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/commands/saajunaid/caddis-plugin/sql-optimization)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/sql-optimization"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/sql-optimization/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/commands/saajunaid/caddis-plugin/sql-optimization"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/sql-optimization.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 | $0.00011 | $0.00602 |
| Opus 5.5 | $0.00004 | $0.00241 |
| Sonnet 5.5 | $0.00002 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
sql-optimization 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Performance Optimization
Analyze the provided SQL queries (or project SQL code) and optimize them for performance. Apply universal techniques that work across MySQL, PostgreSQL, SQL Server, Oracle, and other SQL databases.
Instructions
- Identify the target database engine if possible (ask if unclear).
- For each query or pattern found, analyze and optimize using the areas below.
- Show before (problematic) and after (optimized) versions with explanations.
- Suggest index changes where applicable.
Optimization Areas
Query Structure
- Replace
SELECT *with explicit column lists - Convert correlated subqueries to JOINs or window functions
- Use
EXISTSinstead ofINfor subqueries when appropriate - Filter early in
WHEREclauses to reduce row processing - Avoid functions on indexed columns in
WHERE(breaks index usage)
JOIN Optimization
- Use
INNER JOINinstead ofLEFT JOINwhen NULLs aren't needed - Move filter conditions into
JOIN ... ONwhen logically correct - Order JOINs from smallest to largest result set where the optimizer benefits
Index Strategy
- Suggest composite indexes matching query filter + sort order
- Recommend covering indexes for frequently-run queries
- Flag over-indexing risks (impacts write performance)
- Consider partial indexes for filtered subsets
Pagination
- Replace large-offset
LIMIT/OFFSETwith cursor-based pagination - Use keyset pagination (
WHERE id > last_seen_id ORDER BY id LIMIT N)
Aggregation and Batching
- Combine multiple
COUNTqueries into a single conditional aggregation - Replace row-by-row inserts with batch
INSERT ... VALUES - Use temporary tables for complex multi-step calculations
Anti-Patterns to Flag
SELECT *in production queries- Functions wrapping indexed columns in
WHERE - N+1 query patterns in application code
- Missing
LIMITon unbounded queries ORconditions that prevent index usage (suggestUNION ALL)
Output Format
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 · 76 lines · 11 tokens per session scan A f10f9cbc1374
sql-optimization is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 602 once invoked, about $0.0000 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 2026-09-09.
Other commands, from other repositories
end-session
Wrap up the work session with read-only evidence gathering, owner-classified documentation handoffs, gated issue sync, Kano refinement, and git hygiene checks.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
specify
Command dispatcher for specify.
observe
Show the observability web UI URL (it autostarts with the session); stop or restart it.
accept
Command dispatcher for accept.
change
Command dispatcher for change.