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 commands/cyperx84/claude-code-plugin-examples/querygit clone --depth 1 https://github.com/cyperx84/claude-code-plugin-examplesWhat 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 | $0.00008 | $0.01491 |
| Opus 5 | $0.00004 | $0.00745 |
| Sonnet 5 | $0.00002 | $0.00298 |
| Haiku 4.5 | $0.00001 | $0.00149 |
Grade A, and why
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 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Database Query
Execute query: $ARGUMENTS
Using PostgreSQL MCP
1. Query Understanding
Parse and analyze the query request:
- Natural Language: "Show me all users who signed up last month"
- SQL Query:
SELECT * FROM users WHERE created_at > '2024-09-01' - Query Type: SELECT, INSERT, UPDATE, DELETE, CREATE, ALTER
2. Safety Checks
Before Execution:
Safety Analysis:
✅ READ query - Safe to execute
⚠️ UPDATE without WHERE - DANGEROUS! Add confirmation
⚠️ DELETE without WHERE - DANGEROUS! Require explicit confirmation
⚠️ DROP TABLE - CRITICAL! Require double confirmation
⚠️ TRUNCATE - WARNING! Data loss, confirm
Confirmations Required:
- Any DELETE/UPDATE without WHERE clause
- DROP/TRUNCATE operations
- Schema changes (ALTER)
- Production database operations
3. Query Optimization
EXPLAIN Analysis:
-- Auto-run EXPLAIN before executing
EXPLAIN ANALYZE
SELECT * FROM users WHERE email LIKE '%@gmail.com';
-- Show execution plan:
Seq Scan on users (cost=0.00..1234.56 rows=5000 width=100)
Filter: (email ~~ '%@gmail.com'::text)
Rows Removed by Filter: 45000
⚠️ Warning: Sequential scan detected!
Recommendation: Add index on email column
Optimization Suggestions:
-- ❌ Inefficient:
SELECT * FROM users WHERE email LIKE '%@gmail.com';
-- Sequential scan, checks all 50,000 rows
-- ✅ Better:
CREATE INDEX idx_users_email ON users(email);
SELECT * FROM users WHERE email LIKE '@gmail.com%';
-- Index scan, faster lookup
-- ✅ Even Better (if exact match):
SELECT * FROM users WHERE email = '[email protected]';
-- Index seek, optimal
4. Execute Query
Via PostgreSQL MCP:
// Execute through MCP
const result = await postgres.query(optimizedQuery);
// Return results
{
rows: [...],
rowCount: 42,
executionTime: "125ms",
fromCache: false
}
5. Format Results
Table Format:
┌──────┬─────────────┬───────────────────────┬────────────────────┐
│ id │ username │ email │ created_at │
├──────┼─────────────┼───────────────────────┼────────────────────┤
│ 1 │ alice │ [email protected] │ 2024-09-15 10:30 │
│ 2 │ bob │ [email protected] │ 2024-09-16 14:22 │
│ 3 │ charlie │ [email protected] │ 2024-09-17 09:15 │
└──────┴─────────────┴───────────────────────┴────────────────────┘
Showing 3 of 42 rows (limited for display)
Query executed in: 125ms
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 · 256 lines · 8 tokens per session scan A 4dc972a7508b
query is a command published in the GitHub repository cyperx84/claude-code-plugin-examples (2 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 1,491 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.