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/dohooo/helmor/claude-mdgit clone --depth 1 https://github.com/dohooo/helmorWrote 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/dohooo/helmor/claude-md)<a href="https://agentmods.dev/instructions/dohooo/helmor/claude-md"><img src="https://agentmods.dev/badge/instructions/dohooo/helmor/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 | $0.04327 | $0.04327 |
| Opus 5 | $0.02164 | $0.02164 |
| Sonnet 5 | $0.00865 | $0.00865 |
| Haiku 4.5 | $0.00433 | $0.00433 |
Grade A, and why
helmor 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 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents working with code in this repository.
What is Helmor
Helmor is a local-first desktop app built with Tauri v2 (Rust backend) + React 19 + Vite + TypeScript. It provides a workspace management UI with its own SQLite database (~/helmor/ in release, ~/helmor-dev/ in debug), letting users browse workspaces/sessions/messages and send prompts to AI agents (Claude Code CLI, OpenAI Codex CLI) via streaming IPC.
Commands
bun install # Install deps (bun 1.3+). Also runs `bun install` in sidecar/ via postinstall.
bun run dev # Full desktop app: Tauri + Vite (localhost:1420 in webview)
bun run dev:analyze # Same as dev, with perf HUD (VITE_HELMOR_PERF_HUD=1)
bun run build # tsc + vite build (frontend bundle to dist/)
bun run typecheck # tsc --noEmit for frontend AND sidecar
bun run lint # biome check . + cargo clippy -- -D warnings
bun run lint:fix # biome --write + cargo clippy --fix + cargo fmt
Tests are three targets — bun run test runs all three (frontend -> sidecar -> rust). Pre-commit hook runs biome on JS/TS and clippy/fmt on Rust.
bun run test # All three suites
bun run test:frontend # vitest run (jsdom, @testing-library/react)
bun run test:sidecar # cd sidecar && bun test
bun run test:rust # cd src-tauri && cargo test
bun run test:rust:update-snapshots # INSTA_UPDATE=always
bun run test:watch # vitest watch (frontend only)
Single test file: bun x vitest run src/App.test.tsx | cd sidecar && bun test src/foo.test.ts | cd src-tauri && cargo test --test pipeline_scenarios -- <name>
Architecture
Three-process model
- Frontend (
src/): React 19 SPA in Tauri webview. State management handled by specialized hooks (useAppShellState,useSelectionController,useEditorEditMode,useGlobalShortcutHandlers,useAppBootstrap) undersrc/shell/. TanStack React Query + context providers. - Rust backend (
src-tauri/src/): Tauri host, SQLite database, spawns and supervises the sidecar. - Sidecar (
sidecar/): Bun + TypeScript, wraps@anthropic-ai/claude-agent-sdkand@openai/codex(CLI). Built tosidecar/dist/helmor-sidecarviabun build --compile. JSON event stream over stdout.
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 · 198 lines · 4,327 tokens per session scan A 060ddcc82655
helmor CLAUDE.md is an instructions file published in the GitHub repository dohooo/helmor (1,298 stars, last pushed 12d ago), licensed Apache-2.0. It adds 4,327 tokens to every session, about $0.0216 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
octomux CLAUDE.md
Instructions for ShreyPaharia/octomux, covering octomux, tech stack, commands, architecture and logging.
orcho-core AGENTS.md
Instructions for symphos-ai/orcho-core, covering orcho-core instructions, scope, workspace development pipeline, stable install is read-only and build, run, and test.
orcho-mcp AGENTS.md
Instructions for symphos-ai/orcho-mcp, covering orcho-mcp instructions, scope, local instruction files, workspace development pipeline and stable install is read-only.
tlbx AGENTS.md
AGENTS.md instructions for tlbx-ai/tlbx, covering release authority, terminal design constraints, terminal size ownership, session surface boundary and agent controller runtime principle.
myrlin-workbook CLAUDE.md
Claude Code instructions for therealarthur/myrlin-workbook, covering claude workspace manager, critical scope constraint, project goal, tech stack preferences and agent teams.
tlbx CLAUDE.md
Claude Code instructions for tlbx-ai/tlbx: Read and follow AGENTS.md as if it were this file.