By bino-bi
Co-author and autopilot pixel-perfect IBCS PDF reports with bino — Report-as-Code (YAML + SQL). Registers the bino MCP server and ships IBCS knowledge, slash commands, and a checkpointed autopilot pipeline.
Probe a CSV / Excel / database source and scaffold a typed DataSource (and optional DataSet).
Autopilot — delegate the full requirements → data → authoring → validation → build pipeline to bino subagents, pausing only at safety gates. Tier 1 (checkpointed).
Render the bino report artefacts to PDF.
Validate the bino project and walk the diagnostics to green.
Scaffold a fresh bino report bundle (bino.toml + sample manifests) ready to build or preview.
Autopilot authoring subagent. Chooses IBCS components, drafts report manifests against the live schema, validates every draft before writing, wires embeddable → LayoutPage → ReportArtefact leaves-first, and authors the data-aware narrative Text tied to the brief's primary message. Sole editor of report-structure manifests. Never touches DataSource / DataSet.
Autopilot data subagent. Locates and profiles sources, maps raw columns to IBCS scenario slots (ac/pp/fc/pl) and variances, authors typed DataSet SQL, runs the single data-validation pass, and produces the DATA PLAN. Sole editor of DataSource / DataSet / ConnectionSecret. Owns the honest "the data can't satisfy this."
Autopilot guardrail subagent. Runs a four-layer check (schema, IBCS C1–C14, build-readiness, acceptance spot-checks) and emits a VERDICT with per-diagnostic routing. Diagnoses, never edits, never builds — a judge that wields the pen is not a guardrail.
The disciplined loop for authoring bino report manifests (YAML + SQL) through the bino MCP server — read the live schema, learn a dataset's columns, draft, validate_draft, write, then validate_project and build. Use whenever creating, editing, or wiring bino manifests (DataSource, DataSet, Table, Text, Tree, ChartTime, ChartStructure, LayoutPage, ReportArtefact, …) or fixing validation diagnostics. Pairs with bino-ibcs for the report semantics.
Map raw source columns onto IBCS scenario slots (ac/pp/fc/pl), derive variances (d_/dr_), choose the grain, and write disciplined typed DataSet SQL for a bino report. Use when the bino-data autopilot phase models a source into datasets, or when co-authoring a DataSet. Owns the honest "the data can't satisfy this" — populate unmet[] rather than fabricate a column.
The IBCS rubric for bino reports — the semantics the schema can't carry. Scenarios (ac/pp/fc/pl), variances (d_/dr_ … pos/neg/neu), choosing between Table / ChartTime / ChartStructure, and data-aware narrative Text. Use when modeling a report's scenarios and variances, picking a visualization, or writing commentary, so the report is IBCS-compliant.
The bino autopilot policy — the phase sequence, the autonomy tiers, the four checkpoint gates, the eight hard safety gates, the run-start preflight, the subagent-spawn contract, and the fix-loop policy. Used by /bino:autopilot on the main thread to sequence the bino subagents and hold the gates. The orchestrator never authors or edits manifests — it routes.
Elicit report requirements from the human and produce the REPORT BRIEF — the structured contract (audience, primary message, scenarios, variance, granularity, visualization intent, acceptance criteria) that the bino autopilot subagents consume. Use during /bino:autopilot phase 1 to turn a free-text goal into a brief. Runs on the main thread (it asks the human).
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Pixel-perfect PDF reports from YAML manifests and SQL queries.
Documentation · Download · Discussions
[!WARNING] bino is under active development. Configuration and CLI APIs are not yet stable — expect breaking changes between releases.
[!NOTE] bino is currently tightly coupled to bn-template-engine as its visualization engine. This coupling will be removed in a future release, making the Viz Engine pluggable.
bino is a command-line tool that turns declarative YAML manifests and SQL queries into production-ready PDF reports. It uses DuckDB as an embedded SQL engine and Chrome headless shell for pixel-perfect PDF rendering.
For full documentation, visit cli.bino.bi.
bino preview watches for changes and hot-reloads in the browser via SSE.bino lint catches manifest errors before build. JSON Schemas power IDE auto-completion.vscode-bino/.macOS (Homebrew):
brew install bino-bi/tap/bino-cli
Linux / macOS (script):
curl -fsSL https://github.com/bino-bi/bino-cli-releases/releases/latest/download/install.sh | bash
Windows (PowerShell):
irm https://github.com/bino-bi/bino-cli-releases/releases/latest/download/install.ps1 | iex
Or download a binary from the latest release.
bino init my-report # scaffold a new report bundle
cd my-report
bino build # build all artefacts
See the Getting Started guide for a full walkthrough.
Manifest Discovery → YAML Parsing → Validation → Datasource Collection → Dataset Execution → HTML Rendering → PDF Generation
Manifests are YAML documents typed by a kind field (DataSource, DataSet, LayoutPage, ReportArtefact, etc.). DuckDB serves as the embedded SQL engine for all data queries. Chrome headless shell converts rendered HTML into PDF output.
Each bino release declares the range of bn-template-engine versions it supports. The contract lives in internal/engine/compat.go as SupportedEngineRanges and is enforced by build, preview, serve, lint, and lsp. On a mismatch, build/preview/serve exit non-zero before any pipeline work; lint reports rule engine-version-incompatible and exits non-zero; lsp (and the VS Code extension) publishes an error-severity diagnostic on the engine-version line of bino.toml.
Range syntax follows npm conventions (comparators, hyphen ranges, x-ranges, tilde, caret, AND within an entry, OR across entries) with npm pre-release inclusion semantics: a pre-release version satisfies a range only when at least one comparator in that range explicitly mentions a pre-release of the same MAJOR.MINOR.PATCH.
Current supported ranges: >=1.0.0-alpha, <2.0.0-0 — any 1.x release or pre-release is accepted; 0.x and 2.0.0+ are rejected. To use a specific engine version, pin it in bino.toml:
engine-version = "v1.0.0-alpha.15"
npx claudepluginhub bino-bi/bino-cli --plugin binoHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications