CcGlanceLine: Instructions file for Claude Code

CLAUDE.md

CcGlanceLine CLAUDE.md is an instructions file for Claude Code from CxMYu/CcGlanceLine. It costs 1,057 tokens per session, scanned B, original, MIT.

Repository instructions for CcGlanceLine, a Claude Code status-line renderer. It reads JSON supplied on standard input and prints one status line, with source code kept in the src folder.

In plain words
What is it for?
Use it when changing or verifying the CcGlanceLine repository. It covers source and build rules, zero runtime dependencies, isolated test configuration, and commands for type-checking, building, testing, previewing, and running the local output.
Why use it?
It records the project’s performance, styling, dependency, and build rules in one place. This helps agents avoid editing generated files or testing the wrong installed version.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is CxMYu/CcGlanceLine's own configuration. It tells Claude Code how to work on CcGlanceLine 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 CcGlanceLine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CxMYu/CcGlanceLine. 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/CxMYu/CcGlanceLine/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/CxMYu/CcGlanceLine

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 CcGlanceLine CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cxmyu/ccglanceline/claude-md/github.svg)](https://agentmods.dev/instructions/cxmyu/ccglanceline/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cxmyu/ccglanceline/claude-md"><img src="https://agentmods.dev/badge/instructions/cxmyu/ccglanceline/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 CcGlanceLine CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cxmyu/ccglanceline/claude-md"><img src="https://agentmods.dev/badge/instructions/cxmyu/ccglanceline/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,057 This file is loaded in full into every session.
When invoked 1,057 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01057 $0.01057
Opus 5 $0.00528 $0.00528
Sonnet 5 $0.00211 $0.00211
Haiku 4.5 $0.00106 $0.00106

Measured 9d ago against content hash 33f7bb88fd3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

CcGlanceLine CLAUDE.md scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

committed. `~/.claude/settings.json` and tokens live outside the repo — never
CLAUDE.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for working in this repo. See docs/development.md (and its zh-CN counterpart) for deeper build/test/cache internals.

What this is

@cxmyu/ccglance — a Claude Code status-line renderer. Claude Code pipes JSON on stdin per redraw; dist/cli.js renders one line to stdout. Zero runtime dependencies; the CLI is spawned fresh on every redraw, so cold-start latency matters.

Core rules

  • src/ is the only source of truth. Never hand-edit dist/ — it is gitignored and rebuilt by npm run build (and by npm ci via prepare).
  • Keep the style fixed and built-in: no user config loader, no external style file, no runtime style discovery.
  • Keep runtime dependencies at zero. New deps must be build-time only.
  • Verify local changes with npm run preview / node dist/cli.js, never a bare ccglance (that is the published global install on PATH).

Build / test

npm run typecheck   # tsc --noEmit (strict)
npm run build       # clean + compile src/ -> dist/
npm test            # build + node:test (fixtures / snapshots / smoke)
npm run preview     # render this repo's dist/

Tests and benchmarks isolate CLAUDE_CONFIG_DIR to a temp dir; they never touch the real ~/.claude/ccglance/ cache.

Background refresh (Windows footgun)

Git/version refreshes queue during render and flush after stdout as a single detached helper (dist/runtime/bg.js). On Windows the helper MUST be spawned as spawn(node, [...], { detached: true, windowsHide: true }) — spawning Node directly, never through a cmd/start trampoline. detached maps to DETACHED_PROCESS (no console allocated → no black window flash); a cmd start trampoline flashes a window on every cold refresh (the 1.1.0 regression fixed in 1.1.1). Dropping detached makes the helper die when the parent exits, so the cache never gets written. See src/runtime/refresh.ts.

Release process (publish a new version)

Publishing is done through a GitHub Release, which triggers .github/workflows/publish.yml (release: published). CI runs npm cinpm run typechecknpm testnpm publish --provenance --access public (OIDC provenance; NPM_TOKEN secret must bypass 2FA). Do not npm publish locally.

Read the full file on GitHub · 92 lines

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. 9d ago First seen · 92 lines · 1,057 tokens per session scan B 33f7bb88fd3a

Subscribe to this mod's changes

CcGlanceLine CLAUDE.md is an instructions file published in the GitHub repository CxMYu/CcGlanceLine (5 stars, last pushed 7d ago), licensed MIT. It adds 1,057 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens