zed

Setup instructions for connecting the Watch Skill to Zed, a code editor. The connection uses a context server, which lets an editor provide an external tool or information source to an AI assistant.

In plain words
What is it for?
Use it to install the Watch Skill, run its diagnostic check, add it to Zed's settings, and understand how Zed starts the service.
Why use it?
It removes the guesswork around installing and configuring this service in Zed. Zed uses different settings names and structure from other editors, so copied configurations may not work.

Agent

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 agents/oxbshw/watch-skill/zed
Clone the repo
git clone --depth 1 https://github.com/oxbshw/watch-skill
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 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 $0.00000 $0.00582
Opus 5 $0.00000 $0.00291
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 2d ago against content hash dc388b57c2b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

zed 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.

docs/agents/zed.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watch Skill in Zed

Status: doc-verified ☑ — config matches Zed's official context-server docs; not executed here.

Zed calls MCP servers context servers, and the settings key is context_servers rather than mcpServers. The shape differs from every other client in this matrix, so copying a Cursor or Cline block here will not work.

Install

uvx --from "watch-skill[standard]" watch-skill doctor

uvx fetches the package on first use and needs no checkout. Prefer a permanent install? pipx install "watch-skill[standard]", then use "path": "watch-skill" with "args": ["serve"] below.

git clone https://github.com/oxbshw/watch-skill && cd watch-skill
uv sync --extra all
uv run watch-skill doctor

Configure

Open settings with cmd+, (macOS) or edit the file directly: ~/.config/zed/settings.json, or %APPDATA%\Zed\settings.json on Windows.

{
  "context_servers": {
    "watch-skill": {
      "source": "custom",
      "command": {
        "path": "uvx",
        "args": ["--from", "watch-skill[standard]", "watch-skill", "serve"],
        "env": {}
      }
    }
  }
}

Zed restarts the context-server process when the file is saved, so there is no need to restart the editor.

Smoke test (3 steps)

  1. Open the agent panel and ask: "Watch https://www.youtube.com/watch?v=aqz-KE-bpKQ and tell me what happens at 0:10."
  2. Approve the watch_video call.
  3. Follow up: "what color is the bird?" — should call ask_video and answer from the index without re-processing.

Notes

  • Zed's native context_servers speaks stdio only. watch-skill serve --http will not attach here; use the default stdio form above.
  • Provider keys belong in the env block if you do not want them in a shell profile — Zed passes it to the spawned process.
  • Nothing about vision is required to start: transcription, OCR, indexing, and search all run locally with no key.

Read the full file on GitHub · 74 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. 2d ago First seen · 74 lines · 0 tokens per session scan A dc388b57c2b8

Subscribe to this mod's changes

zed is an agent published in the GitHub repository oxbshw/watch-skill (320 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 582 tokens. 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.