What is sqlprism CLAUDE.md?

A set of project instructions for SQLPrism, a tool that indexes SQL, dbt, and SQLMesh code into a DuckDB-backed graph. dbt and SQLMesh are tools for building and managing data-transformation projects.

Changing SQL, dbt, or SQLMesh parsing; maintaining the dependency graph; reindexing repositories or files; working on MCP tools and the command-line interface; and running checks and tests.

It helps agents work consistently on parsing, indexing, data lineage, and MCP tools without guessing the project structure or validation commands.

sqlprism CLAUDE.md — Instructions file by darkcofy

Install

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.

agentmods

npx agentmods add instructions/darkcofy/sqlprism/claude-md

Clone the repo

git clone --depth 1 https://github.com/darkcofy/sqlprism

Per session 614 This file is loaded in full into every session.

When invoked 614 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00614	$0.00614
Opus 5	$0.00307	$0.00307
Sonnet 5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured yesterday against content hash c96c52a67fe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sqlprism CLAUDE.md 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 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.

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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SQLPrism

SQL knowledge graph MCP server — indexes SQL, dbt, and sqlmesh repos into a DuckDB-backed graph for lineage, impact analysis, and column tracing.

Quick Reference

Language: Python 3.11+
Package manager: uv
Lint: uv run ruff check .
Type check: uv run ty check
Tests: uv run pytest tests/ -v
Single test: uv run pytest tests/test_indexer.py::test_name -v

Project Structure

src/sqlprism/
  core/
    graph.py       — DuckDB storage layer (MVCC, repo_type tracking)
    indexer.py      — Orchestrates parsing + indexing; file-level reindex with repo-type dispatch
    mcp_tools.py   — MCP server tools (non-blocking reindex, per-repo debounce)
    conventions.py — Convention inference engine (layers, naming, references, tags, overrides)
  languages/
    sql.py         — sqlglot-based SQL parser
    dbt.py         — dbt renderer (full project + selective render_models)
    sqlmesh.py     — sqlmesh renderer (full project + selective render_models)
    utils.py       — Shared venv/env utilities
  types.py         — Data classes (ParseResult, NodeResult, etc.)
  cli.py           — Click CLI (serve, reindex, reindex-file, reindex-sqlmesh, reindex-dbt, conventions, status, init)
tests/
  test_indexer.py    — Indexer + integration tests
  test_renderers.py  — dbt/sqlmesh renderer tests
  test_conventions.py — Convention engine + placement + tags tests
  test_sql_parser.py — SQL parser, lineage, and dialect tests

Conventions

Branch naming: <type>-<issue>-<short-description> (e.g. feat-11-indexer-reindex-files)
Types: feat (enhancement), fix (bug), chore (maintenance)
Issues: BDD format with Given/When/Then scenarios
PRs: Link with Closes #<number>, draft first, mark ready after lint+tests pass
Lint before PR: Always run uv run ruff check . and uv run ty check before creating or marking a PR ready

Skills

Custom skills are in .claude/skills/:

implementing-issues — End-to-end issue implementation with task planning and sub-agents
creating-branches-and-prs — Branch/PR naming conventions and creation workflow
reviewing-prs — Three-persona parallel PR review (SWE, data eng, QA)
managing-project-releases — Decompose releases into BDD issues with milestones

Read the full file on GitHub · 53 lines

Changes

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 First seen · 53 lines · 614 tokens per session scan A c96c52a67fe0

Subscribe to this mod's changes

sqlprism CLAUDE.md is an instructions file published in the GitHub repository darkcofy/sqlprism (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 614 tokens to every session, about $0.0031 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 2026-09-01.

Databases Testing

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

sqlprism CLAUDE.md