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/hainrixz/claude-db/explainnpx skills add Hainrixz/claude-db --skill explaingit clone --depth 1 https://github.com/Hainrixz/claude-dbWrote 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/hainrixz/claude-db/explain)<a href="https://agentmods.dev/skills/hainrixz/claude-db/explain"><img src="https://agentmods.dev/badge/skills/hainrixz/claude-db/explain.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.00935 |
| Opus 5 | $0.00044 | $0.00467 |
| Sonnet 5 | $0.00018 | $0.00187 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
explain 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 5d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/claude-db:explain
Plain-language description of a schema (or one finding), plus a paradigm-aware diagram. Read-only — explains, never edits or migrates.
$ARGUMENTS = <path|table|finding-id> [flags]. The target can be a schema/ORM/migration path, a single table/collection name, or a finding id from a prior audit.
What to do
- Detect the paradigm/engine (
scripts/detect-stack.mjs) and parse the model (scripts/parse-schema.mjs/parse-orm-python.py). - Give a plain-language description first — no jargon in the opening: what each entity holds, who owns what, and how the pieces connect, in the user's words ("a user has many orders; each order belongs to exactly one user").
- Render a paradigm-aware diagram (Mermaid) with
node scripts/gen-diagram.mjs --file <schema> [--paradigm relational|document|key-value|wide-column|graph]— paradigm-aware: ERD for relational, access-pattern map for document, key+GSI sketch for DynamoDB/KV, node/edge for graph:- Relational →
erDiagramwith tables, PKs/FKs, and cardinality. - Document → embedding/reference tree showing what is nested vs referenced.
- Key-value → access-pattern / key-design sketch (partition + sort key).
- Wide-column → table-per-query / partition-key layout.
- Vector → collection + metric/dimension + metadata filter fields.
- Time-series → hypertable / measurement + tags + retention.
- Graph → node-and-edge sketch with relationship types.
- Relational →
- Offer an expandable technical layer below the plain description: exact column types, index definitions, constraint names, on-delete behavior — for the reader who wants the precise DDL.
- If the target is a finding id, explain what it checks, which score/axis it affects (design | performance | both), why it matters, and how to reproduce it (
verification.reproduce).
Query / EXPLAIN-plan mode
Two additional inputs, both reusing the db-query-patterns (M13) reasoning:
--query "<SQL>"— given a raw SQL statement, explain in plain language why it would be slow and what fixes it: detect M13 shapes (SELECT *, structural N+1, OFFSET deep paging, non-SARGable predicates), then recommend the concrete index, keyset rewrite, or predicate change that lets an index be used. This is static reasoning over the query text — no live DB needed.- paste-an-EXPLAIN-plan — given a pasted
EXPLAIN/EXPLAIN ANALYZEplan, read the plan nodes (seq scans, sort/hash spills, row estimate vs actual, nested-loop blowups) and explain which step dominates and what index/rewrite removes it, again via the M13 reasoning. - If the user wants a live plan generated for them (running
EXPLAINagainst their database) rather than pasting one, mark the requestneeds_api/ Tier-2 and do not fabricate plan numbers — explain statically from the query text instead, or ask them to paste the plan.
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.
- 5d ago First seen · 37 lines · 88 tokens per session scan A d38501e305e8
explain is a skill published in the GitHub repository Hainrixz/claude-db (19 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 935 once invoked, about $0.0004 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
dynamodb
Use when modeling or operating a DynamoDB table: deriving partition/sort keys from access patterns, single-table vs table-per-entity, adding a GSI/LSI, on-demand vs provisioned capacity, or diagnosing hot-partition throttling. NOT relational schema/SQL/EXPLAIN (that is postgresdb), NOT aggregation-pipeline document…
malloy-lookml-review
Analyze LookML files as prior art for Malloy modeling. Used during Step 1 (DISCOVER) when .lkml files are present. Coordinates reference files that extract business logic, relationships, and curation decisions. Works with or without a database connection.
convex-migrations
Schema migration strategies for evolving applications including adding new fields, backfilling data, removing deprecated fields, index migrations, and zero-downtime migration patterns.
database-design-patterns
Database schema design patterns and optimization strategies for relational and NoSQL databases. Use when designing database schemas, optimizing query performance, or implementing data persistence layers at scale.
terrabase-db-changes
Use when making Postgres schema or migration changes (CREATE/ALTER/DROP TABLE, indexes, columns, constraints, backfills) IN A PROJECT THAT DECLARES A TERRABASE TARGET (a TERRABASEDATABASEURL in its .env). Routes the change through terrabase's MCP tools for a deterministic safety analysis plus a local-Qwen plan, and…
erd-studio
Schema rules for ERD Studio data model files — the .erd-studio/ directory uses a two-file system (YAML model definitions + JSON domain diagrams) with strict format rules you must read before editing. Use this skill whenever the task touches files in .erd-studio/ (domain JSON, logical-models YAML, or .sync-plan.json)…