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/.cursor/skills/verify-foundation/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/verify-foundation)<a href="https://agentmods.dev/skills/dgraziosi/foundation/verify-foundation"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/verify-foundation.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.04530 |
| Opus 5 | $0.00034 | $0.02265 |
| Sonnet 5 | $0.00014 | $0.00906 |
| Haiku 4.5 | $0.00007 | $0.00453 |
Grade C, and why
verify-foundation scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Cleanup may `rm -rf` only `/tmp/foundation-verify-<run-id>` when the recorded data dir is that folder or its `data/` child. A `VERIFY_DATA_DIR` that is a direct child of `/tmp` is that run root. Its parent is `/tmp` and Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS http://127.0.0.1:8787/health How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Foundation (Viewer)
Foundation is a life graph that models the user so bots can help with life goals. Viewer is the human UI — a window on one vault. It writes journal only (Today + autosave). It is not a personal-knowledge-management app and not harness chat-memory.
This skill is for the next agent, read cold. The person using a clone is the user. Stay on product. No live vault contents, no staff names, no personal data.
pstack's generic generator writes .cursor/skills/verify-*. This repo's product recipes stay under .agents/skills/. Do not copy vault-health, Dream, or other product folders here.
Product words
- graph — live records (nodes) and edges
- ontology — types and how they connect
- MCP — how a bot talks to the graph (
http://127.0.0.1:8787/mcp) - Viewer — the human window (
http://127.0.0.1:8788/view). Writes journal only. - vault — one instance (
FOUNDATION_DATA+ host Postgres) - record — the node
- user — the human who runs this vault on this machine
Do not write a live personal vault into git. Do not reintroduce Compose as install. Host programs: Postgres 16 on PATH (initdb, pg_ctl, psql) plus the app (pnpm start). The package name for Postgres is unknown in this repo — do not guess an installer.
Journal write is on this branch. Home always offers Today, even at journal count 0. Today (or /view/journal/today) creates today's journal if none is live, then the page autosaves title and body. An empty title shows Keep a title. Unlock title is Unlock. The field is the vault key. The error is That key did not unlock. Other types stay display-only. Bots still write everything else through MCP.
Launch
Official start on the machine that runs a vault (from the clone root):
cp .env.example .env
# the human sets FOUNDATION_API_KEY to a long random string; do not commit .env
# empty first-day folder at FOUNDATION_DATA (default ./data) may init
./scripts/keep-vault-up.sh
What ships with it
14 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.
- evidence/.gitignore 25 B
- evidence/README.md 319 B
- features/collection.md 3.3 KB
- features/detail.md 3.3 KB
- features/home.md 3.8 KB
- features/journal-write.md 5.3 KB
- features/README.md 4.2 KB
- features/search.md 2.7 KB
- features/unlock.md 4.6 KB
- PROOF.md 11 KB
- scripts/verify-foundation.sh 21 KB runs code
- scripts/verify-foundation.test.sh 34 KB runs code
- scripts/verify-http-drive.sh 9.9 KB runs code
- scripts/verify-mcp-drive.sh 3.5 KB runs code
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 Changed 533e7045beef
- 2d ago First seen · 272 lines · 68 tokens per session scan C 2c6216492ad3
verify-foundation is a skill published in the GitHub repository dgraziosi/foundation (1 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 4,530 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
flutter-skill
Automate and test Flutter applications — launch apps, inspect widgets, tap elements, enter text, scroll, swipe, take screenshots, validate state, and debug via Dart VM Service Protocol. Use when the user wants to run Flutter app tests, automate Flutter UI interactions, inspect widget trees, debug a running Flutter…
qa
Read-only automated QA sweep of a deployed stardust site on AEM Edge Delivery Services — validates routing, content fidelity vs the source capture, template conformance, rendered integrity (geometry, JS errors, broken images), visual regression vs baselines, metadata/SEO/JSON-LD, link integrity, accessibility (axe)…