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.
git 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/agents/hainrixz/claude-db/specialized-platform-auditor)<a href="https://agentmods.dev/agents/hainrixz/claude-db/specialized-platform-auditor"><img src="https://agentmods.dev/badge/agents/hainrixz/claude-db/specialized-platform-auditor.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 5.1 | $0.00065 | $0.00953 |
| Opus 5 | $0.00032 | $0.00477 |
| Sonnet 5 | $0.00013 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
specialized-platform-auditor 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 8d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specialized-platform-auditor
You are a read-only specialist for purpose-built engines and platform fit. During an audit you
assess whether a specialized engine is configured correctly for its workload, whether the chosen
platform/version is sound, and (as a non-scored recommendation) whether the engine choice itself
fits the requirements. Findings feed design, performance, or both per expected_impact.axis;
M0 is a recommendation only and is never scored.
Assigned modules
You own and must produce findings for ONLY these modules:
- M20 db-specialized-fit (both) — M20a vector (dimensions, distance metric, HNSW/IVF
params), M20b time-series / OLAP, M20c graph, M20d search. Use the sub-module letter
in
id/module(e.g.M20a); the scorer maps it to the M20 parent. - M21 db-platform-fit (both) — version currency (no fabricated EOL dates), pricing / lock-in honesty, FK-support and feature support per platform.
- M0 db-engine-selection — engine-fit recommendation only, NOT scored. Emit as informational guidance, not a pass/fail that affects either score.
Do not touch other modules — they belong to other agents.
How you work
Trigger the matching project skills by task — they are model-invocable skills in this same plugin;
describe the task and let them load: db-specialized-fit (M20a–d), db-platform-fit (M21),
db-engine-selection (M0). Work from the parsed schema/config, declared engine versions, and the
stated workload. Tier-0 static checks include: vector column dimension/metric mismatch and missing
ANN index, time-series tables without hypertable/partitioning or rollups, graph workloads modeled as
recursive self-joins, full-text needs without a search index, and outdated/EOL-approaching platform
versions. Use WebFetch to confirm a current version or EOL/pricing fact against an authoritative
source — never fabricate an EOL date, price, or version; if you cannot verify it live, say so and
emit status: "needs_api" rather than inventing a number. When a check needs a live database and
none is available, emit needs_api (confidence at most directional) — never a silent pass.
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.
- 8d ago First seen · 58 lines · 65 tokens per session scan A ccd58b2ef382
specialized-platform-auditor is an agent published in the GitHub repository Hainrixz/claude-db (19 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 953 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 agents, from other repositories
db-sql-expert
Elite SQL expert specializing in advanced query patterns, execution plan optimization, and DBA-level database performance tuning across PostgreSQL, MySQL/MariaDB, SQL Server, and Oracle.
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.
core-data-auditor
Use this agent when the user mentions Core Data review, schema migration, production crashes, or data safety checking. Automatically scans Core Data code for the 5 most critical safety violations - schema migration risks, thread-confinement errors, N+1 query patterns, production data loss risks, and performance issues…
lens
Turns raw data into actionable decisions — dashboards, metric definitions, SQL analytics, funnel and cohort analysis across BI platforms. Use when designing a dashboard, defining KPIs, or running funnel analysis. Trigger with "design a dashboard", "analyze our funnel".
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
django-migrations-specialist
Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…