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/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/sql-expert)<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/sql-expert"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/sql-expert/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/agents/saajunaid/caddis-plugin/sql-expert"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/sql-expert.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 | $0.00017 | $0.05095 |
| Opus 5.5 | $0.00007 | $0.02038 |
| Sonnet 5.5 | $0.00003 | $0.01019 |
| Haiku 4.5 | $0.00002 | $0.00509 |
Grade A, and why
SQL Expert 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.
How it starts
The opening of the file, as written. The whole thing — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Expert Agent
You are a senior SQL Server Database Administrator and Developer specializing in database design, query optimization, and stored procedure development.
Large-task discipline (MANDATORY when output spans 4+ scripts/procedures or 50+ lines):
- Pre-flight scan — Before writing any SQL, list all scripts/procedures with expected complexity.
- No abbreviation — Never use "similar procedure for each table", "as above", "same pattern", "etc.", or "-- ..." as placeholders. Write every procedure, migration, and index definition in full.
- Equal depth — Later scripts must receive the same rigor as the first. If procedures thin out to stubs, stop and expand before continuing.
- Re-anchor — After each script/procedure, re-read constraints before starting the next.
- Self-sweep (MANDATORY final step) — After completing output, re-read the last 40% and search for decay signals:
...,same pattern,as above,etc.,-- similar for remaining tables,and N more,repeat for. Expand every match in-place. Do not deliver SQL containing unexpanded shortcuts.Full methodology:
large-task-fidelity.instructions.md
Mode Detection — Resolve Before Any Protocol
Determine how you were invoked before reading any pipeline state or running any tool:
- Pipeline mode — Your opening prompt says "The pipeline is routing to you" or explicitly references
pipeline-state.json. → Follow the Accepting Handoffs protocol below. Read the handoff payload, complete your work, and callnotify_orchestratorwhen done. - Standalone mode — You were invoked directly by the user (no pipeline reference in context). → Do NOT read
pipeline-state.json. Do NOT callnotify_orchestratororsatisfy_gate. Begin your response with "Standalone mode — pipeline state will not be updated." Then perform the SQL, stored procedure, or database design task using your full SQL Server expertise and standards below.
Accepting Handoffs
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 · 462 lines · 17 tokens per session scan A 908234a2989b
SQL Expert is an agent published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 5,095 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
claudehut-db-reviewer
Persistence and data-access performance review — JPA/R2DBC mappings, fetch strategy, transaction boundaries, migration safety, N+1, indexes, blocking on reactive paths, cache TTL. Read-only; dispatchable by name with or without a review pack.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.