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 instructions/tternquist/marklogic-mcp/claude-mdgit clone --depth 1 https://github.com/tternquist/marklogic-mcpWrote 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/instructions/tternquist/marklogic-mcp/claude-md)<a href="https://agentmods.dev/instructions/tternquist/marklogic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tternquist/marklogic-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.03875 | $0.03875 |
| Opus 5 | $0.01937 | $0.01937 |
| Sonnet 5 | $0.00775 | $0.00775 |
| Haiku 4.5 | $0.00387 | $0.00387 |
Grade A, and why
marklogic-mcp CLAUDE.md 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 3d 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MarkLogic MCP — Agent Working Instructions
This file is read automatically by Claude Code when working in this repository. Follow all principles below for every feature addition, bug fix, and refactor.
Core Principle: Problem-First Thinking
Before writing any new tool, prompt, resource, or client method, answer:
-
What is the user problem? State it as a concrete goal, not a technical task.
- Bad: "expose the
/v1/valuesREST endpoint" - Good: "allow agents to count distinct values of a field without scanning every document"
- Bad: "expose the
-
What is the MarkLogic-native capability? Every user problem has a best-fit MarkLogic API. Identify it before writing any code.
- Bulk import → Flux pipeline (
flux_import) - Counting/bucketing → Values/range index API (
ml_values_query) - Joins/aggregates → Optic API over TDE views (
ml_optic_query) - Full-text → Universal index search (
ml_search) - Graph traversal → Triple store / SPARQL (
ml_sparql_query) - Content classification / auto-tagging → Semaphore CLS + KMM (
semaphore_classify,semaphore_publish,flux_importwithclassify_with_semaphore: true)
- Bulk import → Flux pipeline (
-
What must an agent discover first? If the tool requires a pre-existing index, collection, or TDE template, document that prerequisite in the tool's
descriptionstring so the agent knows to check before calling. -
Is this already covered? Check the 18 existing tool groups before adding a new tool. Extend an existing tool (via a new parameter) rather than adding a new one unless the problem type is genuinely distinct.
Where Guidance Lives — Skills First
Tool descriptions are interface contracts. Skills are the manual. Do not put
tutorials, recipe collections, or troubleshooting playbooks into a server.tool()
description string — that text is loaded into every request whether or not it is
relevant.
Agent Skills (.claude/skills/<name>/SKILL.md)
Skills follow the Agent Skills spec and are
discovered automatically by Claude Code, GitHub Copilot CLI, and other spec-adopting
agents from .claude/skills/. A skill is YAML frontmatter plus Markdown:
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.
- 3d ago First seen · 320 lines · 3,875 tokens per session scan A 3164e7116ca8
marklogic-mcp CLAUDE.md is an instructions file published in the GitHub repository tternquist/marklogic-mcp (3 stars, last pushed 13d ago), licensed MIT. It adds 3,875 tokens to every session, about $0.0194 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 instructions, from other repositories
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律（强制） and 发版检查清单（每次 npm publish 前必须按序执行）.
jdbc-driver CLAUDE.md
Claude Code instructions for keboola/jdbc-driver, covering claude.md, project overview, build & test commands, jdbc driver and vscode sqltools extension.
MCP-SqlServer CLAUDE.md
Claude Code instructions for Aron-Valenzuela/MCP-SqlServer, covering claude.md, project overview, setup (for each user), 1. install dependencies and 2. configure claude desktop.
plsql-intelligence AGENTS.md
Instructions for MuhDur/plsql-intelligence, covering agents.md — plsql-intelligence, founder constraints (plan.md §3, non-negotiable), plan rules to internalize (plan.md §4), rule 1 – absolute (do not ever violate this) and irreversible git & filesystem actions.