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/techgangboss/agentstore/sql-expertnpx skills add techgangboss/agentstore --skill sql-expertgit clone --depth 1 https://github.com/techgangboss/agentstoreWhat 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 | $0.00070 | $0.00800 |
| Opus 5 | $0.00035 | $0.00400 |
| Sonnet 5 | $0.00014 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
sql-expert 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 2d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Expert
Write optimized SQL queries and explain execution plans. Supports PostgreSQL, MySQL, and SQLite.
Capabilities
- Write complex SQL queries from natural language descriptions
- Optimize slow queries with index and structure suggestions
- Explain execution plans in plain English
- Design normalized database schemas
- Debug query errors and suggest fixes
- Generate migrations for schema changes
Instructions
Writing Queries
When the user describes what data they need:
- Ask clarifying questions if the schema is unclear
- Check for existing schema files (
.sql, migrations, ORM models) in the project - Write the query with:
- Clear aliases and formatting
- Appropriate JOINs (prefer explicit JOIN syntax over implicit)
- WHERE clauses with proper indexing considerations
- LIMIT for potentially large result sets
- Explain what the query does and any assumptions made
Optimizing Queries
When the user shares a slow query:
- Analyze the query structure
- Check for common performance issues:
- Missing indexes on JOIN/WHERE columns
- SELECT * when only specific columns needed
- Correlated subqueries that could be JOINs
- Missing LIMIT on large tables
- Unnecessary ORDER BY on unindexed columns
- N+1 query patterns in application code
- Suggest specific improvements with before/after
- Recommend indexes to create:
CREATE INDEX idx_name ON table(column);
Explaining Execution Plans
When the user shares an EXPLAIN output:
- Walk through each step of the plan
- Identify the most expensive operations
- Flag sequential scans on large tables
- Explain estimated vs actual rows discrepancies
- Suggest indexes or query restructuring to improve the plan
Schema Design
When the user needs a new schema:
- Identify entities and relationships
- Apply normalization (typically 3NF for OLTP)
- Choose appropriate data types (prefer specific types:
timestamptzovertext) - Add primary keys, foreign keys, and constraints
- Suggest indexes for expected query patterns
- Generate CREATE TABLE statements
- Generate a migration file if the project uses migrations
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.
- 2d ago First seen · 104 lines · 70 tokens per session scan A fa5a34fb5345
sql-expert is a skill published in the GitHub repository techgangboss/agentstore (4 stars, last pushed 6mo ago), licensed MIT. It adds 70 tokens to every session and 800 once invoked, about $0.0003 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
agent-skills-system
Route and operate software, product, research, and agent tasks through one phase-appropriate execution mode. Use when choosing how an agent should approach a task, resolving speed-versus-quality tradeoffs, planning mode transitions, designing agent workflows, or improving an agent harness. Do not use for a routine…
clawlabor
The autonomous marketplace where AI agents discover, purchase, and sell specialized AI capabilities. Use when the user needs to find, hire, buy, sell, or outsource AI capabilities through UAT escrow.
agent-skills-system
Route and operate software, product, research, and agent tasks through one phase-appropriate execution mode. Use when choosing how an agent should approach a task, resolving speed-versus-quality tradeoffs, planning mode transitions, designing agent workflows, or improving an agent harness. Do not use for a routine…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…