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 agentmods add skills/dosco/graphjin/add-graphjin-databasenpx skills add dosco/graphjin --skill add-graphjin-databasegit clone --depth 1 https://github.com/dosco/graphjinWhat 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 | $0.00060 | $0.00811 |
| Opus 5 | $0.00030 | $0.00405 |
| Sonnet 5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
add-graphjin-database 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 2d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add GraphJin Database
Use this skill to add a database end to end without leaving half-public support behind. GraphJin is a compiler, not a resolver stack: push behavior into dialect, discovery, schema metadata, and tests.
Workflow
-
Ground in docs and repo truth.
- Read the database's official SQL, DDL, type, catalog, and limitations docs before coding.
- Inspect existing GraphJin seams: config validation, dialect factory, introspection,
tests/dbint_test.go, hosted emulators, scripts, README, CONFIG, FEATURES, and website components. - Decide and state the public support level: experimental queries, mutations, subscriptions, full support, or simulator-only.
-
Build a simulator first when live service access is unavailable or slow.
- Add
tests/hostedemu/<db>andtests/<db>emuaroundhostedemu.NewConnector. - Add
tests/<db>.sqlusing database-native DDL, types, constraints, and metadata features. - Keep parser/translator code owned by the target database. Reuse hosted emulator patterns, not another database's grammar, unless docs prove the syntax is identical.
- Translate setup and discovery into DuckDB, but expose the database's real discovery surfaces.
- Add parser, type mapping, metadata, discovery, wrapper, default-fixture, and large-catalog tests.
- Add
-
Use the simulator to build public support.
- Register the DB type in
core/config.go, the psql dialect factory, subscription dialect lookup, introspection switches, and schema-DDL/diff code if public DDL support is claimed. - Add a DB-owned dialect. Inherit behavior only after target-specific tests prove it.
- Add discovery using the docs-recommended catalog path first, with fallbacks only where needed.
- Wire
tests/dbint_test.go, focused skip helpers for unsupported features, andscripts/test-<db>.sh. - Keep GraphJin's collision-free managed artifact SQLite database runtime-only. Its identifier is allocated at startup and must never become an application source, primary database candidate, catalog source, or security-report database.
- Register the DB type in
What ships with it
2 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.
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.
- 2d ago First seen · 46 lines · 60 tokens per session scan A 2a7f6f01506a
add-graphjin-database is a skill published in the GitHub repository dosco/graphjin (3,157 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 811 once invoked, about $0.0003 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
Database Schema Reviewer
Reviews database schemas for normalization issues, missing indexes, naming inconsistencies, and scalability risks.
sql-expert
Expert-level SQL database design, querying, optimization, and administration across PostgreSQL, MySQL, and SQL Server.
database-sql
Design database schemas, write efficient SQL queries, create migrations, and optimize database performance. Use when working with databases, writing queries, or designing data models.
database-query
Generate, optimize, and explain SQL queries - supports SQLite, PostgreSQL, MySQL with schema introspection, migration generation, and query performance analysis.
sql
SQL patterns for database querying and design.
database-query
Natural language database queries with multi-database support, query optimization, and visual results.