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.
npx agentmods add instructions/adambien/bce.design/agents-mdgit clone --depth 1 https://github.com/AdamBien/bce.designWrote 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/adambien/bce.design/agents-md)<a href="https://agentmods.dev/instructions/adambien/bce.design/agents-md"><img src="https://agentmods.dev/badge/instructions/adambien/bce.design/agents-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 | $0.00632 | $0.00632 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
bce.design 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Codex, Gemini CLI, ...) when working with code in this repository.
Project Overview
This is a web component-based single-page application following the Boundary Control Entity (BCE) architectural pattern. The application uses minimal tooling and essential dependencies for building non-trivial web applications.
Template Usage
This repository is a brownfield template. The bookmarks BC (app/src/bookmarks/) is a sample that demonstrates BCE layering. When the user starts building their own features, remove or replace it rather than extending it. Coupling points to clean up: imports and route registration in app/src/app.js, reducer registration in app/src/store.js, the page title in app/src/index.html, and the Playwright specs in tests/tests/bce.design.spec.js and codecoverage/tests/bce.design.spec.js.
Development Commands
Running the Application
Serve app/src with any static web server that falls back to index.html for unknown paths (client-side routing), e.g.:
# Using serve
cd app
npx serve -s src
# Using browsersync
cd app
browser-sync src -f src -b "google chrome" --no-notify
# Using zws (zero-dependency Java web server, ships with the web-static skill on airails.dev)
cd app/src
zws.sh # serves on http://localhost:3000; no index.html fallback — enter the app at /, deep links to /add 404
Note: npx vite does not currently work — Vite resolves the bare lit-html / @reduxjs/toolkit imports itself instead of honoring the import map in index.html.
Testing
# Run Playwright e2e tests (expect the app on http://localhost:3000)
cd tests
npm test # or npx playwright test
# Run tests with code coverage
cd codecoverage
npm test # or npx playwright test
Dependency Management
There is no build system. Runtime dependencies (lit-html, Redux Toolkit) are vendored as self-contained ES modules in app/src/libs/ and mapped via the import map in index.html. To update lit-html, run ./update-lit-html.sh <version> (e.g. 3.3.3) from the repository root — it fetches the release directly from the npm registry.
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.
- 3d ago First seen · 61 lines · 632 tokens per session scan A e71956a49b27
bce.design AGENTS.md is an instructions file published in the GitHub repository AdamBien/bce.design (104 stars, last pushed 1mo ago), licensed MIT. It adds 632 tokens to every session, about $0.0032 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.
Other instructions, from other repositories
titanium-elements CLAUDE.md
Instructions for LeavittSoftware/titanium-elements, covering claude.md, project overview, tech stack, monorepo structure and key scripts.
angular AGENTS.md
Instructions for angular/angular, covering environment, key documentation, testing and pull requests.
PanWatch CLAUDE.md
Instructions for TNT-Likely/PanWatch, covering claude.md, what is panwatch, build & run commands, backend and frontend.
PanWatch AGENTS.md
Instructions for TNT-Likely/PanWatch, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
collie CLAUDE.md
Instructions for AltanS/collie, covering claude.md — working agreement for this repo, decision records — read before reopening a settled question, versioning — mandatory, build / run (operational facts that are easy to forget) and frontend data layer (react router, not tanstack).
cashu.me AGENTS.md
Instructions for cashubtc/cashu.me, covering cashu.me developer guide for agents, 1. tech stack, core frameworks, mobile & desktop and cashu & cryptography.