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/anthropics/knowledge-work-plugins/write-querynpx skills add anthropics/knowledge-work-plugins --skill write-querygit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWhat 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 | $0.00064 | $0.01082 |
| Opus 5 | $0.00032 | $0.00541 |
| Sonnet 5 | $0.00013 | $0.00216 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
write-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 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- write-query — 100% identical, 0 lines differ
- write-query-th — 88% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/write-query - Write Optimized SQL
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Write a SQL query from a natural language description, optimized for your specific SQL dialect and following best practices.
Usage
/write-query <description of what data you need>
Workflow
1. Understand the Request
Parse the user's description to identify:
- Output columns: What fields should the result include?
- Filters: What conditions limit the data (time ranges, segments, statuses)?
- Aggregations: Are there GROUP BY operations, counts, sums, averages?
- Joins: Does this require combining multiple tables?
- Ordering: How should results be sorted?
- Limits: Is there a top-N or sample requirement?
2. Determine SQL Dialect
If the user's SQL dialect is not already known, ask which they use:
- PostgreSQL (including Aurora, RDS, Supabase, Neon)
- Snowflake
- BigQuery (Google Cloud)
- Redshift (Amazon)
- Databricks SQL
- MySQL (including Aurora MySQL, PlanetScale)
- SQL Server (Microsoft)
- DuckDB
- SQLite
- Other (ask for specifics)
Remember the dialect for future queries in the same session.
3. Discover Schema (If Warehouse Connected)
If a data warehouse MCP server is connected:
- Search for relevant tables based on the user's description
- Inspect column names, types, and relationships
- Check for partitioning or clustering keys that affect performance
- Look for pre-built views or materialized views that might simplify the query
4. Write the Query
Follow these best practices:
Structure:
- Use CTEs (WITH clauses) for readability when queries have multiple logical steps
- One CTE per logical transformation or data source
- Name CTEs descriptively (e.g.,
daily_signups,active_users,revenue_by_product)
Performance:
- Never use
SELECT *in production queries -- specify only needed columns - Filter early (push WHERE clauses as close to the base tables as possible)
- Use partition filters when available (especially date partitions)
- Prefer
EXISTSoverINfor subqueries with large result sets - Use appropriate JOIN types (don't use LEFT JOIN when INNER JOIN is correct)
- Avoid correlated subqueries when a JOIN or window function works
- Be mindful of exploding joins (many-to-many)
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 · 123 lines · 64 tokens per session scan A 4c7ef791db1f
write-query is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,082 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 2026-08-30.
Other skills, from other repositories
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…