skills AGENTS.md

Instruction notes for using a collection of flespi IoT platform skills. Flespi is a service for connecting devices and processing telematics data such as vehicle or sensor information.

In plain words
What is it for?
Use them when working with flespi channels, devices, streams, calculators, plugins, geofences, REST APIs, MQTT messaging, filters, or webhooks.
Why use it?
They point to the relevant reference material and the platform concepts needed before working with flespi. This reduces mistakes when handling its APIs, message broker, or data-processing features.

Instructions file for CodexOpenCode

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/flespi-software/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/flespi-software/skills

Made for: Codex, OpenCode.

Per session 127 This file is loaded in full into every session.
When invoked 127 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00127 $0.00127
Opus 5 $0.00063 $0.00063
Sonnet 5 $0.00025 $0.00025
Haiku 4.5 $0.00013 $0.00013

Measured 2d ago against content hash 4d641fa9ff86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills 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.

Origin

This is a copy

94% identical to skills copilot-instructions.md — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 8 lines

What it actually says

You have access to flespi IoT platform knowledge. When working with flespi APIs, MQTT, or telematics integrations, refer to the flespi skill reference at skills/flespi/SKILL.md in this repository for:

  • Platform concepts (channels, devices, streams, calculators, plugins, geofences)
  • REST API reference (base URL: https://flespi.io, auth, CRUD, selectors, pagination)
  • MQTT broker reference (mqtt.flespi.io, topics, filtering, shared subscriptions)
  • Expression syntax for filters, calculators, and webhooks
  • Common API patterns and best practices
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 · 8 lines · 127 tokens per session scan A 4d641fa9ff86

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository flespi-software/skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 127 tokens to every session, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to skills copilot-instructions.md, differing in 3 lines, and is treated as a copy.

Related

Other instructions, from other repositories

agentic-tools AGENTS.md

Instructions for meta-quest/agentic-tools, covering agent guide — meta quest agentic tools, what this repo is, how skills work, shared references and skill index.

meta-quest/agentic-tools · 2,466 tokens

mspm0-skill CLAUDE.md

Instructions for mc3545dada/mspm0-skill, a project described as: 面向电赛的 MSPM0 + SysConfig Agent Skill.

mc3545dada/mspm0-skill · 111 tokens

arduino-skills AGENTS.md

Instructions for wedsamuel1230/arduino-skills: The canonical skill content is under skills/. Select the smallest matching SKILL.md, and load references/ or docs/ only when the skill points to it.

wedsamuel1230/arduino-skills · 161 tokens

arduino-skills GEMINI.md

Instructions for wedsamuel1230/arduino-skills: The shared source of truth is skills/. Load only the specialist skill and references needed for the request. Preserve the board intake, ordered constexpr int declarations, C/C++ embedded-first orientation, and explicit hardware evidence gates.

wedsamuel1230/arduino-skills · 94 tokens

arduino-skills CLAUDE.md

Instructions for wedsamuel1230/arduino-skills: Use the canonical skills under skills/. For physical or multi-session work, start with skills/embedded-project-loop/SKILL.md, then use skills/arduino-workflow-router/SKILL.md for combined or underspecified work. Use a focused specialist when the board and proof stage are…

wedsamuel1230/arduino-skills · 87 tokens

zephyr-rtos-ai AGENTS.md

Instructions for ksachdeva/zephyr-rtos-ai, covering ai coding assistant context, repository structure, project overview, development setup and prohibited.

ksachdeva/zephyr-rtos-ai · 763 tokens