What is semaphore-integration?

A guide for connecting Semaphore, a content-classification service, with MarkLogic, a document database. It covers several ways to classify documents while loading them or after they are stored.

Use it to classify documents during import, enrich stored documents later, classify through a REST transformation, or add classification to a Data Hub Framework pipeline.

It helps choose an integration design that fits new data, existing documents, multiple sources, or entity matching. It also highlights connectivity and configuration issues.

How tternquist/marklogic-mcp configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/tternquist/marklogic-mcp/master/.claude/skills/semaphore-integration/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/tternquist/marklogic-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/semaphore-integration/github.svg)](https://agentmods.dev/skills/tternquist/marklogic-mcp/semaphore-integration)

Your own site

<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/semaphore-integration"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/semaphore-integration/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/semaphore-integration"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/semaphore-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,762 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00110	$0.01762
Opus 5.5	$0.00044	$0.00705
Sonnet 5.5	$0.00022	$0.00352
Haiku 4.5	$0.00011	$0.00176

Measured 2mo ago against content hash 6946b4fcee3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

semaphore-integration 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 2mo 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.

.claude/skills/semaphore-integration/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semaphore + MarkLogic Integration

Choose a pattern

Pattern	How it works	Best for
A. Ingest + classify (preferred for new pipelines)	Flux calls the CLS inline via `--classifier-*` flags; categories written at ingest	new data pipelines; no raw/enriched split needed
B. Reprocess + enrich	Documents already loaded; an SJS transform calls the CLS via `xdmp.httpPost()` and patches each doc, parallelised by Flux	legacy data; adding Semaphore to an existing deployment
C. Transform on ingest	A REST transform maps raw→canonical and classifies in one step; Flux passes `--transform <name>`	simultaneous mapping and classification
D. DHF pipeline	Ingestion → Mapping → custom Semaphore step → optional Mastering	multiple sources; STAGING/FINAL split; entity mastering

Default to Pattern A. It runs outside MarkLogic, so it sidesteps the outbound-HTTP restrictions that make B fragile (see the network note below).

Configuration

CLS (Classification Server) — required for classification:

SEMAPHORE_HOST, optionally SEMAPHORE_SCS_PORT (default 5058)
or SEMAPHORE_URL=http://<host>:<port> for an explicit override
no authentication by default
verify with semaphore_status

KMM (Knowledge Model Manager / Studio) — required for taxonomy authoring:

SEMAPHORE_USERNAME and SEMAPHORE_PASSWORD — KMM uses Java EE form auth, not Basic auth, so these are a separate credential path from the CLS
SEMAPHORE_KMM_PORT (default 5080)
verify with semaphore_studio_status

If semaphore_classify works but semaphore_kmm_* fails, the problem is almost always these KMM-specific settings, not the CLS.

Discovery before designing

semaphore_publish_sets — which taxonomy rule sets are loaded and active in the CLS
semaphore_classes — classification class names (taxonomy domain names)
semaphore_classify with a sample snippet and threshold=0 — validate real output

If no rule sets are loaded, use semaphore_kmm_model_create + semaphore_kmm_skos_load to import a vocabulary, then publish. The full authoring workflow — including the mandatory SKOS-XL reification step — is in the semaphore-taxonomy skill.

Read the full file on GitHub · 150 lines

Files

What ships with it

1 file 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/enrichment-module.md 4.4 KB

Changes

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.

2mo ago First seen · 150 lines · 110 tokens per session scan A 6946b4fcee3e

Subscribe to this mod's changes

semaphore-integration is a skill published in the GitHub repository tternquist/marklogic-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 1,762 once invoked, about $0.0004 per session on Opus 5.5. 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.

Data and AI Databases

semaphore-integration next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
semaphore-integrationtternquist/marklogic-mcp	Skill	4	1mo ago	MIT	A	110	Claude Code
embeddingsruvnet/ruflo	Skill	81k	yesterday	MIT	A	62	Claude Code
rag-pineconedavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	65	Claude Code, Codex
data-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	35	Claude Code, Codex
similarity-search-patternsforyourhealth111-pixel/Vibe-Skills	Skill	3.8k	3d ago	Apache-2.0	A	30	Claude Code, Codex
ingesting-into-data-lakeaws/agent-toolkit-for-aws	Skill	3.4k	yesterday	Apache-2.0	A	228	Claude Code
graphjin-envdosco/graphjin	Skill	3.2k	5d ago	Apache-2.0	A	61	Claude Code, Codex

marklogic-mcp: Skill for Claude Code