation/vault-health"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/vault-health.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 | $0.00052 | $0.00686 |
| Opus 5 | $0.00026 | $0.00343 |
| Sonnet 5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
vault-health 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
You are not the host script. Do not start Postgres or the app. Do not install a schedule. Do not wake a bot to curl /health on a timer. That job is [`scripts/keep-vault-up.sh`](../../../scripts/keep-vault-up.sh). It star How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault health
You are writing the weekday vault-health report. The user can run this, or attach it to Vault Keeper.
Read docs/VAULT_HEALTH.md and follow the written-report section. Call bootstrap if you need the current tools.
You are not the host script. Do not start Postgres or the app. Do not install a schedule. Do not wake a bot to curl /health on a timer. That job is scripts/keep-vault-up.sh. It starts the two host programs, curls /health, and fails on an empty cluster next to a real one. First-day 0 user records is healthy. /health green is not enough.
The user is the human who runs this vault on this machine. A vault is this running instance (FOUNDATION_DATA + Postgres). Do not call the graph “the Vault.”
Schedule and voice
Weekdays, 9:15 user-local. If every check passes, stay quiet. Ping the user only on failure.
Keeping the vault up is the host script on this machine’s own schedule. Not this pass. Quiet when health is green and the live folder is the intended real cluster.
User config (fill in; blank means skip that check)
- MCP / health base: http://127.0.0.1:8787
- FOUNDATION_DATA: (from .env; default ./data) — this path is the vault
- Well-known node ids or titles: (optional; skip if unset)
- Backup path: BACKUP_ROOT (default: sibling of the data dir; skip only if the user unset it)
- Backup stale after: 48 hours (only if BACKUP_ROOT is set)
Checks (in order)
- GET /health — HTTP 200 and { ok: true, service: "foundation", db: "up" }. If this fails, ping. Do not start the host programs.
- FOUNDATION_DATA is the real vault: not an agent profile or memory directory, and not an empty leftover Postgres cluster (missing/empty postgres dir, no PG_VERSION, host cannot read PG_VERSION, empty live next to a backup or second tree that has people). Do not mkdir the live path on that miss. A first-day vault with seed types and 0 user records is healthy unless well-known nodes were configured.
- If well-known nodes are configured, get/search them and confirm they exist (not soft-deleted). If none configured, skip.
- Backup path defaults to BACKUP_ROOT. Skip only if the user unset it. If set, the path is present and the newest artifact is newer than 48 hours. Newest artifact may be
foundation-YYYYMMDD.sql.age. Health checks; it does not dump. Nag if the dump is missing or old.
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.
- 8d ago Changed 39838947101a
- 11d ago First seen · 40 lines · 52 tokens per session scan A 6c5d12417bc7
vault-health is a skill published in the GitHub repository dgraziosi/foundation (2 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 686 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…