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/oliver-kriska/claude-elixir-phoenixWrote 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/oliver-kriska/claude-elixir-phoenix/psql-query)<a href="https://agentmods.dev/commands/oliver-kriska/claude-elixir-phoenix/psql-query"><img src="https://agentmods.dev/badge/commands/oliver-kriska/claude-elixir-phoenix/psql-query/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/oliver-kriska/claude-elixir-phoenix/psql-query"><img src="https://agentmods.dev/badge/commands/oliver-kriska/claude-elixir-phoenix/psql-query.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 | $0.00016 | $0.00325 |
| Opus 5.5 | $0.00006 | $0.00130 |
| Sonnet 5.5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
psql-query 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.
What it actually says
PostgreSQL Analytics
Run analytics queries against the local database using psql or mix run.
Rules
- NEVER run against production
- Use READ-ONLY queries (SELECT only)
- For complex analysis, use
Repo.query/2in a Mix task - Format results as ASCII tables or pipe to
column -t
Tidewave Integration
If Tidewave MCP is available, prefer it over psql/mix run:
mcp__tidewave__execute_sql_queryfor direct SQL queriesmcp__tidewave__project_evalfor Ecto-based queries viaRepo.query!/2orRepo.all/1
Fall back to psql/mix run only if Tidewave is not detected.
Workflow
- Check if Tidewave MCP is available — if yes, use
mcp__tidewave__execute_sql_query - Otherwise, detect database URL from
config/dev.exsorDATABASE_URL - Run query via:
psql $DATABASE_URL -c "YOUR QUERY" --expanded - For Ecto:
mix run -e 'MyApp.Repo.query!("SELECT ...") |> IO.inspect()' - Summarize results
Example prompts
- "How many users signed up this week?"
- "Show me the slowest queries from pg_stat_statements"
- "What's the table size distribution?"
- "Show index usage stats"
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 · 40 lines · 16 tokens per session scan A 787e83e79ed3
psql-query is a command published in the GitHub repository oliver-kriska/claude-elixir-phoenix (569 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 325 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 2026-08-30.
Other commands, from other repositories
archetype-impact
Scan the current workspace for all references to a given archetype across templates (.oet / .t.json source, .opt compiled) and AQL files, producing an impact table useful before editing a widely-reused archetype.
refactor-stack
Coordinated architecture refactor — change database, cloud provider, or framework with full SDL consistency.
db-enum
Enumerate/exploit a database — connect and read first, heavy brute only when justified.
brainstorm
Turn a fuzzy idea into a concrete design doc through guided Q&A.
sparc-supabase-admin
🔐 Supabase Admin - You are the Supabase database, authentication, and storage specialist. You design and implement d...
fix-issue
Command "fix-issue" from KhaiTrang1995/claude-code-structure, covering /project:fix-issue – fix issue command, usage, description, shell steps and run tests after fix.