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-fasttrack/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-fasttrack)<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-fasttrack"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-fasttrack/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-fasttrack"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-fasttrack.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 | $0.00104 | $0.01525 |
| Opus 5.5 | $0.00042 | $0.00610 |
| Sonnet 5.5 | $0.00021 | $0.00305 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
marklogic-fasttrack 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MarkLogic FastTrack
FastTrack is a React component library over MarkLogic's Search API. The UI is driven almost entirely by a stored search options set — get that right and the components mostly configure themselves.
Order of work
- Confirm the indexes exist (
ml_indexes_list). Every facet constraint needs one. - Write the search options and store with
ml_search_options_put. - Verify server-side with
ml_searchbefore touching React. - Scaffold the React app.
Skipping step 3 is the usual reason a FastTrack UI shows no facets — the options set was rejected or the index is missing, and the component just renders empty.
Constraint index rules
Prefer path indexes. For JSON content, a path-index with path //fieldName uses a
range-path-index, creatable via admin:database-add-range-path-index through
ml_eval_xquery.
json-property is the fallback — it needs a range-json-property-index, which is only
creatable through the Management API on port 8002.
// string facet
{"name":"field","range":{"type":"xs:string","facet":true,"path-index":{"text":"//field"}}}
// numeric facet
{"name":"field","range":{"type":"xs:decimal","facet":true,"path-index":{"text":"//field"}}}
// date facet (with buckets)
{"name":"field","range":{"type":"xs:date","facet":true,"path-index":{"text":"//field"}}}
Dates stored as ISO strings (YYYY-MM-DD) should use xs:string, not xs:date —
ISO strings sort chronologically, and this avoids a cast that will fail on any malformed
value.
Geospatial (map widget) — a geo-elem-pair constraint with parent/lat/lon. Only add
it if the schema actually has geo fields.
⚠ Bucket syntax: name, not label
CORRECT: {"name":"Under 80k","lt":"80000"}
CORRECT: {"name":"80-100k","ge":"80000","lt":"100000"}
WRONG: {"label":"Under 80k","lt":"80000"}
label produces XDMP-VALIDATEMISSINGATTR and a 400 from the REST API. Every bucket
needs a name.
Options skeleton
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 · 141 lines · 104 tokens per session scan A 3edf5b1821bb
marklogic-fasttrack is a skill published in the GitHub repository tternquist/marklogic-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,525 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.
marklogic-fasttrack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marklogic-fasttracktternquist/marklogic-mcp | Skill | 4 | 1mo ago | MIT | A | 104 | Claude Code |
| payloadpayloadcms/payload | Skill | 46k | yesterday | MIT | A | 43 | Claude Code, Codex |
| saas-builderixartz/SaaS-Boilerplate | Skill | 7.5k | 5d ago | MIT | A | 75 | Claude Code, Codex |
| build-with-tinybasetinyplex/tinybase | Skill | 5.2k | 16d ago | MIT | A | 90 | Claude Code, Codex |
| db-seedjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 96 | Claude Code |
| monitoring-ingestion-pipelinePostHog/posthog | Skill | 41k | yesterday | none | A | 71 | Claude Code, Codex |
| d1-drizzle-schemajezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 90 | Claude Code |