zcode-delegate skill
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or to run a queue of coding tasks through ZCode while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Is the zcode-delegate skill safe?
Clean: nothing in its files matched our rules. We read 6 files in the folder on 2026-09-28.
No findings.
Install the zcode-delegate skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/amElnagdy/delegate-skills.git /tmp/delegate-skills mkdir -p ~/.claude/skills cp -r /tmp/delegate-skills/skills/zcode-delegate ~/.claude/skills/zcode-delegate
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
ZCode Delegate
You are the orchestrator. This skill lets you hand a bounded coding task to a separate implementer — the Z.AI ZCode CLI — then review what it produced and land it yourself. You write the brief and own the judgment; ZCode does the typing; you verify and commit.
Nothing here is specific to one orchestrating agent. The loop needs only the ability to run a shell command and read a file. (It is designed for and run on Claude Code; treat other orchestrators as designed-for, not yet proven.)
When NOT to use this
- The task is small enough to just do inline — delegation overhead is not worth it.
- ZCode is not installed, or its CLI has no model provider configured.
- You want to write the code yourself, or you only need a review.
Prerequisites (check once)
npm. The relay resolves it in this order: --zcode-path or ZCODE_CLI first, then PATH, then the installed app bundle. On Linux the app is an AppImage with no fixed install path, so the flag or the environment variable is required there — the relay guesses nothing.
- ZCode is installed. The CLI ships inside the desktop app — it is not on PATH and not on
into the desktop app is not enough — see below.
- A model provider is configured for the CLI, with a key it can actually reach. Being signed
- You are in (or will point --cd at) the target git repository.
The relay records the CLI version and how it was resolved into result.json, so a surprising install is visible after the fact.
Authenticating the headless CLI
Signing into the ZCode desktop app does not authenticate the CLI this relay drives. The CLI keeps its own config at ~/.zcode/cli/config.json, separate from the desktop app's, and nothing bridges the two. zcode login is the intended path, but where it fails with OAuth response is not valid JSON the way in is a Z.AI API key.
Two pieces are needed, and they are separate:
endpoint and its models — the environment cannot supply this:
- The provider block must exist in ~/.zcode/cli/config.json. It defines the provider, its
{
"provider": {
"zai": {
"kind": "anthropic",
"options": { "apiKeyRequired": true, "baseURL": "https://api.z.ai/api/anthropic" },
"models": { "glm-5.1": { "name": "GLM-5.1" } }
}
},
"model": { "main": "zai/glm-5.1" }
}environment as any one of ZAIAPIKEY, ZCODEAPIKEY, or ANTHROPICAPIKEY. Prefer the environment — it keeps the secret off disk.
- The key can live either in provider.zai.options.apiKey in that file, or in the
If a run fails with Model provider is missing an API key: , the provider block resolved but no key was found: set one of those variables and re-run.
Autonomy — read this before dispatching
ZCode's own term is mode. It has four values; only two are usable headlessly.
Two limits stated plainly, because ZCode cannot enforce them:
takes a Git fingerprint before the run and reports a tri-state readOnlyViolation afterwards. Confirm touchedFiles came back empty rather than assuming no edits.
- plan mode refused edits in testing, but the relay does not treat that as a guarantee. It
genuinely enforced. An explicit allowlisted tool surface is therefore impossible here — do not assume one.
- ZCode has no --allowed-tools. Only the --disallowed-tools denylist exists, and it is
The loop
Run these five steps per task. Steps 1, 4, and 5 are your judgment; 2 and 3 are mechanical.
1. Write the brief
ZCode sees only what you send — no repo memory, no chat history. Everything the task needs goes in the brief: the goal, the current state, what to change, what to leave untouched, the project's actual gate commands (discover them from the repo's CLAUDE.md/AGENTS.md/Makefile — do not assume), and a report contract. Tell ZCode it will not commit. One task per brief. The relay delivers the brief as an attached file, so the command line no longer bounds its length — the model's context window still does. Full guidance and a template: references/writing-the-brief.md.
2. Dispatch
node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo
# read-only (review/diagnosis, no edits): add --read-only
# continue a specific session: add --session <sess_...> (from result.json; send only the delta brief)
# continue the latest session for --cd: add --resume-last
# withhold tools (denylist): add --disallowed-tools "Write,Edit,Bash"
# point at the CLI explicitly: add --zcode-path /path/to/zcode.cjs
# hard time limit (watchdog): add --timeout 2h (default: off)
# see all options: node .../relay.mjs --help( is this skill's installed directory — the folder containing this SKILL.md.)
The relay writes its artifacts to a temp dir, so the repo under review stays clean. It never commits — see step 5. Mechanics, flags, and the result.json shape: references/dispatch-and-poll.md.
3. Wait for completion
The relay blocks until ZCode finishes, so back it with whatever your orchestrator offers:
file. The run is done when result.json exists with a status. A pre-run usage error exits 2 and writes no result file, so check the exit code too; a CLI that cannot be found exits 127 but does write a result.json with status zcode_unavailable.
- Claude Code: run the Bash call with runinbackground: true; you are notified on completion.
- Plain shell / other agents: foreground for short tasks, or background it and poll the result
Do not trust progress trackers over reality: read the working tree, not a status line.
4. Review — do not trust the self-report
touchedFiles is your starting point.
- Re-run the project's gates yourself. Never take "gates passed" on faith.
- Read the diff against the brief: did ZCode do what was asked, nothing more and nothing less?
- On a --read-only run, check readOnlyViolation and confirm touchedFiles is empty.
- Run the relevant guard skills on the diff if you have them installed.
Full checklist: references/review-and-land.md.
5. Land it
The orchestrator commits. Only after the gates pass and the diff holds:
and review again.
- Commit the verified work yourself, with a clear message.
- If it needs changes, send a delta brief with --session from the prior result.json,
Read-only second opinions
The relay doubles as a way to get an adversarial second opinion with no write risk: dispatch --read-only with a brief listing the agreed points, then each contested point with both positions, and ask ZCode to defend or concede each. Because plan mode's guarantee is measured rather than enforced here, verify touchedFiles came back empty instead of assuming no edits.
Authorization model
Delegation is something the human opts into. Once they have, committing verified, gate-passing work is the agreed contract. Two limits: surface, don't absorb (report ZCode's design decisions and defensible-but-unasked turns rather than silently keeping them) and stop for scope changes (if correct completion needs going beyond the brief, ask). The full treatment is in references/review-and-land.md.
References
execute blind: structure, the report contract, embedding the real gate commands.
- references/writing-the-brief.md — how to write a brief ZCode can
result.json contract, how the CLI is resolved, backgrounding, and recovery.
- references/dispatch-and-poll.md — relay.mjs flags, the
boundary, and the exact-session rework cycle.
More skills from amElnagdy/delegate-skills
- Aagy-delegateDelegate a coding task to the Google Antigravity CLI (`agy`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use Antigravity to implement/fix/refactor" - or wants to run a queue of coding tasks through agy while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Aaider-delegateDelegate a coding task to Aider (`aider`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Aider - phrasings like "have Aider do X", "delegate this to aider", "run it through Aider", or "use Aider to implement/fix/refactor" - or wants to run a queue of coding tasks through Aider while staying the reviewer. This includes asking Aider to drive a local or self-hosted OpenAI-compatible endpoint ("have Aider use my local model", "run Aider against llama.cpp / Ollama / vLLM / LM Studio"), which Aider reaches via `--api-base`. DO NOT USE for local-model or coding requests that do not name Aider, for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Aclaude-delegateDelegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the `claude` CLI — for example, "have another Claude implement this", "delegate this to Claude Code", or "run this queue through a separate Claude session." Do not trigger merely because the current orchestrator is Claude, and do not use when the user asks the current Claude to implement directly without delegation.
- Acline-delegateDelegate a coding task to the Cline coding agent CLI (`cline`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Cline - phrasings like "have Cline implement X", "delegate this to cline", "run it through Cline", or "use cline to implement/fix/refactor" - or wants to run a queue of coding tasks through Cline while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Acodex-delegateDelegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" — or to run a queue of coding tasks through Codex while staying the reviewer. Prefer it over a one-shot Codex forwarder (such as the codex-rescue agent) when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Acommandcode-delegateDelegate a coding task to the Command Code CLI (`cmd`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Command Code — phrasings like "have Command Code do X", "delegate this to commandcode", "run it through cmd", or "use Command Code to implement/fix/refactor" — or to run a queue of coding tasks through Command Code while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Acopilot-delegateDelegate a coding task to the GitHub Copilot CLI (`copilot`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Copilot - phrasings like "have Copilot implement X", "delegate this to copilot", "run it through Copilot CLI", or "use copilot to implement/fix/refactor" - or wants to run a queue of coding tasks through Copilot while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Acursor-delegateDelegate a coding task to the Cursor Agent CLI (`cursor-agent`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use Cursor to implement/fix/refactor" — or wants to run a queue of coding tasks through Cursor while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Adelegate-setupConfigure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or variant) dials. Discovers installed CLIs, proposes a lane map for user approval, and writes global or project config only after explicit yes. Use when the user asks to set up, configure, or reconfigure delegation lanes, a fleet of lanes, or which implementer handles feature/tests/ui work — not for dispatching a coding task to an implementer.
- Agrok-delegateDelegate a coding task to the Grok Build CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Grok — phrasings like "have Grok do X", "delegate this to Grok", "run it through Grok", "use Grok Build to implement/fix/refactor", or "have grok CLI do this" — or to run a queue of coding tasks through Grok while staying the reviewer. Prefer it when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Akimi-delegateDelegate a coding task to the Kimi Code CLI (`kimi`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Kimi - phrasings like "have Kimi implement X", "delegate this to Kimi", "run it through Kimi Code", or "use Kimi to implement/fix/refactor" - or wants to run a queue of coding tasks through Kimi while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
- Aomp-delegateDelegate a coding task to Oh My Pi (`omp`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Oh My Pi / omp - phrasings like "have omp implement X", "delegate this to oh my pi", "run it through omp", "use oh-my-pi to implement/fix/refactor" - or wants to run a queue of coding tasks through omp while staying the reviewer. DO NOT USE for tasks small enough to do inline, when the user wants the code written directly without delegating, or when they mean the original Pi CLI (`pi`) — that is pi-delegate.