pixl-ai: Instructions file for Claude Code

CLAUDE.md

pixl-ai CLAUDE.md is an instructions file for Claude Code from hamzaPixl/pixl-ai. It costs 2,297 tokens per session, scanned A, original, MIT.

A set of instructions for working on Pixl, an AI development platform with an orchestration engine, command-line tools, an API service, and a crew plugin.

In plain words
What is it for?
Use it when setting up, developing, testing, or navigating the Pixl codebase and its Python packages, command-line interface, API, and related tools.
Why use it?
It gives an agent project-specific guidance about the repository layout, setup process, and development conventions.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is hamzaPixl/pixl-ai's own configuration. It tells Claude Code how to work on pixl-ai 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 pixl-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hamzaPixl/pixl-ai. 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/hamzaPixl/pixl-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

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 pixl-ai CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hamzapixl/pixl-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/hamzapixl/pixl-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,297 This file is loaded in full into every session.
When invoked 2,297 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 $0.02297 $0.02297
Opus 5 $0.01149 $0.01149
Sonnet 5 $0.00459 $0.00459
Haiku 4.5 $0.00230 $0.00230

Measured 9d ago against content hash dc0f25f766cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pixl-ai 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 9d 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 · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pixl

AI dev platform — orchestration engine + Claude Code crew plugin.

Structure

pyproject.toml                  # uv workspace root (name="pixl")
Makefile                        # setup, install, test, check, format, release
packages/
├── engine/                     # pixl-engine (Python) — DAG orchestration, LLM providers, SQLite storage
│   ├── pyproject.toml
│   ├── pixl/                   # ~200 modules
│   └── tests/
├── cli/                        # pixl-cli (Python) — Click-based `pixl` binary
│   ├── pyproject.toml          # bundles crew via force-include
│   ├── pixl_cli/
│   │   ├── main.py             # Click group + setup command
│   │   ├── crew.py             # get_crew_root() resolver
│   │   ├── sandbox_client.py   # HTTP client for sandbox API (JWT, SSE, token refresh)
│   │   └── commands/           # artifact, config, cost, events, knowledge, project, sandbox, session, setup, state, template, workflow
│   └── tests/
├── api/                        # pixl-api (Python) — FastAPI service over pixl-cli
│   ├── pyproject.toml
│   ├── pixl_api/               # 24 route modules, 144 endpoints
│   │   ├── app.py              # FastAPI factory + lifespan
│   │   ├── auth/               # JWT auth, bcrypt, dependencies
│   │   ├── routes/             # All API routes (sessions, features, views, budget, etc.)
│   │   ├── schemas/            # Pydantic request/response models
│   │   ├── foundation/         # JWT, error handlers, pagination
│   │   ├── ws.py               # WebSocket event stream
│   │   ├── pool.py             # LRU ProjectDB connection pool
│   │   └── db.py               # User/workspace/API-key SQLite DB
│   └── tests/                  # 123 tests (DB, routes, auth, workspaces, API keys)
├── console/                    # pixl-console (TypeScript) — React SPA
│   ├── package.json
│   ├── src/                    # 321 TS/TSX files
│   │   ├── routes/             # TanStack Router file-based routing
│   │   ├── components/         # Dashboard, sessions, features, settings
│   │   ├── hooks/              # React Query hooks, WebSocket event stream
│   │   ├── lib/api/            # Typed API client (12 domain modules)
│   │   ├── stores/             # Zustand (auth, project, UI)
│   │   └── types/              # TypeScript interfaces
│   ├── vite.config.ts          # Vite + proxy to API at :8420
│   └── tests/                  # Playwright E2E
├── crew/                       # pixl-crew (bash/md) — NOT a Python package
│   ├── .claude-plugin/
│   ├── agents/                 # 14 agents
│   ├── skills/                 # 88 skills (see skills/ROUTING.md)
│   ├── hooks/                  # event hooks
│   ├── references/             # shared domain knowledge
│   ├── studio/stacks/          # nextjs, saas scaffolds
│   ├── contexts/               # dynamic context overlays
│   ├── examples/               # CLAUDE.md templates
│   ├── schemas/                # JSON schemas
│   └── scripts/                # setup, release, scaffold
└── sandbox/                    # pixl-sandbox (TypeScript) — Cloudflare Sandbox containers
    ├── docker/                 # Dockerfile, init.sh, test workflow
    ├── src/                    # Hono router + Durable Object
    ├── scripts/                # e2e test script
    └── wrangler.jsonc          # Cloudflare Workers config
scripts/release.sh              # monorepo release script
.claude/rules/                  # coding style, testing, security, git, etc.

Read the full file on GitHub · 189 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. 9d ago First seen · 189 lines · 2,297 tokens per session scan A dc0f25f766cc

Subscribe to this mod's changes

pixl-ai CLAUDE.md is an instructions file published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,297 tokens to every session, about $0.0115 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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens