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/reolink/reolink-cli/copilot-instructionsgit clone --depth 1 https://github.com/reolink/reolink-cliWrote 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/reolink/reolink-cli/copilot-instructions)<a href="https://agentmods.dev/instructions/reolink/reolink-cli/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/reolink/reolink-cli/copilot-instructions.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 | $0.00354 | $0.00354 |
| Opus 5 | $0.00177 | $0.00177 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
reolink-cli copilot-instructions.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 4d 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.
What it actually says
reolink-cli — GitHub Copilot instructions
This project can operate Reolink IP cameras locally via the reolink-cli binary.
When a request involves an IP / network / surveillance / doorbell camera on the
LAN — discovery, login, snapshot, preview, PTZ, IR/spotlight/LEDs, image tuning,
OSD, motion + AI detection, recording + SD-card status, VOD search/download,
alarm events, users, reboot, firmware upgrade, or RTSP/RTMP/FLV stream URLs —
drive it through reolink-cli (JSON stdout by default), not by guessing.
The authoritative operating guide is skills/reolink-cli/SKILL.md
and its references/. Follow it: never state camera reachability, config, or
capabilities unless a reolink-cli command actually returned them; keep
passwords off argv (use REOLINK_PASSWORD / --password-stdin); most control
commands need the gateway running (reolink-cli gateway start --addr 127.0.0.1:9000 &).
If reolink-cli is not installed, see skills/reolink-cli/references/setup.md
→ Install the reolink-cli binary.
Using this with Copilot in your own project
Install the skill into GitHub Copilot (and other agents) with:
npx skills@latest add reolink/reolink-cli
Select github-copilot; the skill is written to your workspace's
.github/copilot-instructions.md.
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.
- 4d ago First seen · 29 lines · 354 tokens per session scan A 0c6a5fad65fd
reolink-cli copilot-instructions.md is an instructions file published in the GitHub repository reolink/reolink-cli (93 stars, last pushed 6d ago), licensed Apache-2.0. It adds 354 tokens to every session, about $0.0018 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
HomeAssistant-Tapo-Control AGENTS.md
Instructions for JurajNyiri/HomeAssistant-Tapo-Control, covering agent instructions, required user agreement, repository rules and commits and prs.
HomeAssistant-Tapo-Control CLAUDE.md
Instructions for JurajNyiri/HomeAssistant-Tapo-Control: Follow AGENTS.md and CONTRIBUTING.md before working in this repository.
ha-airspace CLAUDE.md
Instructions for ifnull/ha-airspace, covering claude.md, project at a glance, tech stack, code conventions and style.
robsonfelix-hass-addons CLAUDE.md
Instructions for robsonfelix/robsonfelix-hass-addons, covering claude code instructions, before every commit, added/changed/fixed, project structure and version bumping.
nickol-knx-mcp CLAUDE.md
Instructions for NickoScope/nickol-knx-mcp, covering ets / knx assistant — project rules, hard safety rules, two-layer architecture, group address structure (3-level main/middle/sub) and command / status pairs (the most important rule).
advanced-homeassistant-mcp copilot-instructions.md
Instructions for jango-blockchained/advanced-homeassistant-mcp, covering ai agent instructions for homeassistant-mcp, 1. architecture & core concepts, key components, 2. developer workflow & commands and building the project.