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 skills add tulip/tulip-mcp --skill explore-instancegit clone --depth 1 https://github.com/tulip/tulip-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/tulip/tulip-mcp/explore-instance)<a href="https://agentmods.dev/skills/tulip/tulip-mcp/explore-instance"><img src="https://agentmods.dev/badge/skills/tulip/tulip-mcp/explore-instance/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/tulip/tulip-mcp/explore-instance"><img src="https://agentmods.dev/badge/skills/tulip/tulip-mcp/explore-instance.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 | $0.00053 | $0.00940 |
| Opus 5.5 | $0.00021 | $0.00376 |
| Sonnet 5.5 | $0.00011 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
explore-instance 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 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.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore a Tulip instance
Keywords
list tables, list users, list stations, list machines, list apps, audit, instance overview, who has access, what's deployed, environment, shop floor, overview
Overview
This skill helps you survey a Tulip instance — what data tables exist, how stations are configured, who the users are, and what machine types are defined. It's useful for audits, onboarding to a new instance, or answering broad "what do we have?" questions.
Use this skill when: The user wants to understand the current state of their Tulip instance, audit configurations, or explore what's deployed.
Workflow
Tables and data
listTables() # All tables with names and column info
getTable(tableId="<id>") # Full table schema including column types
countTableRecords(tableId="<id>") # How many records are in a table
listTableAggregations(tableId="<id>") # Saved aggregations on a table
listTableQueries(tableId="<id>") # Saved queries on a table
Stations and shop floor
listStations() # All stations
getStation(stationId="<id>") # Station details
listStationGroups() # How stations are organized
getStationGroup(stationGroupId="<id>") # Group details
listStationAppAssignments(stationId="<id>") # What apps are assigned to a station
listStationGroupAppAssignments(stationGroupId="<id>") # App assignments for a group
listInterfaces() # Player interfaces
getInterface(interfaceId="<id>") # Interface details
Apps
listAppGroups() # App groups and their containing apps
Users and access
listUsers() # All users in the instance
getUser(userId="<id>") # User details including role
listUserRoles() # All available roles
getUserRole(userRoleId="<id>") # Role details
listUserGroups() # All user groups
getUserGroup(userGroupId="<id>") # Group details
getUserGroupUsers(userGroupId="<id>") # Members of a user group
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 First seen · 109 lines · 53 tokens per session scan A 1d1ec350dc85
explore-instance is a skill published in the GitHub repository tulip/tulip-mcp (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 940 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
hardware-tuning
Detect server cores/RAM/disk from system tables, then recommend ClickHouse settings sized to that hardware.
sensors-add-skill
Use when registering or adding a new sensor type to the telemetry system's registry, codegen, migrations, and changelog.
ha-recorder
Work with the Home Assistant recorder and statistics. Use when asked about history, statistics, long-term stats, database, recorder exclusion, or historical data.
flashdb-integration
Use when integrating, porting, configuring, or debugging FlashDB KVDB or TSDB on MCU flash, filesystems, RTOS, or bare-metal projects.
nvidia-driver-check
Check if a newer NVIDIA driver is available using TinyNvidiaUpdateChecker.
RSQLite
R RSQLite package for SQLite databases. Use for embedded SQLite database connections.