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/petepeter/helm/copilot-instructionsgit clone --depth 1 https://github.com/PetePeter/helmWhat 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 | $0.06272 | $0.06272 |
| Opus 5 | $0.03136 | $0.03136 |
| Sonnet 5 | $0.01254 | $0.01254 |
| Haiku 4.5 | $0.00627 | $0.00627 |
Grade A, and why
helm 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 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.
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 — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gamepad-cli-hub — Copilot Instructions
Project Purpose
DIY Xbox controller → CLI session manager. Control multiple AI coding CLIs (Claude Code, Copilot CLI, etc.) from a single game controller. Embedded terminals via node-pty + xterm.js — no external windows. Built as an Electron 41 desktop app on Windows.
System Overview
graph TB
subgraph Hardware
XC[Xbox Controller<br/>USB/Bluetooth]
end
subgraph "Electron App"
subgraph "Renderer Process"
UI[UI: Sessions / Settings]
BGA[Browser Gamepad API]
TM[TerminalManager<br/>Tab bar + switching]
TV[TerminalView<br/>xterm.js]
end
subgraph "Main Process"
IPC[IPC Handlers<br/>10 handler groups]
SM[SessionManager<br/>EventEmitter]
SP[SessionPersistence<br/>YAML save/load]
PS[ProcessSpawner]
PTY[PtyManager<br/>node-pty spawn/write/resize]
SD[StateDetector<br/>AIAGENT-* keywords]
PQ[PipelineQueue<br/>Auto-handoff]
IP[InitialPrompt<br/>Sequence → PTY]
CL[ConfigLoader<br/>Profile YAML]
end
UI <-->|contextBridge| IPC
BGA -->|button events| UI
TM --> TV
TV <-->|pty:data / pty:write| PTY
end
XC --> BGA
IPC --> SM
IPC --> SP
IPC --> PS
IPC --> PTY
IPC --> CL
SM --> SP
PS --> PTY
PTY --> SD
SD --> PQ
PTY --> IP
Data Flow Pipeline
flowchart LR
A[Xbox Controller] --> B[Browser Gamepad API<br/>renderer polling]
B --> C[250ms debounce + repeat engine]
C --> D{Binding Resolution}
D -->|per-CLI type| E[Execute Action]
E --> F[keyboard → SequenceParser → PTY stdin<br/>voice → OS-default robotjs, PTY when target: 'terminal'<br/>spawn → PtyManager<br/>switch → SessionManager → TerminalManager<br/>scroll → terminal buffer scroll<br/>context-menu → overlay modal]
Detailed flow:
- Browser Gamepad API polls at 16ms in the renderer process
- Button presses debounced at 250ms; D-pad and sticks auto-repeat when held (400ms initial delay, 120ms rate for D-pad; displacement-proportional for sticks)
- Emits button events to subscribers; analog sticks emit virtual button events
- Binding resolution: check CLI-specific bindings
- Execute resolved action (keyboard sequence → PTY stdin, voice → OS-default robotjs or PTY when target: 'terminal', spawn → PTY, session-switch, scroll, etc.)
- Voice bindings: default to OS (robotjs). If active terminal exists and
target === 'terminal'→ convert key to escape sequence viakeyToPtyEscape()→ptyWrite(). Otherwise → robotjs. Hold mode sends escape sequence once (PTY has no key-up). - Analog sticks: explicit binding found → execute action; no binding → fall back to stick mode (left=cursor arrows via PTY, right=configurable per-CLI bindings, default: scroll)
- D-pad / left stick navigates sessions and auto-selects the terminal
- Keyboard input always routes to the active terminal (PTY stdin)
- Ctrl+V paste: document-level interceptor reads clipboard text → writes to active PTY via
ptyWrite()regardless of DOM focus
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 First seen · 418 lines · 6,272 tokens per session scan A 0f6492cdd7c3
helm copilot-instructions.md is an instructions file published in the GitHub repository PetePeter/helm (24 stars, last pushed 2d ago), licensed MIT. It adds 6,272 tokens to every session, about $0.0314 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
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.