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/anentrypoint/freddie/sql-explainernpx skills add AnEntrypoint/freddie --skill sql-explainergit clone --depth 1 https://github.com/AnEntrypoint/freddieWhat 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 | $0.00021 | $0.00475 |
| Opus 5 | $0.00010 | $0.00237 |
| Sonnet 5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
sql-explainer 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.
What it actually says
SQL Explainer
Explain SQL queries, analyse execution plans, identify performance bottlenecks, and suggest rewrites.
Explanation format
For any query:
WHAT IT DOES (one sentence)
STEP BY STEP:
1. FROM / JOIN — which tables, join type and implications
2. WHERE — filters, sargability (can indexes be used?)
3. GROUP BY / HAVING — aggregation logic
4. SELECT — columns, computed expressions
5. ORDER BY / LIMIT — sort and pagination
EDGE CASES:
- NULLs: which columns and how they affect results
- Empty sets: what happens if a subquery returns no rows
- Duplicates: expected or a bug?
PERFORMANCE NOTES:
- Estimated scan type
- Columns that should have indexes
- Estimated row count at each stage
EXPLAIN ANALYZE reading
- Highest actual time node = bottleneck.
- rows estimated vs actual divergence → stale statistics (
ANALYZEneeded). - Seq Scan on large table with filter → missing index.
- Hash Join with large hash → may spill to disk; check
work_mem. - Nested Loop on large outer, inner Seq Scan → N+1; index the join key.
Common rewrites
| Anti-pattern | Fix |
|---|---|
SELECT * in subquery |
Select only the join key |
NOT IN (subquery with NULLs) |
Use NOT EXISTS |
| Correlated subquery in SELECT | LEFT JOIN + COALESCE |
DISTINCT hiding a bad join |
Fix the join |
ORDER BY on un-indexed column with small LIMIT |
Index the sort column |
Rules
- Always state the SQL dialect assumed (PostgreSQL, MySQL, SQLite, BigQuery, etc.).
- Never change query semantics in a rewrite without flagging the difference.
- If slow but correct, suggest
EXPLAIN ANALYZEoutput before guessing at indexes.
Paste the query (and optionally DDL + EXPLAIN output) and I will explain immediately.
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 · 61 lines · 21 tokens per session scan A 659a96e24176
sql-explainer is a skill published in the GitHub repository AnEntrypoint/freddie (5 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 475 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
analyzing-network-flow-data-with-netflow
Parse NetFlow v9 and IPFIX records to detect volumetric anomalies, port scanning, data exfiltration, and C2 beaconing patterns. Uses the Python netflow library to decode flow records, builds traffic baselines, and applies statistical analysis to identify flows with abnormal byte counts, connection durations, and…
info-funnel
3-6 阶递减漏斗, 突出转化率 / 筛选比例 / 流量损耗。竖图适合 IG Story / 小红书.
build-with-tinybase
Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore…
docetl
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
data-report
把 CSV/Excel/JSON 数据转成漂亮的可视化报告页.