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/deodat-lawson/launchstack/claude-mdgit clone --depth 1 https://github.com/Deodat-Lawson/LaunchStackWhat 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 | $0.00696 | $0.00696 |
| Opus 5 | $0.00348 | $0.00348 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
LaunchStack 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 3d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Monorepo: apps/web (the application), apps/landing (marketing site),
packages/* (the bricks — feature packages, see REPOSITORY.md and the
lint-enforced boundaries in eslint.config.js), pipelines/ (the
compositions — product verticals; may import bricks, never the reverse),
services/* (foreign runtimes). pnpm workspaces.
Frontend rules (apps/web, apps/landing)
- UI primitives come from
~/components/ui/<name>. If one is missing, add it withnpx shadcn@latest add <name>(run in apps/web) — never hand-roll a button, input, table, or overlay. Modals use~/components/ui/dialog. cncomes from~/lib/utils. There is exactly one copy.- Colors are design tokens:
var(--…)frompackages/design-tokens/tokens.cssor semantic Tailwind classes (bg-panel,text-ink-2,border-line,bg-brand,text-danger). Never hex literals, never new inlinestylecolors, never the raw Tailwind palette (purple-600,slate-800) in new code. - The shadcn color names (
bg-background,text-muted-foreground, …) are a deprecated compat layer (apps/web/src/styles/compat.css). Don't extend it. - Dark mode:
data-theme="dark"on<html>. Usedark:variants or[data-theme="dark"]CSS; never branch onresolvedThemein JS for colors. - Icons:
lucide-react; brand marks from~/components/icons/brand. - Fonts:
var(--font-sans|serif|mono)only; loaded once insrc/app/fonts.ts. - Never import across route areas (
app/employer/**↔app/employee/**). Shared pieces go in~/componentsor~/lib. app/employer/_components/primitives.tsxanddocuments/_workspace/icons.tsxare deprecated — do not add imports.- Touch-it-migrate-it: when editing existing UI for feature work, convert the region you touch to kit + tokens; never launch a bulk rewrite.
- Full conventions:
apps/web/README.md. - The Mindmap app (
app/employer/mindmap) has its own README and one deliberate exception: shape colours are literal OKLCH values stored in the document, not tokens — a token would repaint when the viewer switches theme and change someone else's diagram. Its chrome uses tokens normally.
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.
- 3d ago First seen · 46 lines · 696 tokens per session scan A b33be636ca3d
LaunchStack CLAUDE.md is an instructions file published in the GitHub repository Deodat-Lawson/LaunchStack (885 stars, last pushed 3d ago), licensed Apache-2.0. It adds 696 tokens to every session, about $0.0035 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
opik python_sdk.instructions.md
Instructions for comet-ml/opik, covering opik python sdk code review guidelines, 🔧 core architecture principles, three-layer architecture, execution paths and 📋 api design standards.
opik copilot-instructions.md
Instructions for comet-ml/opik, covering copilot code review instructions, project overview, 1. git workflow & branch management, branch naming convention and commit message standards.
opik AGENTS.md
Instructions for comet-ml/opik, covering repository guidelines, scope & inheritance, project structure & module organization, build, test, and development commands and coding style & naming conventions.
openagent CLAUDE.md
Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).
FastGPT AGENTS.md
AGENTS.md instructions for labring/FastGPT, covering agents.md, 项目概述, 设计文档, 架构 and packages (库代码).
litellm AGENTS.md
AGENTS.md instructions for BerriAI/litellm, a project described as: The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM].