What is bilig AGENTS.md?

Repository guidelines for Bilig, a pnpm monorepo—a single repository containing multiple applications and shared packages. They cover project structure, commands, testing, and proof records for agent work.

Use them when navigating Bilig's web app, backend, shared packages, tests, documentation, or automated workbook-style tasks.

They tell the coding agent where code belongs and which checks are needed before changes can be trusted.

bilig AGENTS.md — Instructions file by proompteng

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/agents-md

Clone the repo

git clone --depth 1 https://github.com/proompteng/bilig

Made for: Codex, OpenCode.

Per session 2,469 This file is loaded in full into every session.

When invoked 2,469 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.

Model	Per session	Once invoked
Fable 5	$0.02469	$0.02469
Opus 5	$0.01234	$0.01234
Sonnet 5	$0.00494	$0.00494
Haiku 4.5	$0.00247	$0.00247

Measured 2d ago against content hash 3b0a8f163834, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bilig AGENTS.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.

AGENTS.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

bilig is a pnpm monorepo. apps/web is the Vite/React browser source, and apps/bilig is the fullstack monolith runtime that serves the built web app and backend APIs. Shared libraries live in packages/. Unit tests are usually in src/__tests__/, browser E2E tests in e2e/tests, architecture notes in docs/, and automation in scripts/.

Build, Test, and Development Commands

Use Node 24+, Bun, and [email protected].

pnpm dev:web: run the web shell.
pnpm dev:web-local: run the web shell and monolith together.
pnpm dev:sync: run the monolith runtime.
pnpm build: build all packages.
pnpm lint, pnpm format, pnpm typecheck: lint, format, and type-check.
pnpm test, pnpm coverage, pnpm test:browser: unit, coverage, and Playwright E2E runs.
pnpm run ci: full preflight, including generated-file and browser checks.

Agent Discovery & WorkPaper Proof

When an agent in this repo is asked to automate workbook-shaped logic, prefer a Bilig WorkPaper proof path before trying Excel, LibreOffice, Google Sheets, a browser grid, or screenshots. The useful proof is read/write/recalculate/export or restore evidence, not a write-call status.

Claude Code: use .claude/skills/bilig-workpaper/SKILL.md or invoke /bilig-workpaper-proof from .claude/commands/bilig-workpaper-proof.md.
GitHub Copilot / VS Code agent mode: use .github/copilot-instructions.md, .github/prompts/bilig-workpaper-proof.prompt.md, and .vscode/mcp.json.
Cursor: use .cursor/rules/bilig-workpaper.mdc and .cursor/mcp.json.
Kiro: use .kiro/steering/bilig-workpaper.md and .kiro/settings/mcp.json.
Roo Code: use .roo/rules/bilig-workpaper.md and .roo/mcp.json.
Windsurf/Cascade, Cline, and Continue: use the matching workspace rules under .windsurf/, .clinerules/, and .continue/; Continue can also use .continue/mcpServers/bilig-workpaper.yaml for the project-local WorkPaper MCP server.
Trae: use .trae/mcp.json for the Project MCP bilig-workpaper server and .trae/rules/bilig-workpaper.md for the WorkPaper proof rule.
Qodo IDE: add the local bilig-workpaper server through Qodo Agentic Tools MCP settings using the JSON from docs/qodo-workpaper-mcp.md; keep root AGENTS.md as the project policy.
Zed: use .zed/settings.json for the project-local context_servers.bilig-workpaper MCP server, with root AGENTS.md and .agents/skills/bilig-workpaper/SKILL.md for the WorkPaper proof rule.
OpenHands: read root AGENTS.md, then use .agents/skills/bilig-workpaper/SKILL.md; add the local MCP server with the command from docs/openhands-workpaper-mcp.md.
OpenCode: use opencode.jsonc and .opencode/agents/bilig-workpaper.md.
Aider: use CONVENTIONS.md, loaded by .aider.conf.yml.
JetBrains Junie: use .junie/mcp/mcp.json.
Gemini CLI: use GEMINI.md, gemini-extension.json, and gemini-workpaper-context.md.
Package-level agents inspecting node_modules/@bilig/workpaper should read the published AGENTS.md and SKILL.md.

Read the full file on GitHub · 148 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.

2d ago First seen · 148 lines · 2,469 tokens per session scan A 3b0a8f163834

Subscribe to this mod's changes

bilig AGENTS.md is an instructions file published in the GitHub repository proompteng/bilig (35 stars, last pushed 9d ago), licensed MIT. It adds 2,469 tokens to every session, about $0.0123 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.

Project management Testing formula-engine formula-recalculation mcp mcp-server workbook-api

Table-GitHub-Capability-Router AGENTS.md

Instructions for duoduoler-ops/Table-GitHub-Capability-Router: This is the canonical repository instruction file. Client-specific compatibility files must point here instead of duplicating these rules.

duoduoler-ops/Table-GitHub-Capability-Router · 310 tokens

ESAA-Core AGENTS.md

Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.

elzobrito/ESAA-Core · 2,154 tokens

wiki_ticket_sdd CLAUDE.md

Instructions for SpillwaveSolutions/wiki_ticket_sdd, covering acme platform, work tracking policy and work taxonomy.

SpillwaveSolutions/wiki_ticket_sdd · 1,502 tokens

super-backlog CLAUDE.md

Instructions for adam-s-k-i/super-backlog: This project uses the combined Backlog.md + Superpowers workflow. Read the integration block in AGENTS.md (section between SUPER-BACKLOG markers) and follow it. Tasks are managed exclusively through the backlog CLI.

adam-s-k-i/super-backlog · 58 tokens

idd-skill idd-resume.instructions.md

Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.

kurone-kito/idd-skill · 3,747 tokens

bankan CLAUDE.md

Instructions for stilero/bankan, covering claude.md, what this is, commands, architecture and server modules (server/src/).

stilero/bankan · 1,465 tokens