agentmods.dev

pixir: Instructions file for Claude Code

CLAUDE.md

pixir CLAUDE.md is an instructions file for Claude Code from Ranvier-Technologies/pixir. It costs 246 tokens per session, scanned A, original, MIT.

A project guide for the Pixir harness, an agent runtime with sessions, providers, tools, and terminal or standard-input/output interfaces.

In plain words
What is it for?
Use it when working on Pixir, especially to inspect its architecture, run checks and tests, format code, compile it, or build the executable.
Why use it?
It points agents to the current source of truth, project vocabulary, architecture notes, and validation commands.

Instructions file for Claude Code

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

This is Ranvier-Technologies/pixir's own configuration. It tells Claude Code how to work on pixir 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 pixir configures →

not rated 24repo 1mo ago A scan 246 tokens original MIT
View source ↗ Ranvier-Technologies/pixir pixir.dev
Reuse

Borrowing it

Nothing to install: this file belongs to Ranvier-Technologies/pixir. 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/Ranvier-Technologies/pixir/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Ranvier-Technologies/pixir

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 pixir CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ranvier-technologies/pixir/claude-md/github.svg)](https://agentmods.dev/instructions/ranvier-technologies/pixir/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ranvier-technologies/pixir/claude-md"><img src="https://agentmods.dev/badge/instructions/ranvier-technologies/pixir/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.

agentmods 80×15 button for pixir CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ranvier-technologies/pixir/claude-md"><img src="https://agentmods.dev/badge/instructions/ranvier-technologies/pixir/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 246 This file is loaded in full into every session.
When invoked 246 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 $0.00246 $0.00246
Opus 5.5 $0.00098 $0.00098
Sonnet 5.5 $0.00049 $0.00049
Haiku 4.5 $0.00025 $0.00025

Measured 2mo ago against content hash e27989abbc37, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pixir 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 · 36 lines

What it actually says

Pixir Harness - legacy agent guide

AGENTS.md is the canonical instruction file for coding agents in this repo. Start there, then read CONTEXT.md for vocabulary and the relevant ADR in docs/adr/.

This file remains only as a compatibility pointer for harnesses that still look for CLAUDE.md.

Current map

  • Runtime spine: Session -> Turn -> Provider -> Tools.
  • Source of truth: append-only local Log under .pixir/sessions/.
  • Presenters: terminal CLI and ACP over stdio.
  • Provider path: OpenAI Responses, store: false, provider usage as durable evidence, WebSocket-preferred transport with HTTP/SSE fallback.
  • Growth surfaces: Skills, Subagents, Workflows, Session Resources/Image Attachments, Provider-hosted Web Search, and future Skill Context Hydration.

Commands

mix deps.get
mix check
mix test
mix format --check-formatted
mix compile --warnings-as-errors
mix escript.build
./pixir doctor --json

Run Python helpers, if any, with:

uv run python file_name.py
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. 2mo ago First seen · 36 lines · 246 tokens per session scan A e27989abbc37

Subscribe to this mod's changes

pixir CLAUDE.md is an instructions file published in the GitHub repository Ranvier-Technologies/pixir (24 stars, last pushed 1mo ago), licensed MIT. It adds 246 tokens to every session, about $0.0010 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.

Building agentsacpagent-harnesscoding-agentsdeveloper-toolselixirotp
Related

pixir CLAUDE.md compared with instructions from other repositories

pixir CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pixir CLAUDE.mdRanvier-Technologies/pixirInstructions file241mo agoMITA246Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode