Borrowing it
Nothing to install: this file belongs to stilero/bankan. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stilero/bankan/main/CLAUDE.mdgit clone --depth 1 https://github.com/stilero/bankanWrote 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/instructions/stilero/bankan/claude-md)<a href="https://agentmods.dev/instructions/stilero/bankan/claude-md"><img src="https://agentmods.dev/badge/instructions/stilero/bankan/claude-md.svg" alt="Measured on agentmods" 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 | $0.01465 | $0.01465 |
| Opus 5 | $0.00732 | $0.00732 |
| Sonnet 5 | $0.00293 | $0.00293 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
bankan CLAUDE.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 8d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
Ban Kan is a local AI agent orchestration dashboard — a Kanban board where tasks flow through Backlog → Planning → Implementation → Review → Done, with each stage driven by AI coding agents (Claude CLI or Codex CLI). Published as @stilero/bankan on npm.
Commands
npm run install:all # Install root + server + client dependencies
npm run setup # Interactive setup wizard (writes .env.local, installs deps)
npm run dev # Run server + Vite client concurrently (alias: npm start)
npm run dev --prefix client # Client only (Vite dev server on :5173)
npm run dev --prefix server # Server only (node --watch on :3001)
npm run build # Build client bundle (vite build)
npm run lint # Run ESLint across the repo
npm run lint:fix # Apply safe ESLint autofixes
npm test # Run server + client automated tests
npm run test:server # Run server Vitest suite
npm run test:client # Run client Vitest suite
npm run coverage # Run both coverage suites and enforce the combined 80% gate
Dev mode: client runs at http://localhost:5173 with API proxy to :3001.
Architecture
Monorepo with two packages — no workspace manager, just npm --prefix:
server/— Express + WebSocket backend (ES modules, no TypeScript)client/— React 18 + Vite SPA (JSX, no TypeScript, inline styles)bin/bankan.js— CLI entry point fornpx @stilero/bankanscripts/setup.js— Interactive setup wizard
Server modules (server/src/)
index.js— Express app, REST API, WebSocket handler, static file serving, bridge terminal logic. All HTTP/WS endpoints live here.orchestrator.js— Core pipeline engine. Poll loop (4s) assigns tasks to agents, signal checker (2.5s) detects completion/timeout/blockers. Builds prompts for each stage, manages git workspaces (clone → branch → push), handles PR creation viaghCLI.agents.js—Agentclass wrapsnode-ptyprocesses.AgentManagersingleton manages agent pool with role-based scaling (planners/implementors/reviewers). Agents parse token counts from CLI output.store.js—TaskStorepersists tasks to.data/tasks.json. Handles restart recovery (resets orphaned in-flight tasks).config.js— Loads settings from.data/config.jsonwith fallback to.env.localand process env. Contains default prompts for planning/implementation/review stages.paths.js— Runtime path resolution. Two modes: development (.data/in repo root) vs packaged (~/Library/Application Support/bankanon macOS).events.js— SharedEventEmitterbus connecting orchestrator, agents, store, and WebSocket broadcasts.
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.
- 8d ago First seen · 114 lines · 1,465 tokens per session scan A 5cc5cb11525c
bankan CLAUDE.md is an instructions file published in the GitHub repository stilero/bankan (4 stars, last pushed 5mo ago), licensed MIT. It adds 1,465 tokens to every session, about $0.0073 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.