New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pi Agent Delegation

by CherryHQ in CherryHQ/cherry-studio

Runs the Pi agent in sessionless JSON mode and limits it to read-only tools for analysis, since Pi has no approval prompt of its own.

AGPL-3.0Auto-check passedAgent Workflows

Install Pi Agent Delegation

skills CLI
$ npx skills add CherryHQ/cherry-studio --skill code-mate-pi -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CherryHQ/cherry-studio code-mate-pi --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/code-cli-skills/code-mate-pi .claude/skills/code-mate-pi && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-mate-pi
GitHub stars
52k
Token cost
~348 tokens
SKILL.md length
183 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Runs the Pi agent in sessionless JSON mode and limits it to read-only tools for analysis, since Pi has no approval prompt of its own.

  • Works in 3 steps: Set the Bash working directory to the… → Check availability with command -v pi.… → Run one sessionless task
  • Delegating a read-only diagnosis to Pi
  • SKILL.md covers Run and Authentication And Permissions
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pi has no tool-approval prompt, so this skill puts the guardrails on the command line. The agent runs `pi --mode json --no-session` with the prompt as one quoted argument, from the project you named and under a finite timeout, normally 10 minutes, after confirming that `pi` is installed.

For analysis it appends `--tools read,grep,find,ls`, and write, edit or Bash tools are added only when you explicitly ask for workspace changes, with the tool list and directory kept as narrow as possible. Output is JSONL, and the agent inspects it for error events because Pi can report a model or tool failure there while the process still exits cleanly. The final message is used only when no error event occurred, and interactive Pi and `/login` are never started.

When your agent uses it

  • Delegating a read-only diagnosis to Pi
  • Running Pi on a scoped implementation task you have approved
  • Parsing Pi's JSON event stream to tell a real success from a hidden failure

Example prompts

  • “Have Pi diagnose the flaky integration test using read-only tools and report its final message.”
  • “Delegate the rename of the retry helper in ./lib to Pi, allowing edits only inside that folder.”
  • “Run Pi on this repo and tell me if its event stream contained any error events.”

Requirements

  • Pi installed through Code Mate
  • Login, model and provider configured in Code Mate

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
  2. Check availability with command -v pi. If it is missing, stop and ask the user to install Pi in Code Mate.
  3. Run one sessionless task

What it can do on your machine

Read from SKILL.md and the folder at commit dd0767e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pi Agent Delegation loads about 348 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 183 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~348

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from CherryHQ/cherry-studio at commit dd0767e, republished under its AGPL-3.0 licence (© CherryHQ). 183 words, ~348 tokens.

Download SKILL.mdSave it as .claude/skills/code-mate-pi/SKILL.md (or your agent's skills folder).
name
code-mate-pi
description
Runs Pi non-interactively and parses its JSON event stream for repository tasks. Use when the user asks to delegate a bounded analysis or implementation task to Pi.

Pi

Run

  1. Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
  2. Check availability with command -v pi. If it is missing, stop and ask the user to install Pi in Code Mate.
  3. Run one sessionless task:
bash
pi --mode json --no-session "<prompt>"

Pass the prompt as one quoted argument. Parse stdout as JSONL and inspect error events; Pi can report model or tool failure in the event stream, so process exit alone is insufficient. Never start interactive Pi or /login.

Authentication And Permissions

If Pi reports missing login, model, provider, or API configuration, stop and ask the user to configure Pi in Code Mate. Never request, read, print, or copy credentials.

Pi has no tool-approval prompt and normally exposes read, write, edit, and Bash tools. For analysis, append --tools read,grep,find,ls. Include write, edit, or Bash only when the user explicitly requested workspace changes, and keep the tool list and working directory as narrow as possible.

Example: run a read-only diagnosis with --tools read,grep,find,ls, then use the final JSONL message only if no error event occurred.

© CherryHQ, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in resources/code-cli-skills/code-mate-pi of CherryHQ/cherry-studio.

Open the folder on GitHubat commit dd0767e

Compare with similar skills

Pi Agent Delegation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pi Agent Delegation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pi Agent Delegation this skillCherryHQ/cherry-studio52k—~348Automated safety check: PassAGPL-3.0
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Harness Agent Team Designerrevfactory/harness9.1k—~4.5kAutomated safety check: PassApache-2.0
ClawTeam Multi-Agent Swarmwin4r/ClawTeam-OpenClaw1.5k1 repos~2.9kAutomated safety check: PassMIT
Sub-Agent Delegationcodewhale-hq/Codewhale41k—~790Automated safety check: PassMIT

Similar skills

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Harness Agent Team Designer

    revfactory/harness

    Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.

    9.1k GitHub stars~4.5k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • ClawTeam Multi-Agent Swarm

    win4r/ClawTeam-OpenClaw

    Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

    1.5k GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed

  • Sub-Agent Delegation

    codewhale-hq/Codewhale

    Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.

    41k GitHub stars~790 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Parallel Agents

    xenitV1/Antigravity-Workflows

    Native multi-agent orchestration using Claude Code's Agent Tool.

    130 GitHub starsUsed in 9 repos~1.3k tokens
    Agent WorkflowsAuto-check passed

More from CherryHQ/cherry-studio

All 30 skills in this repo

  • Office File Transform

    CherryHQ/cherry-studio

    Derives new files from a selected part of a spreadsheet, Word document, PDF or slide deck, such as a cell range, paragraph, page or slide, without ever modifying the source file.

    52k GitHub stars~4.7k tokensUpdated today
    Auto-check passed

  • GitHub Issue Creator

    CherryHQ/cherry-studio

    Creates GitHub issues for the current repository by choosing the matching issue template and following its format, with a permission check for engineering tasks.

    52k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Cherry Studio PR Review

    CherryHQ/cherry-studio

    Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.

    52k GitHub stars~3.9k tokensUpdated today
    Auto-check passed

  • Cherry Studio Regression Tests

    CherryHQ/cherry-studio

    Runs Cherry Studio's critical-path regression suite as deterministic Playwright E2E tests through a GitHub workflow on macOS and Windows runners.

    52k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Antigravity CLI Runner

    CherryHQ/cherry-studio

    Runs the Antigravity CLI headlessly with the agy command to analyze a repository or carry out a coding task, then checks its JSON result and the diff.

    52k GitHub stars~531 tokensUpdated today
    Auto-check passed

  • Kimi Code Delegation

    CherryHQ/cherry-studio

    Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.

    52k GitHub stars~504 tokensUpdated today
    Auto-check passed

Categories

Questions about Pi Agent Delegation

What does Pi Agent Delegation do?

Runs the Pi agent in sessionless JSON mode and limits it to read-only tools for analysis, since Pi has no approval prompt of its own. Pi has no tool-approval prompt, so this skill puts the guardrails on the command line. The agent runs `pi --mode json --no-session` with the prompt as one quoted argument, from the project you named and under a finite timeout, normally 10 minutes, after confirming that `pi` is installed.

When should I use Pi Agent Delegation?

Pi Agent Delegation fits situations like: delegating a read-only diagnosis to Pi; running Pi on a scoped implementation task you have approved; parsing Pi's JSON event stream to tell a real success from a hidden failure.

How do I install Pi Agent Delegation in Claude Code?

Run `npx skills add CherryHQ/cherry-studio --skill code-mate-pi -a claude-code`. Or copy the skill folder (resources/code-cli-skills/code-mate-pi in CherryHQ/cherry-studio) into .claude/skills/code-mate-pi in your project. Claude Code loads it when a task matches its description.

How do I install Pi Agent Delegation in Codex?

Run `npx skills add CherryHQ/cherry-studio --skill code-mate-pi -a codex`. Or copy the skill folder (resources/code-cli-skills/code-mate-pi in CherryHQ/cherry-studio) into .agents/skills/code-mate-pi in your project. Codex loads it when a task matches its description.

Can I use Pi Agent Delegation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CherryHQ/cherry-studio --skill code-mate-pi -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-mate-pi, .gemini/skills/code-mate-pi, .github/skills/code-mate-pi and .opencode/skills/code-mate-pi in your project.

What does Pi Agent Delegation need to run?

SKILL.md names no scripts, command-line tools or credentials: Pi Agent Delegation is instructions for the agent only. Our summary lists: Pi installed through Code Mate; Login, model and provider configured in Code Mate.

Does Pi Agent Delegation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pi Agent Delegation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pi Agent Delegation use?

Pi Agent Delegation is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pi Agent Delegation use?

About 348 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pi Agent Delegation?

Skills that share tags, products or a category with Pi Agent Delegation: Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars), Harness Agent Team Designer (revfactory/harness, 9.1k stars) and ClawTeam Multi-Agent Swarm (win4r/ClawTeam-OpenClaw, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pi Agent Delegation?

CherryHQ (a GitHub organization) maintains it in CherryHQ/cherry-studio, which has 52,407 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 7, 2026.

Source: CherryHQ/cherry-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.