Borrowing it
Nothing to install: this file belongs to tternquist/marklogic-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tternquist/marklogic-mcp/master/.claude/skills/marklogic-project-setup/SKILL.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/skills/tternquist/marklogic-mcp/marklogic-project-setup)<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-project-setup"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-project-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-project-setup"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-project-setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.03380 |
| Opus 5.5 | $0.00000 | $0.01352 |
| Sonnet 5.5 | $0.00000 | $0.00676 |
| Haiku 4.5 | $0.00000 | $0.00338 |
Grade A, and why
marklogic-project-setup scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
in `gradle.properties` makes every subsequent request (curl tests, module reloads, How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MarkLogic Project Setup (ml-gradle)
When to scaffold instead of using write tools
The MCP write tools (ml_document_put, ml_tde_install, ml_extension_put) change a
running database. They leave nothing in source control and nothing to promote to
another environment.
Scaffold a project instead when you hear any of:
- "build me an app / API / service / backend"
- "create a new project / repo"
- "set up MarkLogic for…"
- "add a REST endpoint" / "expose this as an API"
- "add an index" / "deploy to production" / "promote to staging"
- "I want this in CI/CD" / "version-controlled" / "multi-environment"
- any request naming a custom REST extension, transform, or module path
Ad-hoc exploration and one-off queries do not need a project.
First decision: plain ml-gradle or DHF?
| Use plain ml-gradle when | Use DHF when |
|---|---|
| custom application, not a data-integration pipeline | entity-centric integration from multiple source systems |
| a single content database | staging (raw) and final (mastered) databases needed |
| you want full control without DHF conventions | ingestion → mapping → matching/merging (mastering) |
| lighter footprint, simpler deploy | SmartMastering or Entity Services features required |
The template below is plain ml-gradle. For DHF, the dhf_* tools scaffold and run flows;
DHF still sits on an ml-gradle project, so most of this skill still applies.
Using the template
templates/ is a complete, deploy-ready ml-gradle tree. Copy it into the target
directory and rename:
cp -r templates/ <project-dir>/
Then replace throughout:
| Placeholder | Replace with |
|---|---|
myapp |
the application name (also in mlAppName, role filenames, TDE schema) |
8010 |
the REST port (mlRestPort) |
localhost |
the target host (mlHost) |
admin / admin |
real credentials — do not commit these |
Deploy with:
cd <project-dir>
gradle mlDeploy
Drop any part you don't need — src/main/ml-data, the roles, the REST extension, and
the environment overlays are all independent.
What ships with it
32 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/gradle-tasks.md 7.4 KB
- references/rest-extensions.md 9.3 KB
- templates/.gitignore 48 B
- templates/build.gradle 816 B
- templates/gradle-dev.properties 53 B
- templates/gradle-local.properties.example 746 B
- templates/gradle-prod.properties 54 B
- templates/gradle.properties 1.7 KB
- templates/README.md 2.6 KB
- templates/settings.gradle 27 B
- templates/src/main/dev-config/databases/content-database.json 97 B
- templates/src/main/ml-config/databases/content-database.json 485 B
- templates/src/main/ml-config/databases/schemas-database.json 46 B
- templates/src/main/ml-config/databases/triggers-database.json 47 B
- templates/src/main/ml-config/security/roles/1-myapp-reader.json 123 B
- templates/src/main/ml-config/security/roles/2-myapp-writer.json 144 B
- templates/src/main/ml-data/items/collections.properties 52 B
- templates/src/main/ml-data/items/item-001.json 91 B
- templates/src/main/ml-data/items/item-002.json 92 B
- templates/src/main/ml-data/items/permissions.properties 104 B
- templates/src/main/ml-modules/options/default.xml 288 B
- templates/src/main/ml-modules/root/lib/items-lib.sjs 1.8 KB
- templates/src/main/ml-modules/services/echo.sjs 690 B
- templates/src/main/ml-modules/services/items.sjs 2.5 KB
- templates/src/main/ml-modules/services/metadata/echo.xml 224 B
- templates/src/main/ml-modules/services/metadata/items.xml 621 B
- templates/src/main/ml-modules/transforms/identity.sjs 267 B
- templates/src/main/ml-modules/transforms/metadata/identity.xml 160 B
- templates/src/main/ml-schemas/tde/items.tdej 632 B
- templates/src/test/ml-modules/root/test/suites/items/setup.sjs 711 B
- templates/src/test/ml-modules/root/test/suites/items/teardown.sjs 303 B
- templates/src/test/ml-modules/root/test/suites/items/test-find-by-category.sjs 1022 B
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.
- 1mo ago Changed · +47 lines 85b5e9f8aab9
- 2mo ago First seen · 235 lines · 0 tokens per session scan A 2b88817218ab
marklogic-project-setup is a skill published in the GitHub repository tternquist/marklogic-mcp (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,380 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
marklogic-project-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marklogic-project-setuptternquist/marklogic-mcp | Skill | 4 | 1mo ago | MIT | A | 0 | Claude Code |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | yesterday | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 923 | yesterday | MIT | A | 79 | Claude Code, Codex |
| volcengine-rds-postgresqlbytedance/agentkit-samples | Skill | 484 | today | Apache-2.0 | A | 63 | Claude Code, Codex |