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/nyxtoolsdev/claude-md-starter/claude-mdgit clone --depth 1 https://github.com/NyxToolsDev/claude-md-starterWrote 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/nyxtoolsdev/claude-md-starter/claude-md)<a href="https://agentmods.dev/instructions/nyxtoolsdev/claude-md-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/nyxtoolsdev/claude-md-starter/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 | $0.00477 | $0.00477 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
claude-md-starter 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.
What it actually says
[PROJECT_NAME]
What This Project Does
[2-3 sentences describing the project's purpose and scope]
Tech Stack
| Layer | Tech |
|---|---|
| Language | [e.g., TypeScript, Python, Go] |
| Framework | [e.g., Next.js, FastAPI, Express] |
| Database | [e.g., Postgres, MongoDB, SQLite] |
| Hosting | [e.g., Vercel, Railway, AWS] |
Commands
[PACKAGE_MANAGER] run dev # Start dev server
[PACKAGE_MANAGER] run build # Production build
[PACKAGE_MANAGER] run test # Run tests
[PACKAGE_MANAGER] run lint # Lint all files
Conventions
Code Style
- File naming:
kebab-case.tsfor files,PascalCase.tsxfor components - Use
constby default,letonly when reassignment is needed, nevervar - Prefer
typeoverinterface, never useenum(use string literal unions) - Functions should be under 50 lines — extract if longer
- Extract magic numbers and strings to named constants
Error Handling
- Always handle errors explicitly — never swallow silently
- Use try-catch for async operations
- Return typed error objects from APIs, don't throw
- Log errors with context (what was attempted, what failed, relevant IDs)
Git
- Conventional commits:
feat:,fix:,docs:,refactor:,test: - Keep commits small and focused on one change
Things Claude Should Never Do
- Use
anytype — useunknownand narrow - Use
var— useconstorlet - Use
enum— use string literal unions - Commit secrets, API keys, or credentials
- Use string concatenation for SQL queries (use parameterized queries)
- Use
eval()orexec()with user input - Log sensitive data (PII, passwords, tokens)
- Skip error handling on async operations
- Generate code without reading the existing file first
Project-Specific Rules
[Add rules specific to your project here — naming patterns, architectural decisions, domain-specific constraints]
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 · 54 lines · 477 tokens per session scan A 9701cb9f9814
claude-md-starter CLAUDE.md is an instructions file published in the GitHub repository NyxToolsDev/claude-md-starter (0 stars, last pushed 5mo ago), licensed MIT. It adds 477 tokens to every session, about $0.0024 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
cookiecutter-mlops-package AGENTS.md
Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
nuxt-supabase-starter CLAUDE.md
Claude Code instructions for YuDefine/nuxt-supabase-starter, covering claude.md, language, project structure and meta vs template 邊界.
python-template AGENTS.md
Instructions for gpauloski/python-template, covering agent instructions, repository layout, environment & commands, conventions and skills.
rust-2026-template AGENTS.md
Instructions for d-oit/rust-2026-template, covering agent coding contract, quick reference, project structure, agent skills (.agents/skills/) and multi-agent support.
agent-context-os AGENTS.md
AGENTS.md instructions for conorbronsdon/agent-context-os, covering context os, session lifecycle, lifecycle kernel, context routing and safety.
template CLAUDE.md
Claude Code instructions for snowdreamtech/template, covering 🚨 critical system instruction 🚨, rules location, 🚨 critical token limit protocol 🚨 and why this file exists.