tooljet-app-builder

A builder for creating ToolJet apps, such as dashboards and internal tools, from connected data sources, queries, and interface components.

In plain words
What is it for?
Use it to create a new ToolJet app or modify an existing one, including its pages, data queries, components, and user interactions.
Why use it?
It gives an agent a defined process for planning pages, connecting data, wiring actions, and checking the result without assuming unsupported ToolJet features.

Skill for Claude CodeCodex

Part of the tooljet-app-builder plugin — 2 skills, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/tooljet/tooljet-mcp/skill
Any agent
npx skills add ToolJet/tooljet-mcp --skill skill
Clone the repo
git clone --depth 1 https://github.com/ToolJet/tooljet-mcp

Made for: Claude Code, Codex.

Or install tooljet-app-builder, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.01218
Opus 5 $0.00028 $0.00609
Sonnet 5 $0.00011 $0.00244
Haiku 4.5 $0.00006 $0.00122

Measured 3d ago against content hash 5f3317c75790, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tooljet-app-builder 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/browser-audit.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skill/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ToolJet app builder

Build only what ToolJet's real components, connected datasources, and MCP tools support. Never invent a property, action, integration, or successful result. User requirements override the adaptable quality defaults in the references.

Core workflow

  1. Call list_workspaces; if several exist, confirm and switch before creating anything. Decide the page architecture before components. A simple single-job app can stay on one page; separate substantial jobs into an overview plus focused pages.
  2. Treat 3+ substantive pages, 2+ complex workflows, a multi-table model, or multiple integrations as a large build. Before mutations, show the page/phase plan and rough time ranges, then ask for phased checkpoints (recommended) or the whole app in one run. Do not re-ask if the user already chose.
  3. Call create_app, preserve its ids and links, then call list_datasources. Fetch only the component, event-action, and datasource contracts needed for the current phase, using one selective batch per contract class, and reuse them. Typed component catalog reads are compact by default; request exact sections and property_keys/style_keys instead of broad full contracts. Confirm a new data model before creating it; ToolJet DB table names are at most 31 characters.
  4. Plan a complete useful phase with stable client_ref values. Root components omit parent and slot_name; page ids are not component parents. Await lint_app_spec as a standalone barrier, fix its errors and review warnings, then pass its one-time plan_token to apply_app_phase. Never run the linter alongside a write. Put planned persisted component definition patches in component_updates; use targeted update tools for ad-hoc repairs, never duplicate resources or rebuild the app. After an error, inspect it and change the repair—never replay an identical mutation.
  5. Verify each completed page/primary flow using references/qa.md. Static validation does not prove runtime query behavior, rendering, or event delivery.
  6. Share editor_url while authoring. After the first meaningful page works, open viewer_url in the built-in browser when available and reuse that tab. Final handoff includes both links, what works, limitations, and a short tool-call-count efficiency note.

Read the full file on GitHub · 53 lines

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.

  1. 3d ago First seen · 53 lines · 56 tokens per session scan A 5f3317c75790

Subscribe to this mod's changes

tooljet-app-builder is a skill published in the GitHub repository ToolJet/tooljet-mcp (21 stars, last pushed 3d ago), licensed ISC. It adds 56 tokens to every session and 1,218 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens