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 pretensor-ai/pretensor --skill connectorsgit clone --depth 1 https://github.com/pretensor-ai/pretensorWrote 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/pretensor-ai/pretensor/connectors)<a href="https://agentmods.dev/skills/pretensor-ai/pretensor/connectors"><img src="https://agentmods.dev/badge/skills/pretensor-ai/pretensor/connectors/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/pretensor-ai/pretensor/connectors"><img src="https://agentmods.dev/badge/skills/pretensor-ai/pretensor/connectors.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 | $0.00000 | $0.00082 |
| Opus 5.5 | $0.00000 | $0.00033 |
| Sonnet 5.5 | $0.00000 | $0.00016 |
| Haiku 4.5 | $0.00000 | $0.00008 |
Grade A, and why
connectors 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.
What it actually says
Connectors — schema introspection (graph layer)
Read first
PostgreSQL connector and inspect() live in this package; graph product routing: SKILL.md.
Verification
Run tests from repo root:
uv sync --extra dev
uv run pytest tests/
What ships with it
12 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.
- __init__.py 567 B runs code
- base.py 4.8 KB runs code
- bigquery.py 16 KB runs code
- inspect.py 12 KB runs code
- lineage_sqlglot.py 3.0 KB runs code
- models.py 3.7 KB runs code
- mysql.py 14 KB runs code
- pg_array_parse.py 1.3 KB runs code
- postgres.py 38 KB runs code
- registry.py 3.2 KB runs code
- snapshot.py 8.3 KB runs code
- snowflake.py 34 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.
- 1mo ago First seen · 17 lines · 0 tokens per session scan A 95ecbe631893
connectors is a skill published in the GitHub repository pretensor-ai/pretensor (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 82 tokens. 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.
Other skills, from other repositories
db-design
Design and evolve PostgreSQL schemas that survive scale and refactors. Use when modeling a new domain, choosing between normalization and denormalization, designing indexes for known query patterns, writing migrations safely, picking ORM-vs-raw-SQL trade-offs, deciding on soft delete vs hard delete, or evaluating…
supabase
Build on Supabase correctly — Row Level Security, auth, realtime, storage, edge functions, and the Postgres underneath. Use when wiring a Supabase client, writing or reviewing RLS policies, debugging "anyone can read everyone's rows", setting up auth, adding realtime subscriptions, handling file storage, or deciding…
postgres
Read Postgres as compact YAML through bin/postgres/query.go (read-only guard, named profiles). Use when a task needs table contents, column types, or a SELECT against an ops database.
claude-memory
Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…
setup-people-memory
Set up or reconfigure People Memory for an existing Codex, Claude Code, Cursor, or other MCP-capable agent; create a minimal personal agent if needed; choose local PostgreSQL or hosted Supabase; install the schema, MCP, UI, and durable memory instructions; ask which LinkedIn, Google Contacts, WhatsApp, Gmail…
upgrade-people-memory
Upgrade an installed People Memory plugin, MCP package, PostgreSQL/Supabase schema, optional API, web UI, and bundled skills; inspect release notes, back up data, apply ordered migrations, refresh uvx or local installs, preserve config and credentials, restart agents, and verify reads and writes. Use when the user…