bilig copilot-instructions.md

Project instructions for Bilig, including its required Node.js and pnpm versions, development commands, architecture, and agent workpaper rules. A workpaper is a record of intermediate evidence used to verify automated work.

In plain words
What is it for?
Use them when developing Bilig, running its web app, changing shared packages, or checking work with tests and build commands.
Why use it?
They prevent version mismatches and show how to build, test, lint, and type-check the project correctly.

Instructions file for GitHub Copilot

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 instructions/proompteng/bilig/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/proompteng/bilig

Made for: GitHub Copilot.

Per session 1,895 This file is loaded in full into every session.
When invoked 1,895 The same file — it is already loaded in full.
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 $0.01895 $0.01895
Opus 5 $0.00948 $0.00948
Sonnet 5 $0.00379 $0.00379
Haiku 4.5 $0.00189 $0.00189

Measured 2d ago against content hash 38da8544e4bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bilig copilot-instructions.md 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 2d 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.

.github/copilot-instructions.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bilig Copilot instructions

Toolchain and commands

  • Use Node 24.11.1 locally via .nvmrc / .node-version. Published runtime packages allow Node 22+ and are smoke-tested under Node 22 in the runtime-package workflow. pnpm 10.32.1 remains required.
  • Activate the pinned runtime before running pnpm commands (nvm use in a normal shell, or let your version manager honor .node-version automatically).
  • Install dependencies with pnpm install.
  • Start the default app shell with pnpm dev (apps/web).
  • Other dev entrypoints:
    • pnpm dev:web
    • pnpm dev:local
    • pnpm dev:sync
  • Build the workspace with pnpm build.
  • Rebuild the AssemblyScript/WASM fast path with pnpm wasm:build.
  • Lint with pnpm lint.
  • Auto-fix lint issues with pnpm lint:fix.
  • Type-check the composite TypeScript workspace with pnpm typecheck.
  • Run the full Vitest suite with pnpm test.
  • Run one Vitest file with pnpm exec vitest --run packages/core/src/__tests__/engine.test.ts.
  • Run one Vitest test by name with pnpm exec vitest --run packages/core/src/__tests__/engine.test.ts -t "recalculates simple formulas".
  • Run browser smoke tests with pnpm test:browser.
  • Run the web-shell Playwright suite with pnpm exec playwright test e2e/tests/web-shell.pw.ts --config playwright.config.ts.
  • Run the full repository gate with pnpm run ci.
  • Use tea for Forgejo workflow checks and logs (for example tea login ls, tea actions ls, and tea actions jobs --run <id>).

High-level architecture

  • This repo is a pnpm monorepo with thin apps/* shells over reusable packages/*.
  • packages/core is the framework-agnostic spreadsheet engine. It owns workbook state, storage, dependency scheduling, snapshots, selectors, events, sync state, and execution routing.
  • packages/formula owns A1 addressing, lexer/parser, binding, optimization, translation, compatibility, and the JS evaluator.
  • packages/wasm-kernel is the AssemblyScript/WASM numeric fast path. packages/core decides when formulas stay on the JS path versus the WASM path.
  • packages/crdt, packages/binary-protocol, packages/worker-transport, packages/agent-api, and packages/storage-server make up the local-first sync and transport stack used by the browser and server runtimes.
  • packages/renderer is the custom workbook reconciler and workbook DSL.
  • packages/grid is the reusable React spreadsheet UI: selection, editing, metrics, inspectors, and workbook/grid views.
  • apps/web is the thin React/Vite shell around the shared workbook surface. Shared behavior should usually live in packages/renderer or packages/grid, not inside app folders.
  • apps/local-server hosts local workbook sessions and emits committed frames over websocket.
  • apps/sync-server is the remote sync/backend service surface.
  • When you need the architectural contracts, start with docs/architecture.md, docs/reconciler-layering.md, docs/local-first-realtime-loop.md, docs/public-api.md, and docs/testing-and-benchmarks.md.

Read the full file on GitHub · 108 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. 2d ago First seen · 108 lines · 1,895 tokens per session scan A 38da8544e4bd

Subscribe to this mod's changes

bilig copilot-instructions.md is an instructions file published in the GitHub repository proompteng/bilig (35 stars, last pushed 9d ago), licensed MIT. It adds 1,895 tokens to every session, about $0.0095 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 instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens