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/claude-mdgit 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 | $0.02549 | $0.02549 |
| Opus 5 | $0.01274 | $0.01274 |
| Sonnet 5 | $0.00510 | $0.00510 |
| Haiku 4.5 | $0.00255 | $0.00255 |
Grade A, and why
helm 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 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helm
Mission
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.
Scope of this file: orientation and the invariants that constrain code anywhere in the repo. It is deliberately NOT a feature catalogue — per-feature behaviour lives in
docs/. When you add a feature, document it there and link it from the table; do not grow this file.
System Overview
graph TB
XC[Gamepad<br/>Xbox USB/BT · Generic/DirectInput]
subgraph "Electron App"
subgraph "Renderer Process"
UI[UI: Sessions / Settings<br/>Vue 3 + Pinia]
BGA[Browser Gamepad API]
TV[TerminalManager → xterm.js]
end
subgraph "Main Process"
IPC[IPC Handlers<br/>domain files + orchestrator]
SM[SessionManager<br/>EventEmitter]
PTY[PtyManager<br/>node-pty]
SD[StateDetector<br/>activity + AIAGENT-* keywords]
CL[ConfigLoader<br/>Profile YAML]
FEAT[Feature managers<br/>Plans · Drafts · Artifacts · …]
end
UI <-->|contextBridge| IPC
BGA -->|button events| UI
TV <-->|pty:data / pty:write| PTY
end
XC --> BGA
IPC --> SM & PTY & CL & FEAT
PTY --> SD
Every feature manager follows the same shape: an EventEmitter class in src/session/, an injected persist sink writing YAML/JSON under the user config dir, IPC channels exposed through the preload bridge, and a renderer composable owning the reactive mirror. Match that shape when adding one.
Data Flow
Gamepad → Browser Gamepad API (renderer polling, 16ms)
→ IPC gamepad:event → debounce (250ms)
→ Resolve binding (per-CLI type)
→ Execute action (keyboard/voice/spawn/switch/prompt-tree)
D-pad / left stick navigates sessions and auto-selects the terminal.
Keyboard input routes to the active terminal (PTY stdin), blocked while a
selection-mode modal overlay is visible.
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 · 176 lines · 2,549 tokens per session scan A b5a6dea8dca0
helm CLAUDE.md is an instructions file published in the GitHub repository PetePeter/helm (24 stars, last pushed 3d ago), licensed MIT. It adds 2,549 tokens to every session, about $0.0127 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
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).
spec-kit AGENTS.md
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.
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.
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.
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).
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.