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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/ivanwng97/pixtuoid/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ivanwng97/pixtuoid/copilot-instructions.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 | $0.00823 | $0.00823 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
pixtuoid copilot-instructions.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot instructions — pixtuoid
pixtuoid is a terminal-native, multi-agent pixel-art visualizer for AI coding
agents — a Cargo workspace of five Rust crates: pixtuoid-core (headless lib),
pixtuoid-scene (backend-agnostic render+sim engine), pixtuoid (binary),
pixtuoid-web (wasm <canvas> painter, publish-excluded), and pixtuoid-hook
(the shim). DAG: pixtuoid-core ← pixtuoid-scene ← {pixtuoid, pixtuoid-web}.
Read CLAUDE.md first (and the nested crates/*/CLAUDE.md for
the crate you touch). It holds the architecture invariants and "known sharp
edges" — much of what looks like a bug is documented, load-bearing design.
Path-scoped Rust standards: .github/instructions/rust.instructions.md.
Workflow + how to add a theme / agent-CLI Source: CONTRIBUTING.md.
Architecture invariants (never break these)
pixtuoid-coreandpixtuoid-scenehave no terminal/window dependencies — noratatui,crossterm,winit, orstdout/println!(compiler-enforced by the crate boundary, checked byjust arch). Terminal/window concerns live in the binary's thin painters over the engine's render seam (pixtuoid_scene::floor::render_floor/pixel_painter::render_to_rgb_buffer) (there is no core render trait).- Events flow through one channel typed
mpsc::Sender<(Transport, AgentEvent)>; theTransporttag is load-bearing (hook-wins dedup). EachSourcetags its own events — don't hardcodeTransport::Hookon the consumer side. - The
Sourcetrait is the only seam for adding a transcript-bearing agent CLI (hook-only CLIs like Reasonix instead ship a hook decoder + an installTarget). - Hook install (
install::install_target, driven by the in-TUI Sources panels— noinstall-hooksCLI) writes through symlinks (resolve_symlink) — don't replace withfs::rename. - The hook shim must never block Claude Code — always exit 0 silently; the 200 ms write timeout is non-negotiable.
- Walkable mask = ground footprint only (top-down view); visual sprites may be wider/taller.
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.
- 4d ago First seen · 40 lines · 823 tokens per session scan A 6653aaed21f8
pixtuoid copilot-instructions.md is an instructions file published in the GitHub repository IvanWng97/pixtuoid (467 stars, last pushed today), licensed MIT. It adds 823 tokens to every session, about $0.0041 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 2026-08-30.
Other instructions, from other repositories
VTCode AGENTS.md
AGENTS.md instructions for vinhnx/VTCode, covering agents.md, rules, detailed guides, workspace and per-module guidance.
VTCode copilot-instructions.md
Copilot instructions for vinhnx/VTCode, covering vt code agent guidelines, build & test commands, preferred (faster with cargo-nextest), standard cargo commands and fallback (if nextest unavailable).
herdr-sidebar CLAUDE.md
Instructions for alexarthurs/herdr-sidebar, covering herdr-sidebar monorepo, build / test / lint, plugin dev workflow, windows caveats (verified against herdr 0.7.1 and 0.8.x) and release flow (verified for v0.7.0).
claude-replay CLAUDE.md
Claude Code instructions for tanghong123/claude-replay, covering claude.md — claude-replay, work tracking, the monitor's two shells, serving local files and test the tui without a tty.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.