sensecraft-solutions: Instructions file for Codex

AGENTS.md

sensecraft-solutions AGENTS.md is an instructions file for Codex, OpenCode from suharvest/sensecraft-solutions. It costs 8,739 tokens per session, scanned C, original, Apache-2.0.

A working guide for agents helping people use the SenseCraft Solutions repository, which contains IoT solution content and tools for authoring and validation.

In plain words
What is it for?
Use it to decide how to help non-technical editors, app users, and DevOps users, including when to use the import API, deployment API, or solutionctl command-line tool.
Why use it?
It clarifies the different user workflows, from editing content and previewing it to one-click deployment and automated operations.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is suharvest/sensecraft-solutions's own configuration. It tells Codex and OpenCode how to work on sensecraft-solutions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sensecraft-solutions configures →

Reuse

Borrowing it

Nothing to install: this file belongs to suharvest/sensecraft-solutions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/suharvest/sensecraft-solutions/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/suharvest/sensecraft-solutions

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for sensecraft-solutions AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/suharvest/sensecraft-solutions/agents-md/github.svg)](https://agentmods.dev/instructions/suharvest/sensecraft-solutions/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/suharvest/sensecraft-solutions/agents-md"><img src="https://agentmods.dev/badge/instructions/suharvest/sensecraft-solutions/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sensecraft-solutions AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/suharvest/sensecraft-solutions/agents-md"><img src="https://agentmods.dev/badge/instructions/suharvest/sensecraft-solutions/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,739 This file is loaded in full into every session.
When invoked 8,739 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.08739 $0.08739
Opus 5.5 $0.03496 $0.03496
Sonnet 5.5 $0.01748 $0.01748
Haiku 4.5 $0.00874 $0.00874

Measured 5d ago against content hash 18be18780453, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

sensecraft-solutions AGENTS.md scanned grade C with 2 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 5d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- **`sensecraft-engine`** — a single command-line binary (`curl -fsSL https://sensecraft-statics.seeed.cc/solution-app/engine/install.sh | sh -s -- --with-content`). It downloads the solutions from the CDN (`sensecraft-e

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **`sensecraft-engine`** — a single command-line binary (`curl -fsSL https://sensecraft-statics.seeed.cc/solution-app/engine/install.sh | sh -s -- --with-content`). It downloads the solutions from the CDN (`sensecraft-e
AGENTS.md · 575 lines

How it starts

The opening of the file, as written. The whole thing — 575 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Working Guide for AI Agents Assisting SenseCraft Solution Users

This document is for AI agents (Claude Code and similar assistants). It defines the standard workflows an agent should follow when helping different kinds of SenseCraft Solution users.

This open-source repository contains the solution content (YAML / Markdown / assets) and the authoring & validation tooling (spec/, packages/, skills/). The deployment engine is distributed separately, in two forms:

  • sensecraft-engine — a single command-line binary (curl -fsSL https://sensecraft-statics.seeed.cc/solution-app/engine/install.sh | sh -s -- --with-content). It downloads the solutions from the CDN (sensecraft-engine content pull), carries the device catalog inside the binary, and deploys without starting any Python process. This is the engine agents use to deploy (the solution-cli skill).
  • The SenseCraft Solution desktop app (Python backend provisioning-station). Content preview (Part A), the app HTTP API (Part C) and the legacy solutionctl deploy / manage / stage commands (Part D, appendix) need it.

Four user roles, four workflows

Part User role Typical need Key artifact
A Non-technical user (operations, AE, marketing) Edit copy, add images, tweak intro/guide, then preview in the app Solution import API (preview flow)
C End user, deploying with an agent "One-click deploy a solution" solution-cli skill + sensecraft-engine CLI; the desktop app's HTTP API boost flow is the app-only alternative
D DevOps / CI / scripted Headless batch deploy, CI automation, single-device debugging sensecraft-engine CLI (deploy --detach, status, logs); legacy: solutionctl deploy (starts the Python backend)
E DevOps / agent operating deployed devices List deployed apps, start/stop/update, firmware OTA, factory restore, content updates, Docker ops sensecraft-engine docker / content / api; the remaining endpoints need serve --headless (Python backend) or the desktop app
F Solution author / AE turning a project into a solution Convert an existing project into a one-click solution, then submit it author-solution / author-cli skills + solutionctl validate / steps (offline) + PR

Read the full file on GitHub · 575 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. 5d ago Changed · +1 lines · +58 tokens per session 18be18780453
  2. 10d ago Changed · +3 lines · +95 tokens per session bd8a047d1e05
  3. 11d ago Changed · +151 tokens per session 8528a3a250b0
  4. 14d ago Changed · +24 lines · +742 tokens per session scan A → C 772eb83dbbdf
  5. 16d ago Changed · +11 lines · +229 tokens per session f2982c1a9ea3
  6. 1mo ago Changed · +27 lines · +301 tokens per session 97d6a486ade5
  7. 1mo ago First seen · 509 lines · 7,163 tokens per session scan A bb9e352515ef

Subscribe to this mod's changes

sensecraft-solutions AGENTS.md is an instructions file published in the GitHub repository suharvest/sensecraft-solutions (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 8,739 tokens to every session, about $0.0350 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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 · 9,715 tokens

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.

vercel/next.js · 7,581 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens