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 skills add vladkesler/initrunner --skill database-verificationgit clone --depth 1 https://github.com/vladkesler/initrunnerWrote 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/vladkesler/initrunner/database-verification)<a href="https://agentmods.dev/skills/vladkesler/initrunner/database-verification"><img src="https://agentmods.dev/badge/skills/vladkesler/initrunner/database-verification/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/vladkesler/initrunner/database-verification"><img src="https://agentmods.dev/badge/skills/vladkesler/initrunner/database-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.00905 |
| Opus 5.5 | $0.00012 | $0.00362 |
| Sonnet 5.5 | $0.00006 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
database-verification 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database verification skill using standard database CLI tools.
When to activate
Use this skill when tests fail with connection errors or timeouts to a database, when database-related tests exist in the test suite, when docker-compose or similar configs define database services, or when a migration has recently been applied and needs verification.
Connectivity checks
Test reachability before running any data queries. Each database has its own tool:
PostgreSQL
pg_isready -h host -p 5432
Returns exit code 0 if accepting connections. For authenticated check:
psql -h host -p 5432 -U user -d dbname -c "SELECT 1"
Redis
redis-cli -h host -p 6379 ping
Expected response: PONG.
SQLite
sqlite3 /path/to/file.db ".tables"
Returns the list of tables. A missing file or corrupt database produces an error.
MySQL / MariaDB
mysql -h host -u user -p -e "SELECT 1"
Or check just connectivity:
mysqladmin -h host -u user ping
MongoDB
mongosh --host host --port 27017 --eval "db.runCommand({ ping: 1 })"
Schema verification
After connectivity is confirmed:
- Tables exist -- query the information schema or equivalent to list tables; compare against expected table names.
- Columns match -- for each critical table, list columns and types; verify expected columns are present with correct types.
- Indexes present -- check that performance-critical indexes exist (primary keys, foreign key indexes, unique constraints).
- Constraints -- verify NOT NULL, UNIQUE, and foreign key constraints are in place on the relevant columns.
Data integrity
- Row counts -- check that tables have expected minimum rows (not empty when they should be populated).
- Foreign key consistency -- verify that foreign key references point to existing rows (no orphaned records).
- Null checks -- scan NOT NULL columns for unexpected nulls (can happen if constraints were added after data).
- Duplicate detection -- check unique columns for duplicates when constraints might be missing.
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.
- 1mo ago First seen · 140 lines · 29 tokens per session scan A 3e1545f3bb2b
database-verification is a skill published in the GitHub repository vladkesler/initrunner (41 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 905 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.
session-persistence
Imports OpenClaw session transcripts into a local SQLite database with FTS5 full-text search — the agent never loses a message, even after context compaction or session rollover.
quality-gate-orchestrator
Tracks required validation gates, records pass/fail/waived results, and reports readiness before task completion.
test-driven-development
Red-green-refactor discipline. Use when writing new functionality.
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
Vizra ADK Tool Creation
Build custom tools for Vizra ADK agents - includes patterns for database, API, file, and email tools.