Glancey: Instructions file for Claude Code

CLAUDE.md

Glancey CLAUDE.md is an instructions file for Claude Code from nicholaspsmith/Glancey. It costs 431 tokens per session, scanned A, original, MIT.

Claude Code instructions for the Glancey project, including required project rules, preferred command-line tools, semantic code search, and a ban on OpenAI products.

In plain words
What is it for?
They guide session startup, codebase searching, file discovery, commit preparation, and tool or library choices.
Why use it?
They reduce inconsistent development practices by telling the agent how to explore the code, follow branching rules, and respect project-specific restrictions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is nicholaspsmith/Glancey's own configuration. It tells Claude Code how to work on Glancey itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Glancey configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nicholaspsmith/Glancey. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nicholaspsmith/Glancey/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nicholaspsmith/Glancey

Made for: Claude Code.

Wrote 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.

agentmods badge for Glancey CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nicholaspsmith/glancey/claude-md/github.svg)](https://agentmods.dev/instructions/nicholaspsmith/glancey/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nicholaspsmith/glancey/claude-md"><img src="https://agentmods.dev/badge/instructions/nicholaspsmith/glancey/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Glancey CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nicholaspsmith/glancey/claude-md"><img src="https://agentmods.dev/badge/instructions/nicholaspsmith/glancey/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 431 This file is loaded in full into every session.
When invoked 431 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00431 $0.00431
Opus 5.5 $0.00172 $0.00172
Sonnet 5.5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured 2mo ago against content hash 9f5243f06015, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Glancey 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 2mo 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.

CLAUDE.md · 53 lines

What it actually says

Claude Code Preferences

⚠️ SESSION START - READ FIRST

Before making any changes, read .claude/rules.md for project standards.

Key requirements:

  • NEVER commit directly to main - always create a feature branch first
  • One responsibility per commit - split multiple changes into separate commits
  • Use glancey for semantic code search, not Grep/Read for exploration

Command Preferences

Use modern CLI tools when available:

  • Use fd instead of find for file searching (faster, simpler syntax)
  • Use rg (ripgrep) instead of grep for content searching (faster, better defaults)
  • These tools are available on this system and should always be preferred

This project uses glancey for semantic code search. When exploring the codebase:

  1. Use search_code tool to find relevant code using natural language queries
  2. Run index_codebase if the index appears out of date
  3. Prefer semantic search over manual file exploration for understanding code patterns and finding implementations

OpenAI Policy

NEVER use any OpenAI products or services. This includes:

  • OpenAI API (GPT models, embeddings, etc.)
  • OpenAI SDKs or libraries
  • ChatGPT
  • DALL-E
  • Whisper API
  • Any other OpenAI service

For embeddings, use Jina or Ollama instead.

Pre-Commit Checklist

STOP! Before committing, verify:

  1. Read .claude/rules.md (required every time)
  2. On a feature branch, NOT main (git branch --show-current)
  3. Each commit has exactly ONE responsibility
  4. Subject line under 72 characters, imperative mood
  5. Body contains ONLY "Co-Authored-By: Claude [email protected]"
# Create feature branch first!
git checkout -b feature/your-feature-name
Changes

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.

  1. 2mo ago First seen · 53 lines · 431 tokens per session scan A 9f5243f06015

Subscribe to this mod's changes

Glancey CLAUDE.md is an instructions file published in the GitHub repository nicholaspsmith/Glancey (1 stars, last pushed 2mo ago), licensed MIT. It adds 431 tokens to every session, about $0.0017 per session on Opus 5.5. 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.

Related

Glancey CLAUDE.md compared with instructions from other repositories

Glancey CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Glancey CLAUDE.mdnicholaspsmith/GlanceyInstructions file12mo agoMITA431Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode