AgentDock AGENTS.md

A set of repository instructions for AgentDock, a desktop hub for managing AI coding clients, providers, skills, and MCP tools. It defines how changes, releases, versions, and deployments must be handled.

In plain words
What is it for?
Use it when modifying or releasing AgentDock so the required files are updated together, checks are run, a universal macOS DMG is created, and online publishing follows the stated approval rules.
Why use it?
It gives coding agents project-specific rules that general instructions do not contain. This helps keep application versions, release files, builds, and deployment steps consistent.

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/cailiang/agentdock/agents-md
Clone the repo
git clone --depth 1 https://github.com/Cailiang/AgentDock

Made for: Codex, OpenCode.

Per session 287 This file is loaded in full into every session.
When invoked 287 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00287 $0.00287
Opus 5 $0.00143 $0.00143
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00029 $0.00029

Measured yesterday against content hash 0b7d5e0ef890, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentDock 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 yesterday.

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.

AGENTS.md · 12 lines

What it actually says

Repository Instructions

  • Do not commit, tag, or push to GitHub unless the user explicitly requests it.
  • Every repository modification must increment the application patch version before verification and deployment. Keep the version synchronized in package.json, package-lock.json, src-tauri/tauri.conf.json, src-tauri/Cargo.toml, and src-tauri/Cargo.lock.
  • After modifying the repository, run the relevant checks and deploy the verified build with npm run release:macmini.
  • Every Mac mini release must also create a locally installable universal macOS DMG in release-artifacts/ and verify that it contains the Intel x86_64 architecture.
  • The default deployment target is [email protected]:/Applications/AgentDock.app.
  • Only after the user explicitly approves an online release, commit the verified changes and run npm run release:github.
  • Every GitHub release must use release-notes/v<version>.md instead of auto-generated notes. Write an accurate Chinese section first and an English section second; both sections must summarize the release and list new features and bug fixes based on the changes since the previous release.
  • Do not publish a GitHub release when its bilingual release notes are missing, incomplete, or still contain template placeholders.
  • Keep deployment credentials out of the repository. Use the configured SSH key.
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. yesterday First seen · 12 lines · 287 tokens per session scan A 0b7d5e0ef890

Subscribe to this mod's changes

AgentDock AGENTS.md is an instructions file published in the GitHub repository Cailiang/AgentDock (2 stars, last pushed 29d ago), licensed MIT. It adds 287 tokens to every session, about $0.0014 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 2026-08-31.