ApraPipes CLAUDE.md

ApraPipes CLAUDE.md is an instructions file for Claude Code from Apra-Labs/ApraPipes. It costs 1,556 tokens per session, scanned A, original, MIT.

A project instruction file for coding agents working on ApraPipes. It records the current development task, repository structure, platform details, and required build and test checks.

In plain words
What is it for?
Use it as a reference when working on the ApraPipes SDK, command-line tools, platform libraries, examples, and tests.
Why use it?
It gives agents project-specific guidance, including how to handle Windows integration tests and when verification is required.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

Install

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.

agentmods
npx agentmods add instructions/apra-labs/aprapipes/claude-md
Clone the repo
git clone --depth 1 https://github.com/Apra-Labs/ApraPipes

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.

agentmods badge for ApraPipes CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/apra-labs/aprapipes/claude-md.svg)](https://agentmods.dev/instructions/apra-labs/aprapipes/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/apra-labs/aprapipes/claude-md"><img src="https://agentmods.dev/badge/instructions/apra-labs/aprapipes/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,556 This file is loaded in full into every session.
When invoked 1,556 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01556 $0.01556
Opus 5 $0.00778 $0.00778
Sonnet 5 $0.00311 $0.00311
Haiku 4.5 $0.00156 $0.00156

Measured yesterday against content hash 18d5b719eea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ApraPipes 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 yesterday.

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 · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - ApraPipes Declarative Pipeline

Instructions for Claude Code agents working on the ApraPipes project.

Branch: feat/sdk-packaging Documentation: docs/declarative-pipeline/


Current Phase: Sprint 12 - Windows Integration Test Fix

Mission: Fix Windows integration tests that fail with exit code 127.

Problem:

  • Windows integration tests fail with exit code 127 (CLI fails to launch)
  • Linux, macOS, and ARM64 all pass
  • Root cause: Git Bash PATH handling for DLL loading is problematic on Windows

Solution:

  • Use PowerShell (pwsh) for Windows integration tests
  • Native Windows PATH handling works correctly
  • Linux/macOS continue to use bash (works correctly)

Status: Awaiting CI verification (commit c41375381)


SDK Structure (Complete)

aprapipes-sdk-{platform}/
├── bin/
│   ├── aprapipes_cli              # CLI tool
│   ├── aprapipesut                # Unit tests
│   ├── aprapipes.node             # Node.js addon
│   └── *.so / *.dll / *.dylib     # Shared libraries
├── lib/
│   └── *.a / *.lib                # Static libraries
├── include/
│   └── *.h                        # Header files
├── examples/
│   ├── basic/                     # JSON pipeline examples
│   ├── cuda/                      # CUDA examples (if applicable)
│   ├── jetson/                    # Jetson examples (ARM64 only)
│   └── node/                      # Node.js examples
├── data/
│   ├── frame.jpg                  # Sample input files
│   └── faces.jpg                  # For examples to work out of box
├── README.md                      # SDK usage documentation
└── VERSION                        # Version info

Current State:

Workflow SDK Artifact Status
CI-Windows aprapipes-sdk-windows-x64 ✅ Complete (integration tests pending)
CI-Linux aprapipes-sdk-linux-x64 ✅ Complete
CI-MacOSX aprapipes-sdk-macos-arm64 ✅ Complete
CI-Linux-ARM64 aprapipes-sdk-linux-arm64 ✅ Complete

Read the full file on GitHub · 204 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. yesterday First seen · 204 lines · 1,556 tokens per session scan A 18d5b719eea9

Subscribe to this mod's changes

ApraPipes CLAUDE.md is an instructions file published in the GitHub repository Apra-Labs/ApraPipes (34 stars, last pushed 25d ago), licensed MIT. It adds 1,556 tokens to every session, about $0.0078 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 2026-09-04.