By Agents365-ai
Offload code reviews, design critiques, and debugging tasks to the Pi agent from within Claude Code, with background job management and output retrieval. Also manages TTS and VLM model lifecycle for voice and vision capabilities.
Run a Pi review that challenges the implementation approach and design choices
Cancel an active background Pi job in this repository
Delegate investigation, an explicit fix request, or follow-up rescue work to the Pi rescue subagent
Show the stored final output for a finished Pi job in this repository
Run a Pi code review against local git state
Internal helper contract for calling the pi-companion runtime from Claude Code
Internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagnosis, and research tasks
Internal guidance for presenting Pi helper output back to the user
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No model invocation
No model invocation
Executes directly as bash, bypassing the AI model
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
English · 中文
External references: Pi coding agent · Pi RPC mode · Pi providers
A Claude Code plugin that delegates reviews and coding tasks to the Pi coding agent. 1:1 fork of codex-plugin-cc, runtime swapped from Codex to Pi.
The hard dependency is pi, not any particular LLM. Pi can be configured for DeepSeek, OpenAI, Anthropic, Google, Ollama, LM Studio, or any OpenAI-compatible endpoint via ~/.pi/agent/models.json. The plugin defers all model selection to pi unless you override per command.
status, result, cancel, and stop-time review gatecodex login requiredPlays well with pi-subagents: if installed, it works inside /pi:rescue runs without configuration.
Claude Code ─► /pi:review · /pi:rescue · /pi:status ...
│
▼
pi-companion.mjs (Node)
│ one pi --mode rpc subprocess per task
▼
Pi coding agent ─► whichever provider/model pi is configured for
│
▼
JSONL events + final assistant message
│
▼
job state files (status / result / cancel)
Codex's broker layer is gone — Pi is one-conversation-per-process, so the plugin spawns a fresh pi --mode rpc for each task. Background jobs are tracked in workspace-scoped state files. Review prompts inline the JSON schema since Pi has no outputSchema knob.
| Command | What it does |
|---|---|
/pi:setup | Verifies pi is installed + a provider is configured; toggles the stop-time review gate |
/pi:review | Standard code review of local git state |
/pi:adversarial-review | Steerable challenge review — questions the approach itself |
/pi:rescue | Delegate investigation or implementation to a Pi run via the pi:pi-rescue subagent |
/pi:status [job-id] | List active / recent Pi jobs in this repository |
/pi:result <job-id> | Show the stored final output for a finished job |
/pi:cancel <job-id> | Terminate a running background job |
Every command accepts --model <id> to pin a specific model just for that run. With no --model and no env override (see Pick your model), pi falls back to whatever it has configured by default.
# 1. Install pi (required)
npm install -g --ignore-scripts @earendil-works/pi-coding-agent
# 2. Configure a provider — pick one
export OPENAI_API_KEY=sk-... # OpenAI
export ANTHROPIC_API_KEY=sk-ant-... # Anthropic
export GOOGLE_API_KEY=... # Google
export DEEPSEEK_API_KEY=sk-... # DeepSeek
# or run a local model: see https://github.com/earendil-works/pi (Ollama / LM Studio)
# 3. Verify pi sees a model
pi --list-models | head
Install the plugin in Claude Code:
> /plugin marketplace add Agents365-ai/pi-plugin-cc
> /plugin install pi@agents365-pi
> /reload-plugins
> /pi:setup
npx claudepluginhub agents365-ai/pi-plugin-cc --plugin piUse Codex from Claude Code to review code or delegate tasks.
Automatic code review, adversarial review, and rescue via Codex.
Use Copilot from Claude Code to review code or delegate tasks.
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.