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/amelmo/loadout/claude-mdgit clone --depth 1 https://github.com/AmElmo/loadoutWhat 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 | $0.01780 | $0.01780 |
| Opus 5 | $0.00890 | $0.00890 |
| Sonnet 5 | $0.00356 | $0.00356 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
loadout 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loadout
A Tauri 2.x desktop application with React + Vite frontend.
Project Structure
src/- React frontend (Vite)src/components/- React UI componentssrc/lib/api/- Frontend-backend communication wrappers (e.g.,mcps.ts)src/stores/- Zustand state management storessrc/types/- TypeScript interfaces (mirror Rust structs)
src-tauri/- Rust backend (Tauri 2.x)src-tauri/src/commands/- Tauri command handlerssrc-tauri/src/parsers/- Configuration file parserssrc-tauri/src/scanners/- File system scanners
issues/- Task breakdown and specs with Acceptance Criteria, Technical Details, and Test Plans
Tech Stack
- Frontend: React, Vite, Tailwind CSS, Zustand, TanStack Query
- Backend: Rust, Tauri 2.x
- Package Manager: pnpm
Key Commands
pnpm tauri dev # Start development (both frontend and backend)
pnpm tauri:dev:fixtures # Start dev with demo fixtures (uses LOADOUT_HOME)
pnpm tauri:dev:empty # Start dev with empty fixtures (all empty states)
pnpm build # Build frontend only
pnpm tauri build # Build full application
Test Fixtures
fixtures/home/ contains a realistic mock home directory with configurations for Claude, Codex, and Gemini (skills, rules, hooks, MCPs, and project-level settings). Use pnpm tauri:dev:fixtures to run the app against these fixtures instead of your real home directory. fixtures/empty/ is a bare directory with no AI tool configs — use pnpm tauri:dev:empty to see all empty states across the UI. The LOADOUT_HOME env var is only honored in debug builds.
AI Tools Documentation
docs/ai-tools-reference.md maps every supported tool (Claude, Codex, Gemini, Cursor, Copilot, Windsurf, Roo, Cline, Kilo, OpenCode) and concept (MCPs, skills, agents, hooks, prompts, plugins, commands) to its official documentation URL. When modifying scanners, parsers, or fixture data for any AI tool, always consult this reference and verify against live docs using context7 or web search — config formats change frequently and the reference file may lag behind.
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 · 129 lines · 1,780 tokens per session scan A f3ac8707b68d
loadout CLAUDE.md is an instructions file published in the GitHub repository AmElmo/loadout (9 stars, last pushed 4mo ago), licensed MIT. It adds 1,780 tokens to every session, about $0.0089 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 2026-08-31.
Other instructions, from other repositories
thinkrail AGENTS.md
Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.
memorix GEMINI.md
Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.
Ctxo CLAUDE.md
Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).
calva-backseat-driver changelog.instructions.md
CHANGELOG.md conventions — audience, scope, and entry format for the Backseat Driver extension changelog.
wgm AGENTS.md
Instructions for agent-frontier/wgm, covering agents.md, build & run, validate (backpressure), operational notes and codebase patterns.
AmbyKit AGENTS.md
Instructions for ambystechcom/AmbyKit, covering agents.md — ambykit, what ambykit is, golden rules, project structure and build & test.