SkillsAdd

maxedapps/agent-skills

use-pi-subagents

>- Pi-specific launcher for bounded scout, research, and worker agents via the Pi RPC script adapter. Use this skill when on Pi, native `subagent_*` tools are inactive, and you need to launch, follow up, status, stop, or clean RPC children. Apply together with `use-subagents` policy (delegation, isolation, verify, cleanup). Do not use when a native subagent runtime should own the lane, for recursive delegation, ordinary background processes, or automatic Git/worktree management.

First seen Jul 22, 2026

Installation

$ npx skills add maxedapps/agent-skills --skill use-pi-subagents
View on skills.sh ↗ GitHub repository ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

find-skills Same topic
vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "fi…

3.3M installs
agent-browser Same topic
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

810.4K installs
vercel-react-best-practices Same topic
vercel-labs/agent-skills 697.8K installs
web-design-guidelines Same topic
vercel-labs/agent-skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…

617.3K installs
microsoft-foundry Same topic
microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …

576.5K installs
azure-prepare Same topic
microsoft/azure-skills

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Te…

568.3K installs

Also in this package

Other skills from maxedapps/agent-skills · top by installs.

npx skills add maxedapps/agent-skills
code-review 48 create-plan 1 implement-plan 1 web-research 34 create-skill 33 use-subagents 32 decomplex 1 explain 27 create-slides 1 vps-setup-hardening 19

Browse all from maxedapps/agent-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 58
License LICENSE
Default branch main
Open issues 0
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

LicenseMIT
CompatibilityRequires Node.js 22.19+ and Pi 0.81.1+ on tested macOS/Linux. Asynchronous supervision uses Unix process groups and a private Unix-domain control socket. Do not co-activate with a competing native subagent runtime. Children never run Git; the parent owns every workspace and Git operation. Complements `use-subagents`; does not replace it.
More metadata
short-description
Pi RPC launcher for subagents (with use-subagents policy)

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,085 B
  • docs SUMMARY.md 504 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 20 installs

SKILL.md

Use Pi Subagents

Pi RPC launcher only. Load/follow use-subagents for delegation, split, assignment shape, worktrees/Git, verify, workspace cleanup, and reporting.

This skill is how to start and supervise Pi RPC children via [scripts/subagents.mjs](scripts/subagents.mjs).

Pi rules

  • Only node scripts/subagents.mjs … from this skill directory — never raw pi --mode rpc
  • Roles: scout · research · worker (Pi profiles in [assets/agents/](assets/agents/); portable behavior also in use-subagents)
  • Parent supplies exact --cwd (prepare worktrees per use-subagents first)
  • Pi children: no Git at all (including bash); no worktree/branch management; no recursive delegation
  • Child claims/exit/status = evidence, not acceptance
  • clean retires script run state only — never cwd/worktrees/Git

Workflow

  1. Apply use-subagents (split, ownership, isolation, join points); prepare each --cwd.
  2. Build the task prompt; script wraps it with [assets/assignment-prompts.md](assets/assignment-prompts.md) + role profile from [assets/agents/](assets/agents/).
  3. Preflight from this skill directory:

- node scripts/subagents.mjs --help - node scripts/subagents.mjs info

  1. Launch: node scripts/subagents.mjs run --role <scout|research|worker> (--assignment FILE|--prompt TEXT) --cwd PATH --timeout MS [--async]

- blocking default; --async only for independent lanes

  1. Supervise: node scripts/subagents.mjs status|send|stop …

States/generations/recovery: [references/rpc-lifecycle.md](references/rpc-lifecycle.md)

  1. Verify + integrate + remove safe worktrees/branches per use-subagents.
  2. Runtime cleanup (after review): node scripts/subagents.mjs clean --run ID then --apply when safe.
  3. Report per use-subagents (include runId only if needed).

Failure

Unproven ownership, permissions, identity, liveness, or cwd provenance → stop. Retain ambiguous runtime/state; report runId, last state, cwd, next safe inspection step. No force-kill of unverified PIDs.