Skip to main content
skill CX Codex

pi-delegate — Claude Code skill: what it does, install

This skill sends coding work to the Pi agent in the background, then keeps diff review and landing with the orchestrator. Use it when implementation should be delegated.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add amElnagdy/delegate-skills --skill pi-delegate -a claude-code
Open on GitHub

What pi-delegate does

pi-delegate defines a workflow around the Pi coding agent CLI: the orchestrator writes a bounded brief, starts Pi in a separate session, waits for completion, and reviews the result. The brief covers the goal, change boundaries, project gates, and the expected report. Pi receives that text plus what it can inspect in the workspace.

The workflow uses scripts/relay.mjs. The relay pipes the brief to pi --mode json, records the event stream, and writes result.json; edits stay in the working tree, while the orchestrator commits after review. You can select a model, target directory, read-only mode, or resume a session with --resume-last or --session <id>.

You need an installed and authenticated pi, a successful pi --version, and a target git repository. Pi has no sandbox or permission modes, so a write-capable run can edit files and execute shell commands without prompts; inspect touchedFiles, the diff, and the project gates yourself.

What it helps with

  • delegate an implementation task to Pi
  • write a bounded brief for the implementer
  • wait for a background Pi run to finish
  • review touchedFiles and the resulting diff
  • continue work through an existing Pi session

Example prompts for the agent

  • “Delegate this implementation task to Pi, wait for it to finish, and review the diff before committing.”
  • “Run this queue of coding tasks through Pi, using one brief per task, and leave the commit to me.”
  • “Use Pi to refactor this code, then run the project gates and show me touchedFiles.”

How to install pi-delegate

1Skills CLI (Vercel)

npx skills add amElnagdy/delegate-skills --skill pi-delegate -a claude-code

2Manually: put the files in place

~/.claude/skills/pi-delegate/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/pi-delegate/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about pi-delegate

How do I install pi-delegate in Claude Code?

Run npx skills add amElnagdy/delegate-skills --skill pi-delegate -a claude-code, then run the same command again: npx skills add amElnagdy/delegate-skills --skill pi-delegate -a claude-code. The skill file will be available at ~/.claude/skills/pi-delegate/SKILL.md.

What does pi-delegate do?

It delegates a bounded coding task to Pi, waits for completion, and keeps diff review, project gates, and the commit with the orchestrator.

What is required before using pi-delegate?

Install and authenticate pi, confirm that pi --version succeeds, and work in the target git repository or pass its path with --cd. Pi has no sandbox, so its file changes and shell commands need manual review.

Source text

SKILL.md · MIT
---
name: pi-delegate
description: >-
  Delegate a coding task to the Pi coding agent CLI (`pi`) as a background implementer, then review
  its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Pi -
  phrasings like "have Pi implement X", "delegate this to pi", "run it through Pi", or "use pi to
  implement/fix/refactor" - or wants to run a queue of coding tasks through Pi 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.
license: MIT
metadata:
  version: 0.5.0
---

# Pi Delegate

You are the **orchestrator**. Delegate a bounded coding task to a separate **implementer** - the Pi
coding agent CLI - then review what it produced and land it yourself. You write the brief and own
the judgment; the implementer makes changes in its own session; you verify and commit.

The loop needs only a shell command and file access, so any comparable orchestrator can drive it.

## When NOT to use this

- The task is small enough to do inline; delegation overhead is not worth it.
- The `pi` CLI is not installed or authenticated.
- You need a sandboxed implementer. Pi has no sandbox and no permission modes; `--read-only`
  restricts the tool surface, but a write-capable run executes without prompts.

## Prerequisites (check once)

1. Install pi with `npm install -g @earendil-works/pi-coding-agent`.
2. Authenticate: `/login` inside pi for a subscription provider, or an API-key environment
   variable / `pi`'s auth file for an API-key provider.
3. Confirm `pi --version` succeeds.
4. Work in, or point `--cd` at, the target git repository.

## Choose the model (optional)

Omit `--model` to use pi's configured default. To pick another, choose from `pi --list-models`
and pass an explicit id or pattern like `<provider>/<model-id>` or `sonnet:high`. The relay
accepts letters, digits, and `. _ : / -` only (the value reaches a shell on Windows), so glob
patterns with `*` are not forwarded.

## The loop

Run these five steps per task. Steps 1, 4, and 5 require judgment; 2 and 3 are mechanical.

### 1. Write the brief

Pi sees only the text you send plus what it can inspect in the workspace - no chat history or
shared context. Include the goal, current state, what to change, what to leave untouched, the
project's **actual** gates, and a report contract. Tell pi not to commit. Keep one task per brief.
Pi auto-loads `AGENTS.md`/`CLAUDE.md` context files from the workspace and its parents, so repo
instructions reach it without inlining. See
[references/writing-the-brief.md](references/writing-the-brief.md).

### 2. Dispatch

For **Codex orchestration of background work**, install and configure the separate
**codex-background** support utility first. If its MCP tools or registry are missing, stop and
report the setup requirement; do not silently fall back to model-driven polling. Then invoke its
registered `delegate_run` MCP tool once in place of the shell example below.
Follow that skill for structured common arguments, unchanged provider flags and reattachment by
runId. Keep the request pending until completion, then continue this skill's review and landing
steps. Other orchestrators keep the shell workflow below.

Use the bundled relay. It pipes the brief to `pi --mode json` on stdin, captures the JSON event
stream, and writes `result.json`. (`<skill-dir>` is the installed folder containing this
`SKILL.md`.)

```bash
node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo
# choose a model:                          add --model <id from pi --list-models>
# choose a provider:                       add --provider <name>
# read-only run (review/diagnosis):        add --read-only
# trust project .pi resources:             add --approve
# resume the most recent session:          add --resume-last  (delta brief only)
# resume a specific session:               add --session <id> (delta brief only)
# hard time limit (watchdog):              add --timeout 2h  (the 30m default suits short runs; implementation briefs routinely need 1-2h)
# see all options:                         node .../relay.mjs --help
```

The child process's cwd pins the workspace. The relay writes artifacts under the system temp dir
by default and never commits. See [references/dispatch-and-poll.md](references/dispatch-and-poll.md).

### 3. Wait for completion

Codex using codex-background keeps the original MCP request pending: no model-driven sleep,
status or log polling. Use `delegate_wait` only to reattach after an interrupted request.

The relay blocks until pi finishes. Run it with the orchestrator's background-command facility,
or background it in the shell and poll for `result.json`. A pre-run usage error exits 2 and writes
no result; a missing `pi` exits 127 and writes `status: "pi_unavailable"`.

Trust process state and the working tree over a progress display. Completion means the process
exited and `result.json` exists. Pi's full report is the `finalMessage` field in `result.json`
(also printed in full on stdout between the report markers).

### 4. Review - do not trust the self-report

Treat pi's final message and gate claims as claims:

- Re-run the project's gates yourself.
- Read the diff against the brief, starting with `touchedFiles`.
- Run relevant guard skills if installed.
- Round-trip migrations and grep for dangling references after removals or renames.

See [references/review-and-land.md](references/review-and-land.md).

### 5. Land it

The implementer edits the working tree; **the orchestrator commits.** Commit only after the gates
pass and the diff holds. If rework is needed, send a delta brief with `--resume-last` or
`--session <id>`, then review again.

## Autonomy and permissions

Pi has **no sandbox and no permission modes**. A default headless run reads, writes, edits, and
executes shell commands with no prompts - the controls are:

1. `--read-only` restricts pi's callable tools to `--tools read,grep,find,ls` across built-in,
   extension, and custom tools. Installed extension code still runs with the user's host permissions.
2. The relay passes `--no-approve` by default, so project `.pi` settings, extensions, and skills
   stay untrusted. `--approve` is the explicit opt-in for a repository the user trusts.
3. `touchedFiles` and the diff are the record of what changed. Inspect them after every run.

## Authorization model

Delegation is something the human opts into. Once they have ("run this queue", "proceed"),
committing verified, gate-passing work is the agreed contract. Two limits remain: **surface, don't
absorb** (report pi's design decisions, defensible-but-unasked turns, and non-blocking nitpicks)
and **stop for scope changes** (if correct completion needs going beyond the brief, ask instead of
expanding the mandate). See [references/review-and-land.md](references/review-and-land.md).

## References

- [references/writing-the-brief.md](references/writing-the-brief.md) - structure, report contract,
  real gates, stdin delivery, and delta briefs.
- [references/dispatch-and-poll.md](references/dispatch-and-poll.md) - flags, artifacts,
  `result.json`, polling, and failure recovery.
- [references/review-and-land.md](references/review-and-land.md) - review checklist, commit
  boundary, and rework through pi sessions.
- [references/multi-task-queues.md](references/multi-task-queues.md) - sequential queues,
  constraint carry-forward, progress tracking, and the final coherence pass.

© amElnagdy · MIT · amElnagdy/delegate-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set18

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor