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 Kevin-Liu-01/Agent-Machines --skill dbgit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/db)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/db"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/db/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/kevin-liu-01/agent-machines/db"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/db.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 | $0.00034 | $0.00703 |
| Opus 5 | $0.00017 | $0.00351 |
| Sonnet 5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
db 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 11d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Databases: !
cat packages/python/cli/databases.yml - Local Supabase status: !
pnpm db status 2>&1 | head -10
Query script
The query tool lives at ${CLAUDE_SKILL_DIR}/scripts/query.ts. Run it with:
node --experimental-strip-types ${CLAUDE_SKILL_DIR}/scripts/query.ts [flags] "<sql>"
Flags:
--env local|dev|preview|prod(default: local)--db core|admin(default: core)--readonly(enforced by this skill, always pass it)--format table|json|csv(default: table)
Credentials
Remote connections resolve credentials in order: SUPABASE_DB_PASSWORD env var > ~/.pgpass.
If neither is available, fetch from AWS SSM (requires active SSO session):
# Prod (admin profile, account 717408097146)
aws ssm get-parameter --name "/prod/SUPABASE_DB_PASSWORD" --with-decryption --query "Parameter.Value" --output text --profile admin
# Dev/preview passwords are not in SSM. Use ~/.pgpass or ask a teammate.
To populate ~/.pgpass (one entry per environment):
# Format: hostname:port:database:username:password
db.<project_ref>.supabase.co:5432:postgres:postgres:<password>
See packages/python/cli/databases.yml for project refs per environment.
Schema reference
Generated Supabase types with full table schemas, enums, and function signatures:
- Core DB:
packages/typescript/databases/core/database.types.ts - Admin DB:
packages/typescript/databases/admin/database.types.ts
Read the relevant file when you need column names, types, enums, or relationships.
The Database type has schemas (public, billing, oauth, dcs) with Tables, Enums, and
Functions for each. Each table has Row (all columns typed), Insert, and Update variants.
Rules
- Always pass
--readonly. This skill is read-only. For mutations, the user must invoke/db-write. - Never target prod unless the user explicitly says "prod" or "production."
- Default to
--env localunless the user specifies otherwise. - For schema exploration, start with
information_schema.tablesandinformation_schema.columns. - Format as
--format jsonwhen the user wants structured output or when piping to analysis. - Format as
--format tablefor human-readable display (default). - Quote identifiers that may conflict with SQL keywords.
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.
- 11d ago First seen · 75 lines · 34 tokens per session scan A bbe484a651ba
db is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 703 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
hermes-mnemosyne
Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMESHOME/plugins/mnemosyne/.
cmdb-patterns
Create ServiceNow CIs and cmdbrelci relationships, walk upstream/downstream impact, detect orphan/stale CIs, and align discovered CIs with the proper sysclassname hierarchy.
gliderecord-patterns
Write efficient ServiceNow GlideRecord queries — addQuery vs addEncodedQuery, setLimit, GlideAggregate for counts, avoiding N+1 in loops, query operators, and safe CRUD with workflow control.
organize-database
Transform unstructured Notion pages into a well-designed database with proper schema and migration.
change-tracking
A change-tracking workflow for a 1C database, a business accounting and records system. It retrieves records changed after a saved time marker, including document details and document line items.