What is pie CLAUDE.md?

Project instructions for Pie, a Rust workspace with separate crates for AI-provider access and the coding-agent runtime. They outline where the agent loop, provider implementations, storage, permissions, skills, generated model data, and other components live.

Use them to navigate the Rust workspace, update AI providers or agent behavior, regenerate model data, and work with sessions, permissions, prompts, skills, and notifications.

They help an agent change the correct layer without confusing the basic agent state machine with optional features that perform file or session work.

How c4pt0r/pie configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to c4pt0r/pie. 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/c4pt0r/pie/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/c4pt0r/pie

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/c4pt0r/pie/claude-md/github.svg)](https://agentmods.dev/instructions/c4pt0r/pie/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/c4pt0r/pie/claude-md"><img src="https://agentmods.dev/badge/instructions/c4pt0r/pie/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/c4pt0r/pie/claude-md"><img src="https://agentmods.dev/badge/instructions/c4pt0r/pie/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,140 This file is loaded in full into every session.

When invoked 2,140 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.

Model	Per session	Once invoked
Fable 5.1	$0.02140	$0.02140
Opus 5.5	$0.00856	$0.00856
Sonnet 5.5	$0.00428	$0.00428
Haiku 4.5	$0.00214	$0.00214

Measured 2mo ago against content hash 16a4a8263c88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pie CLAUDE.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 2mo 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Workspace layout

Rust 2024 Cargo workspace. Four crates; no non-crate workspace members.

crates/ai (pie-ai) — unified streaming LLM client. Provider implementations live under src/providers/; model + image catalogs are generated (models.generated.json, models_generated.rs, image_models_generated.rs — regenerate via crates/ai/scripts/regen_models.sh). Anthropic/OAuth, AWS SigV4, Vertex ADC, SSE/event-stream helpers, and retry/overflow utilities are here. Public surface is re-exported through src/lib.rs.
crates/agent (pie-agent-core) — agent runtime layered on pie-ai. The bare Agent in src/agent.rs is IO-free and owns conversation state, listeners, queues, and the cancellation token. The agent loop is src/agent_loop.rs. The harness module (feature harness) assembles opinionated extras: session storage (JSONL + in-memory), cost tracker, compaction, permission policy, prompt templates, skills loading, system prompt, and the trigger runtime / notification-hook abstraction. Filesystem IO is in the harness, not the bare agent.
crates/coding-agent (pie-coding-agent) — the pie CLI binary, REPL/TUI, slash-command registry, hooks, LSP supervisor, tool implementations under src/tools/, and trigger source adapters under src/triggers/. Entry point is src/main.rs.
crates/mcp (pie-mcp) — minimal MCP client: stdio transport, JSON-RPC framing, tools/list / tools/call. The coding-agent wraps server tools as AgentTools via tools/mcp_adapter.rs.
examples/ — runnable demos, not workspace members. examples/mcp-notify-python/ is a stdlib-only Python MCP server that pushes a synthetic heartbeat into pie's trigger runtime; examples/mcp-weather-python/ is the same shape but polls a live weather API and pushes a one-line summary for the harness to act on. See each README for wiring.

Layering goes one direction: coding-agent → agent (harness feature on) → ai; mcp is consumed by coding-agent. Keep the bare Agent IO-free — anything touching the filesystem, env, or network adapters belongs in harness/ or in coding-agent.

Read the full file on GitHub · 69 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.

2mo ago First seen · 69 lines · 2,140 tokens per session scan A 16a4a8263c88

Subscribe to this mod's changes

pie CLAUDE.md is an instructions file published in the GitHub repository c4pt0r/pie (173 stars, last pushed 3mo ago), licensed MIT. It adds 2,140 tokens to every session, about $0.0086 per session on Opus 5.5. 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.

pie CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pie CLAUDE.mdc4pt0r/pie	Instructions file	173	3mo ago	MIT	A	2,140	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

pie: Instructions file for Claude Code