pi-permission-modes: Instructions file for Codex

AGENTS.md

pi-permission-modes AGENTS.md is an instructions file for Codex, OpenCode from GeorgeDong32/pi-permission-modes. It costs 2,448 tokens per session, scanned A, original, MIT.

Repository instructions for a coding agent extension that adds permission modes such as ask, plan, auto and bypass to the pi coding agent. They also describe the project structure, technology choices and commands.

In plain words
What is it for?
Use them when changing or reviewing the pi permission-modes extension, checking its TypeScript setup, or running its project commands.
Why use it?
They give an agent the rules it needs to work in this repository and control when tool actions need approval. They also point it to the product requirements and project conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is GeorgeDong32/pi-permission-modes's own configuration. It tells Codex and OpenCode how to work on pi-permission-modes itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pi-permission-modes configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GeorgeDong32/pi-permission-modes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GeorgeDong32/pi-permission-modes/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/GeorgeDong32/pi-permission-modes

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for pi-permission-modes AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/georgedong32/pi-permission-modes/agents-md/github.svg)](https://agentmods.dev/instructions/georgedong32/pi-permission-modes/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/georgedong32/pi-permission-modes/agents-md"><img src="https://agentmods.dev/badge/instructions/georgedong32/pi-permission-modes/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pi-permission-modes AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/georgedong32/pi-permission-modes/agents-md"><img src="https://agentmods.dev/badge/instructions/georgedong32/pi-permission-modes/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,448 This file is loaded in full into every session.
When invoked 2,448 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02448 $0.02448
Opus 5 $0.01224 $0.01224
Sonnet 5 $0.00490 $0.00490
Haiku 4.5 $0.00245 $0.00245

Measured 10d ago against content hash 8f6c12d90033, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pi-permission-modes 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 10d 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.

AGENTS.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — permission-modes

Guide for coding agents working in this repository. Product context (goals, users, features, success metrics): see docs/PRD.md.

Summary

A pi extension that implements Claude-Code-style permission modes (ask / plan / auto / bypass) for the pi coding agent, published on npm as @georgedong32/[email protected]. It intercepts tool calls, gates approvals per mode, supports CC-compatible allow/deny/ask permission rules (global + per-project), injects minimal mode context via a system-prompt anchor, provides an adaptive live footer, guards reads outside cwd in ask mode, supports an optional built-in auto classifier (completeSimple via @earendil-works/pi-ai/compat + ctx.modelRegistry auth), auto-switches the model per mode when the user has defined profiles in ~/.pi/agent/model-profiles.json, tracks outside-cwd writes for undo (bypass mode), and supports per-mode skill filtering.

Tech Stack

  • Language: TypeScript (ESM — "type": "module")
  • Framework: Pi coding agent extension API (@earendil-works/pi-coding-agent, @earendil-works/pi-ai, @earendil-works/pi-tui)
  • Package Manager: npm (no lock file committed)
  • Peer Dependencies: @earendil-works/pi-coding-agent, @earendil-works/pi-ai, @earendil-works/pi-tui, typebox
  • Third-party deps: None

Project Structure

permission-modes/             # @georgedong32/permission-modes
├── package.json              # pi manifest + npm package metadata
├── index.ts                  # main extension — default-exported factory function
├── classifier-client.ts      # built-in auto classifier (pi-ai completeSimple + modelRegistry auth)
├── config.ts                 # ~/.pi/agent/permission-modes.json loader
├── permissions.ts            # rule evaluation (deny → ask → allow)
├── permissions-loader.ts     # global + project permissions.json merge/persist
├── permission-rule-parser.ts # CC Tool(specifier) parse/serialize
├── shell-rule-matching.ts    # bash exact/prefix/wildcard matching
├── bash-permission-match.ts  # bash compound-command rule matching
├── path-permission-match.ts  # Read/Edit/Write path glob matching
├── profiles.ts               # model-profile config helpers (load, resolve, parse)
├── profiles.test.ts          # unit tests for profiles.ts (vitest)
├── utils.ts                  # pure helpers: bash allowlist, Plan: extraction, [DONE:n] tracking
├── index.test.ts             # integration tests (vitest)
├── utils.test.ts             # unit tests for utils (vitest)
├── vitest.config.ts          # vitest configuration
├── CHANGELOG.md              # release history
├── LICENSE                   # MIT
├── .gitignore                # excludes node_modules, package-lock.json, .pi/ artifacts
├── docs/
│   ├── PRD.md                # product requirements (human audience)
│   ├── prompts/              # mode-specific prompt context
│   │   ├── ask-mode-prompts.md
│   │   ├── plan-mode-prompts.md
│   │   └── auto-mode-prompts.md
│   └── suggestions.md        # feature ideas for future versions
├── AGENTS.md                 # this file
├── CLAUDE.md                 # thin pointer → AGENTS.md
└── .pi/
    └── permission-modes-45ea0551.md  # pi project marker (auto-generated)

Read the full file on GitHub · 124 lines

Changes

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.

  1. 10d ago First seen · 124 lines · 2,448 tokens per session scan A 8f6c12d90033

Subscribe to this mod's changes

pi-permission-modes AGENTS.md is an instructions file published in the GitHub repository GeorgeDong32/pi-permission-modes (2 stars, last pushed 4d ago), licensed MIT. It adds 2,448 tokens to every session, about $0.0122 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens