operate-zed-agent

A guide for configuring and troubleshooting Zed Agent, Zed's coding assistant, along with external agents and terminal threads.

In plain words
What is it for?
It helps choose and configure the right agent path, manage Zed skills and MCP connections, set up profiles and permissions, and inspect ACP logs.
Why use it?
Zed can run agents in different ways, and each path has different settings, permissions, skills, and logs.

Skill for Claude CodeCodex

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 skills/gaelic-ghost/socket/operate-zed-agent
Any agent
npx skills add gaelic-ghost/socket --skill operate-zed-agent
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/socket

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 937 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00042 $0.00937
Opus 5 $0.00021 $0.00468
Sonnet 5 $0.00008 $0.00187
Haiku 4.5 $0.00004 $0.00094

Measured 2d ago against content hash 453b29bf9c6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

operate-zed-agent 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.

plugins/agent-portability-skills/skills/operate-zed-agent/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operate Zed Agent

Choose the Zed agent path before editing settings. Read references/zed-surface-map.md when the request crosses native and external agent configuration.

Choose the Agent Path

  • Use Zed Agent when Zed should own the model, provider, tools, profiles, permissions, instructions, skills, and MCP configuration.
  • Use an External Agent when an ACP agent such as Codex, Claude, OpenCode, or Hermes should own its runtime, model, authentication, native skills, and persistent state while Zed owns the editor UI.
  • Use a Terminal Thread when the original CLI or TUI behavior matters more than ACP-native diffs, approvals, or session rendering.

Do not apply Zed Agent Skills or profiles to an External Agent by assumption. The external agent keeps its own configuration unless its ACP implementation explicitly accepts a forwarded capability.

Configure Zed Agent

  1. Confirm the worktree is trusted before expecting project-local skills.
  2. Use Zed's Skills Manager to create or import a skill when interactive management is appropriate. A GitHub URL import is an installation copy, not a remote runtime dependency.
  3. Keep manually managed skills as direct children of global ~/.agents/skills/ or project .agents/skills/; Zed does not discover nested or arbitrary search roots.
  4. Keep names and descriptions concise because Zed has a catalog budget.
  5. Use /skill or @skill for explicit invocation. Use disable-model-invocation only when the skill must never be selected implicitly.
  6. Treat zed://skill links as sharing/import affordances, not proof of a centrally hosted runtime registry.
  7. Use Zed Instructions for always-on guidance, Agent Profiles for tool selection, Tool Permissions for approval policy, and Zed MCP configuration for external tools.
  8. Expect installed skill changes to reload without restarting, then verify the catalog entry and one harmless invocation.

Configure an External Agent

  1. Check the live canonical ACP Registry instead of trusting a product page or an agent's source manifest.
  2. Prefer the registry only when the requested agent is actually present.
  3. Otherwise add a custom agent_servers entry using the agent's official executable and arguments. Do not substitute an unreviewed third-party launcher merely to make a registry row appear.
  4. Configure provider credentials and native agent state in the external agent unless its integration documents another owner.
  5. Start a new thread and verify the agent identity, working directory, model, skills, MCP tools, and approval behavior.
  6. Use dev: open acp logs to inspect Zed-to-agent protocol traffic.

Read the full file on GitHub · 91 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 91 lines · 42 tokens per session scan A 453b29bf9c6f

Subscribe to this mod's changes

operate-zed-agent is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 42 tokens to every session and 937 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

xcode-disk-cleanup

Audit and safely clean Xcode-related developer storage on macOS. Use whenever a developer mentions low disk space, Xcode storage, DerivedData, simulator devices or runtimes, stale beta platforms in Xcode Settings, DeviceSupport, archives, dSYMs, CocoaPods caches, simulator dyld caches, project .build folders…

AvdLee/Xcode-Disk-Cleanup-Agent-Skill · 147 tokens

storescreens

Set up and run storescreens-cli to automate App Store screenshot capture for iOS apps: render captioned/framed App Store-ready screenshots with device bezels, markdown captions, and panoramic backgrounds; upload screenshots + per-locale metadata (name, subtitle, description, keywords, what's new, promotional text) to…

ciscoriordan/storescreens-skill · 331 tokens

swift-concurrency-pro

Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.

jacklandrin/OnlySwitch · 35 tokens

swiftui-pro

Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. Use when reading, writing, or reviewing SwiftUI projects.

jacklandrin/OnlySwitch · 36 tokens

baocut

BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…

JimLiu/baocut · 160 tokens

boutique-swiftui

Integrate Boutique with SwiftUI views using onChange, onStoreDidLoad, bindings, and preview stores. Use when building SwiftUI views that display or react to Boutique-persisted data.

mergesort/Boutique · 45 tokens