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/umair444/chat-sql-mcp/chat-sqlnpx skills add Umair444/chat-sql-mcp --skill chat-sqlgit clone --depth 1 https://github.com/Umair444/chat-sql-mcpWhat 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 | $0.00081 | $0.00723 |
| Opus 5 | $0.00041 | $0.00362 |
| Sonnet 5 | $0.00016 | $0.00145 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
chat-sql 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chat-sql — natural language to SQL
Answer data questions by generating and running SQL through the chat-sql MCP server. The server enforces security itself (PII masking, write-guard, connector isolation); your job is to write correct, aggregated SQL and present results clearly.
When to use
- A user asks a question answerable from a configured database.
- A user wants a metric, a breakdown, a trend, or a one-off lookup.
- A user wants a data export (a CSV lead list, a report extract).
Workflow
- Recall first. Call
find_similar_queries(question)to reuse prior style and known-correct SQL for these databases. - Pick the database. Call
list_databases()if unsure whichdb_keyfits. - Aggregate by default. Write counts / sums / averages / group-bys. Only project identifier columns when truly required — they come back masked anyway.
- Write SQL to a file, then
run_query_file(db_key, path)(editable, rerunnable). Userun_query(db_key, sql)for short one-off lookups. - Read the result honestly. Identifier columns arrive hashed/redacted and a
🔒note lists what was masked — that is expected, not an error. - Save good queries.
save_query_example(...)only for logically-correct, reusable queries. - Exports. For raw-value files, use
export_to_csv(db_key, sql, path)— it writes the file and returns only a row count + path.
Rules the server enforces (do not fight them)
- PII is masked in every result. Aggregates pass raw. Prefer aggregation.
- Writes only to
tmp_scratch tables you created (viaload_fileorCREATE TEMP). Any write to a real table is refused. run_pythoncannot reach a database — it is for local data transforms only.
SQL style
Lowercase keywords; alias every subquery; group by before having; CTEs over
deep nesting; no select *; 4-space indent; sentinel -1 for missing values.
Match the target dialect (Teradata sel/top/bare date; ClickHouse
limit/toDate; Postgres limit/::cast/ilike; etc. — see the project
CLAUDE.md).
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 · 53 lines · 81 tokens per session scan A 83cae752b9cc
chat-sql is a skill published in the GitHub repository Umair444/chat-sql-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 81 tokens to every session and 723 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…