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.
npx agentmods add instructions/ivanwng97/pixtuoid/claude-mdgit clone --depth 1 https://github.com/IvanWng97/pixtuoidWrote 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.
[](https://agentmods.dev/instructions/ivanwng97/pixtuoid/claude-md)<a href="https://agentmods.dev/instructions/ivanwng97/pixtuoid/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanwng97/pixtuoid/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03644 | $0.03644 |
| Opus 5 | $0.01822 | $0.01822 |
| Sonnet 5 | $0.00729 | $0.00729 |
| Haiku 4.5 | $0.00364 | $0.00364 |
Grade B, and why
pixtuoid CLAUDE.md scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- No direct `~/.claude/settings.json` writes — go through `install/io.rs` (`write_config_atomic` / `ConfigLock`). How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Instructions for Claude Code (or any AI coding agent) in this repo.
(AGENTS.md symlinks here.) This is the workspace map; per-crate detail lives
in nested guides, auto-loaded when you touch their tree:
crates/pixtuoid-core/CLAUDE.md— headless lib: sources/decoders, reducer/state, sprites, grid/walkable. (+tests/CLAUDE.md: the 9-binary test layout, add-a-CLI test steps.)crates/pixtuoid-scene/CLAUDE.md— backend-agnostic render+sim engine: pixel painter, layout, walk/pose/pathfind, theme model, weather, pets, chitchat.crates/pixtuoid/CLAUDE.md— the binary: install, runtime, cli, config, multi-floor. (+src/tui/CLAUDE.md: the terminal painter.)integrations/raycast/CLAUDE.md,site/CLAUDE.md— the non-Rust--jsonconsumers; their gates aretsc/eslint/just site-check, not cargo.
What the guides hold. A nested CLAUDE.md says what its crate IS, plus the
facts no single declaration can own: cross-file workflows, comment-less
manifests, and directory-shape rules. Everything else a change needs —
the constraint that looks like a bug, the WHY, the test that pins it — is on
the declaration it constrains: read the item's doc comment before changing it.
A third consumer lives outside this repo: homebrew-core's pixtuoid
formula asserts exact CLI output (test do) and needs pixtuoid man /
completions <shell> on clean stdout — breakage surfaces in THEIR CI on an
autobump we never see, while our suite stays green (it asserts the same
strings as goldens). The asserted rows are marked "homebrew-core contract" at
validate.rs, sources_cli.rs, claude_code.rs; release-side consequences
in CONTRIBUTING.md.
What this is
Terminal-native, multi-agent pixel-art visualizer for AI coding agents: each
running CC session is an animated sprite in an ASCII office. Rust workspace,
five crates. Overview: README.md.
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.
- 2d ago Changed · +168 tokens per session 4d9b070997ce
- 6d ago First seen · 133 lines · 3,476 tokens per session scan B c75b62baff34
pixtuoid CLAUDE.md is an instructions file published in the GitHub repository IvanWng97/pixtuoid (469 stars, last pushed today), licensed MIT. It adds 3,644 tokens to every session, about $0.0182 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
deno CLAUDE.md
Claude Code instructions for denoland/deno, covering deno development guide, git workflow, high level overview, key directories and quick start.
compiler-explorer AGENTS.md
AGENTS.md instructions for compiler-explorer/compiler-explorer, covering agents.md, build & test commands, important workflow requirements, style guidelines and architecture guidelines.
moon AGENTS.md
AGENTS.md instructions for moonrepo/moon, covering agents.md, repository layout, prerequisites, rust workflow and conventions.
zeptoclaw CLAUDE.md
Claude Code instructions for qhkm/zeptoclaw, covering zeptoclaw, quick reference, agent workflow — task tracking protocol, 1. session start — check open issues and 2. new work — create issue first.
VTCode AGENTS.md
AGENTS.md instructions for vinhnx/VTCode, covering agents.md, rules, detailed guides, workspace and per-module guidance.
Better-Fullstack AGENTS.md
AGENTS.md instructions for Marve10s/Better-Fullstack, covering guidelines, web ui, workflow and bun.