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/tternquist/marklogic-mcp/marklogic-performancenpx skills add tternquist/marklogic-mcp --skill marklogic-performancegit clone --depth 1 https://github.com/tternquist/marklogic-mcpWhat 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 | $0.00121 | $0.01728 |
| Opus 5 | $0.00060 | $0.00864 |
| Sonnet 5 | $0.00024 | $0.00346 |
| Haiku 4.5 | $0.00012 | $0.00173 |
Grade A, and why
marklogic-performance 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MarkLogic Performance
Architecture in one paragraph
E-nodes (Evaluator) parse requests, execute XQuery/SJS, and do filtering, snippeting, and all SPARQL joins. D-nodes (Data Manager) store data and indexes, resolve indexes, read from disk, and run background merges. A combined node does both. Around 16+ nodes, separate E and D for analytics workloads.
The two-step search process — the usual culprit
- Index resolution (D-nodes) → candidate fragment IDs from indexes.
- Filtering (E-nodes) → load each candidate document and verify the full match.
cts:search runs filtered by default. When a query is fully backed by range and word
indexes, add the "unfiltered" option and step 2 disappears.
Diagnostics:
ml_profile_query→filterMisses > 0means step 2 is doing real work.cts:contains(result, query)returns false for a false positive — a quick way to measure the false-positive rate directly.
Reading cache stats
| Cache | Holds | A miss means |
|---|---|---|
| List cache | index term lists (D-node) | disk read during index resolution |
| Compressed tree cache | document bodies (D-node) | disk read during filtering |
| Expanded tree cache | uncompressed doc trees (E-node) | document expansion work |
| Triple cache | triple data for SPARQL | normal on first query |
Always compare a cold run against a warm run. Many misses on the first query are expected; the same misses on repeat runs indicate a structural bottleneck, not startup.
When a range index is mandatory
cts:range-query,cts:element-range-queryORDER BYin a FLWOR — on the ORDER BY field (last XPath step)ml_values_query,ml_facets_query— range index or element word index- Optic
ORDER BY— on the sort column; without one, all documents load to sort
Missing range index + filtered search is the worst case: a full document scan.
Run ml_indexes_list before writing any range-dependent query.
Optic rules
ml_explain_optic shows the plan. Read the node types:
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 · 137 lines · 121 tokens per session scan A ac104a0fb011
marklogic-performance is a skill published in the GitHub repository tternquist/marklogic-mcp (3 stars, last pushed 12d ago), licensed MIT. It adds 121 tokens to every session and 1,728 once invoked, about $0.0006 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
prisma-upgrade-v7
Complete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7 errors, or migrating existing projects. Triggers on "upgrade to prisma 7", "prisma 7 migration", "prisma-client generator", "driver adapter required".
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
sqlitecpp-update-sqlite
How to update the bundled SQLite3 amalgamation (sqlite3/sqlite3.c and sqlite3.h), the Meson wrap, README.md, and CHANGELOG.md. Use when upgrading SQLite, refreshing the vendored amalgamation, or bumping the sqlite3 wrap.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK…
mongodb-natural-language-querying
Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill whenever the user asks to write, create, or generate MongoDB queries, wants to filter/query/aggregate data in MongoDB, asks "how do I query...", needs help with…
sql-translate
Translate SQL queries between database dialects (Snowflake, BigQuery, PostgreSQL, MySQL, etc.).