Borrowing it
Nothing to install: this file belongs to erikdarlingdata/PerformanceMonitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/erikdarlingdata/PerformanceMonitor/main/.claude/skills/duckdb/SKILL.mdgit clone --depth 1 https://github.com/erikdarlingdata/PerformanceMonitorWrote 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/skills/erikdarlingdata/performancemonitor/duckdb)<a href="https://agentmods.dev/skills/erikdarlingdata/performancemonitor/duckdb"><img src="https://agentmods.dev/badge/skills/erikdarlingdata/performancemonitor/duckdb/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/skills/erikdarlingdata/performancemonitor/duckdb"><img src="https://agentmods.dev/badge/skills/erikdarlingdata/performancemonitor/duckdb.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 | $0.00637 |
| Opus 5.5 | $0.00007 | $0.00255 |
| Sonnet 5.5 | $0.00003 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
duckdb 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 15d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query Lite's DuckDB Database
Safely query the PerformanceMonitor Lite DuckDB database using Python. This skill exists because DuckDB only allows one read-write connection at a time. When Lite is running (collecting data), it holds the write connection, so an external reader connects in read-only mode.
Database Location
The store lives at:
%LOCALAPPDATA%\PerformanceMonitorLite-Data\monitor.duckdb
Lite 3.3.0 and earlier kept it at the path below, and the file moves to the path above only when a newer build first runs. Check the path above first, and fall back to this one when it does not exist:
%LOCALAPPDATA%\PerformanceMonitorLite\monitor.duckdb
How to Query
Use Python with the duckdb module, always with this pattern:
python -c "
import duckdb, os
la = os.environ['LOCALAPPDATA']
p = la + '/PerformanceMonitorLite-Data/monitor.duckdb'
if not os.path.exists(p):
p = la + '/PerformanceMonitorLite/monitor.duckdb'
con = duckdb.connect(p, read_only=True)
result = con.execute('YOUR SQL HERE').fetchall()
for row in result:
print(row)
con.close()
"
Rules
- Pass
read_only=Truetoduckdb.connect(). The default is read-write. Lite's write lock blocks a read-write connection, and it hangs or fails. - Use forward slashes in the path (Python on Windows handles this fine)
- Close the connection when done, so no read lock is left dangling
- Use Python with its
duckdbmodule
Common Queries
List all tables:
SELECT table_name FROM information_schema.tables WHERE table_schema = 'main' ORDER BY table_name;
List columns for a table:
SELECT column_name, data_type FROM information_schema.columns WHERE table_name = 'TABLE_NAME' ORDER BY ordinal_position;
List all views:
SELECT table_name FROM information_schema.tables WHERE table_type = 'VIEW' ORDER BY table_name;
Row counts:
SELECT table_name, estimated_size FROM duckdb_tables() ORDER BY estimated_size DESC;
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.
- 15d ago Changed · -2 lines c17c0230256f
- 1mo ago First seen · 82 lines · 17 tokens per session scan A 0557a1a82d51
duckdb is a skill published in the GitHub repository erikdarlingdata/PerformanceMonitor (528 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 637 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 2026-09-10.
duckdb compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| duckdberikdarlingdata/PerformanceMonitor | Skill | 528 | today | MIT | A | 17 | Claude Code |
| usageCanner/WrenAI | Skill | 18k | 2d ago | none | A | 156 | Claude Code, Codex |
| generate-mdlCanner/WrenAI | Skill | 18k | 2d ago | none | A | 82 | Claude Code, Codex |
| dlt-connectorCanner/WrenAI | Skill | 18k | 2d ago | none | A | 158 | Claude Code, Codex |
| wrenCanner/WrenAI | Skill | 18k | 2d ago | none | A | 315 | Claude Code |
| duckdb-spatialznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 125 | Claude Code, Codex |
| duckdb-differentialtobilg/duckdb-differential | Skill | 48 | 4d ago | MIT | A | 123 | Claude Code |