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 matshoppenbrouwers/anvil-uplink-cli --skill anvil-bridgegit clone --depth 1 https://github.com/matshoppenbrouwers/anvil-uplink-cliWrote 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/matshoppenbrouwers/anvil-uplink-cli/anvil-bridge)<a href="https://agentmods.dev/skills/matshoppenbrouwers/anvil-uplink-cli/anvil-bridge"><img src="https://agentmods.dev/badge/skills/matshoppenbrouwers/anvil-uplink-cli/anvil-bridge/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/matshoppenbrouwers/anvil-uplink-cli/anvil-bridge"><img src="https://agentmods.dev/badge/skills/matshoppenbrouwers/anvil-uplink-cli/anvil-bridge.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 | $0.00144 | $0.01956 |
| Opus 5 | $0.00072 | $0.00978 |
| Sonnet 5 | $0.00029 | $0.00391 |
| Haiku 4.5 | $0.00014 | $0.00196 |
Grade A, and why
anvil-bridge 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 11d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anvil-bridge
anvil-bridge is a CLI that opens an Anvil Server Uplink connection and exposes Data Table access and server-callable invocation from the shell. Use it instead of pasting Python into the Anvil Server Console.
Source: https://github.com/matshoppenbrouwers/anvil-uplink-cli
Critical rules (read first)
-
Call by full path. The CLI lives in a dedicated venv that is NOT on
PATHin fresh Bash subshells (Claude Code spawns one per tool call). Callinganvil-bridgebare will usually fail with "command not found".- Default install path:
~/.anvil-bridge/bin/anvil-bridge(absolute:/home/<user>/.anvil-bridge/bin/anvil-bridgeon Linux/WSL). - Discover it:
ls ~/.anvil-bridge/bin/anvil-bridge 2>/dev/null || which anvil-bridge.
- Default install path:
-
NEVER pass the Uplink key inline. Not as
--key ..., not asANVIL_BRIDGE_KEY=... anvil-bridge .... The key lands in the transcript and creates a prompt-injection exfiltration path. The CLI resolves the key from a.envancestor viadotenv:ANVIL_UPLINK_KEY— it works silently, do not interfere with it. Also do NOTcat .envor read the key file. -
Run from inside a directory with a
.envancestor. The CLI walks up from CWD looking for.env. If the user's shell is in a directory with no.envabove it, the key won't resolve —cdinto the relevant repo first (or tell the user to). -
Prefer
--jsonwhen the output is for parsing or passing to another tool. Pretty-printed tables are for humans and get garbled in agent transcripts.
First call in any session
Always verify the connection works before querying:
<BRIDGE> doctor
Expected output includes connected: yes and the configured profile. If it fails:
auth error→ key isn't resolving; user needs a.envwithANVIL_UPLINK_KEYat or above CWD, or a configured profile. Do NOT try to fix by passing the key inline.command not found→ you used bareanvil-bridgeinstead of the full path.connection refused/ timeout → Anvil Server Uplink isn't enabled in the app's Editor; user has to fix in the Anvil UI.
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.
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.
- 11d ago First seen · 125 lines · 144 tokens per session scan A c6a821a3d321
anvil-bridge is a skill published in the GitHub repository matshoppenbrouwers/anvil-uplink-cli (5 stars, last pushed 4mo ago), licensed MIT. It adds 144 tokens to every session and 1,956 once invoked, about $0.0007 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 skills, from other repositories
ship-safe-scan
Quick scan for leaked secrets — API keys, passwords, tokens, database URLs. Use when the user wants to check for hardcoded secrets or exposed credentials.
backend-development
Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.
database-connections
Connect a Mendix app to an external database over JDBC with the External Database Connector, and define the queries microflows run against it. Use when the app must read or write Oracle, PostgreSQL, MySQL or SQL Server directly from a microflow.
connect-rapidminer-graph
Fetch data from a RapidMiner graph mart or any SPARQL 1.1 HTTP endpoint (AnzoGraph and friends) and surface it as Mendix entities. Use when a graph database with a SPARQL endpoint has to feed a Mendix app read-only.
mendix-odata-pushdown
Push OData query options into the SQL of a Mendix resource served by a read microflow, so $filter, $orderby, $top, $skip, $count and the key lookup reach the database instead of being silently dropped. Use when publishing an OData resource over data Mendix has no table for — a warehouse view, a legacy database, a…
generate-domain-model
Generate a complete Mendix domain model in MDL — entities, attributes, associations, enumerations — and validate it. Use when asked for a domain model for a business area (e-commerce, HR, CRM, …) rather than a single entity.