reolink-cli: Instructions file for Claude Code

AGENTS.md

reolink-cli AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from reolink/reolink-cli. It costs 4,192 tokens per session, scanned D, original, Apache-2.0.

Installation and setup instructions for an AI agent that operates Reolink cameras through the reolink-cli command-line tool.

In plain words
What is it for?
Use them to verify the Reolink command-line tools, start the camera gateway, add a camera for the first time, check installed versions, and troubleshoot setup problems.
Why use it?
They help catch missing programs, unreachable services, and unloaded instructions before camera tasks begin. They also explain what to do when setup fails.

Instructions file for Claude CodeCodexOpenCode

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

This is reolink/reolink-cli's own configuration. It tells Claude Code, Codex and OpenCode how to work on reolink-cli 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 reolink-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to reolink/reolink-cli. 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/reolink/reolink-cli/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/reolink/reolink-cli

Made for: Claude Code, 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 reolink-cli AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/reolink/reolink-cli/agents-md/github.svg)](https://agentmods.dev/instructions/reolink/reolink-cli/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/reolink/reolink-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/reolink/reolink-cli/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 reolink-cli AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/reolink/reolink-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/reolink/reolink-cli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,192 This file is loaded in full into every session.
When invoked 4,192 The same file — it is already loaded in full.
Security scan D 3 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 $0.04192 $0.04192
Opus 5.5 $0.01677 $0.01677
Sonnet 5.5 $0.00838 $0.00838
Haiku 4.5 $0.00419 $0.00419

Measured 18d ago against content hash 9524f655b2ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

reolink-cli AGENTS.md scanned grade D with 3 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 18d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| Linux (Debian/Ubuntu) | `sudo apt-get install -y ffmpeg` |

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.

curl -fsSL https://raw.githubusercontent.com/reolink/reolink-cli/main/install.sh | sh

Makes network callslowCapability

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

curl -fsSL https://raw.githubusercontent.com/reolink/reolink-cli/main/install.sh | sh
AGENTS.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read this when an AI agent first encounters the plugin. Your job is to confirm the install, then operate cameras via the skill.

If the binaries are not on disk yet, the one-line installer fetches them and verifies the download against the checksum committed to this repository:

curl -fsSL https://raw.githubusercontent.com/reolink/reolink-cli/main/install.sh | sh

What you (the AI) should do, in order:

  1. Part 1 — Verify the install (binaries on PATH, gateway reachable).
  2. Part 2 — Confirm the skill is loaded for your agent surface.
  3. Part 3–4 — Start the gateway and (first time only) add a camera.
  4. Part 5 — Echo installed versions back to the user.

If any step fails, do not silently continue — see Part 6 — Troubleshooting and surface the remedy.


Part 1 — Verify CLI install

Both binaries should be at ~/.local/bin/ (or %USERPROFILE%\.local\bin\ on Windows).

reolink-cli --version
command -v reolink-gateway

If command not found, the install prefix isn't on PATH:

# Unix
export PATH="$HOME/.local/bin:$PATH"
# Windows PowerShell
$env:PATH += ";$HOME\.local\bin"

To upgrade, run reolink-cli self-update (macOS and Linux). It checks the latest release, replaces both binaries in place, and is a no-op when already current. On Windows it exits with the download link instead: the archive is a .zip and a running .exe cannot be replaced in place, so upgrade there by extracting the new archive and running install.ps1.

Re-running the one-line installer is an equivalent upgrade path on any platform, and is idempotent — it overwrites both binaries in place.


Part 2 — Confirm the skill is loaded

The plugin tree (SKILL.md, slash commands, skill references) is already on disk after the install. How your agent surface sees it depends on the agent:

Agent Skill path
Claude Code ~/.claude/plugins/cache/reolink-cli/reolink-cli/<version>/ (auto-loaded by /plugin install)
Codex Symlinked into ~/.agents/skills/reolink-cli by setup-codex on first install
Gemini CLI GEMINI.md next to this file is treated as agent context
Cursor / Windsurf .cursor-plugin/ next to this file is auto-detected on workspace open
Other Read skills/reolink-cli/SKILL.md next to this file as a system rule

Read the full file on GitHub · 297 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. 18d ago Changed · +22 lines · +471 tokens per session 9524f655b2ff
  2. 1mo ago First seen · 275 lines · 3,721 tokens per session scan D 357d54915181

Subscribe to this mod's changes

reolink-cli AGENTS.md is an instructions file published in the GitHub repository reolink/reolink-cli (117 stars, last pushed 15d ago), licensed Apache-2.0. It adds 4,192 tokens to every session, about $0.0168 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories