Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/agents365-ai/pi-plugin-cc/agents-mdgit clone --depth 1 https://github.com/Agents365-ai/pi-plugin-ccWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/agents365-ai/pi-plugin-cc/agents-md)<a href="https://agentmods.dev/instructions/agents365-ai/pi-plugin-cc/agents-md"><img src="https://agentmods.dev/badge/instructions/agents365-ai/pi-plugin-cc/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00533 | $0.00533 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
pi-plugin-cc AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AGENTS.md
pi-plugin-cc drives the Pi coding agent to review code
and delegate tasks. The core is a harness-agnostic CLI, plugins/pi/scripts/pi-companion.mjs —
any coding agent that can run shell commands can drive it directly, not just Claude Code.
Full behavior, flags, and usage examples: see README.md (English) / README_CN.md (中文). This file only orients a coding agent working in this repo.
Using pi-plugin-cc from an agent
- Claude Code: install as a plugin (
/plugin marketplace add Agents365-ai/pi-plugin-cc,/plugin install pi@agents365-pi) and use the/pi:*slash commands documented inplugins/pi/commands/*.md. - Codex CLI: install the bundled custom prompts from
codex-prompts/into~/.codex/prompts/(see README.md § "Use from Codex"); invoke as/pi-review,/pi-rescue, etc. - Any other agent: call
node plugins/pi/scripts/pi-companion.mjs <subcommand> [args]directly. Runnode plugins/pi/scripts/pi-companion.mjs helpfor the full command list (review,adversarial-review,task,status,result,cancel,setup). Pass--jsonfor machine-readable output.
Working on this repo
- Requires Node.js >= 18.18 (
"engines"inpackage.json). No build step; plain ESM (.mjs). - Tests:
npm test(Node's built-in test runner,tests/*.test.mjs). Run this after any change underplugins/pi/scripts/. - Source of truth for CLI behavior is
plugins/pi/scripts/pi-companion.mjsandplugins/pi/scripts/lib/*.mjs;plugins/pi/commands/*.mdare the Claude Code slash-command prompt wrappers around that same CLI. - Version/changelog conventions:
plugins/pi/CHANGELOG.md, versions inpackage.jsonandplugins/pi/.claude-plugin/plugin.jsonstay in sync (npm run check-version). - Licensed under Apache-2.0, forked from
codex-plugin-cc— seeNOTICE.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 34 lines · 533 tokens per session scan A 60760658ff86
pi-plugin-cc AGENTS.md is an instructions file published in the GitHub repository Agents365-ai/pi-plugin-cc (44 stars, last pushed 21d ago), licensed Apache-2.0. It adds 533 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
dsh-TUI AGENTS.md
AGENTS.md instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.
Tianshu-harness CLAUDE.md
Claude Code instructions for huiliyi37/Tianshu-harness, covering 天枢 (tianshu) / rivet, build & test, architecture, conventions and known constraints.
peri CLAUDE.md
Claude Code instructions for KonghaYao/peri, covering claude.md — perihelion, 先读什么, 跨仓库契约, 任务路由 and 代码定位.
open-plan-annotator AGENTS.md
AGENTS.md instructions for ndom91/open-plan-annotator, covering open-plan-annotator: development guide, what this is, architecture, runtime distribution and key files.
carboncode AGENTS.md
Instructions for Yapie0/carboncode, covering agents.md, project context, current status, product direction and chosen base.
openinterpreter AGENTS.md
Instructions for openinterpreter/openinterpreter, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.