What is carrel CLAUDE.md?

A project instruction file that tells Claude Code how to work on the carrel repository, a local file toolkit and plugin marketplace.

Use it to guide coding, resume work from the project's saved state, follow its Python and command-structure rules, and maintain its Claude Code plugins.

It keeps important project decisions, naming rules, code standards, and command conventions in one place so work stays consistent across sessions.

How coltonbearden/carrel configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to coltonbearden/carrel. 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/coltonbearden/carrel/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/coltonbearden/carrel

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/coltonbearden/carrel/claude-md/github.svg)](https://agentmods.dev/instructions/coltonbearden/carrel/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/coltonbearden/carrel/claude-md"><img src="https://agentmods.dev/badge/instructions/coltonbearden/carrel/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/coltonbearden/carrel/claude-md"><img src="https://agentmods.dev/badge/instructions/coltonbearden/carrel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 900 This file is loaded in full into every session.

When invoked 900 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.

Model	Per session	Once invoked
Fable 5.1	$0.00900	$0.00900
Opus 5	$0.00450	$0.00450
Sonnet 5	$0.00180	$0.00180
Haiku 4.5	$0.00090	$0.00090

Measured 4d ago against content hash 8b2d6c2d9f8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

carrel 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 4d 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project CLAUDE.md — Local File Toolkit + Plugin Marketplace

Resume from disk: read STATE.md first — it always says what's done, what's in flight, and what's next. Decisions live in docs/DECISIONS.md.

Product name — single source of truth

The product name, tagline, and version live ONLY in product.json at the repo root. Never hardcode the name in code. Docs/manifests may use the name in prose, but anything generated (CLI banner, --version, asset text) must read product.json. scripts/finalize.sh performs renames by updating product.json and regenerating derived references.

Stack & layout

Python ≥3.12 (dev box: 3.14), managed by uv (pyproject.toml, uv run, uv sync).
Core library in src/<pkg>/; umbrella CLI entry in pyproject.toml [project.scripts].
All external binaries are called through the single adapter layer src/<pkg>/core/adapters.py — never subprocess directly from command modules. Adapters do capability detection and convert timeouts into a clean error. One documented exception: commands/watch.py runs user-authored --run shell actions itself (shell-quoted substitutions, --action-timeout).
Repo root doubles as a Claude Code plugin marketplace: .claude-plugin/marketplace.json + plugins/<name>/.

Coding standards

Python: type hints on public functions, pathlib.Path over strings, no global state, f-strings, stdlib argparse-free — we use the CLI framework chosen in Phase 2 (see docs/ARCHITECTURE.md).
Every CLI command MUST have: working --help, --json flag when output is data, ≥1 test, graceful degradation when an optional binary is missing (actionable message + install hint, exit code 3 — never a traceback, never a silent no-op).
No stubs/TODO/placeholder code in shipped commands. Cut and document in docs/FEATURES.md instead.
Wrap, don't rewrite: prefer proven libraries/binaries via the adapter layer; attribute in docs/LICENSES section.

Exit code convention

0 success
1 general/unexpected error (message to stderr, no traceback unless --debug); diff reuses 1 to mean "inputs differ" (documented in its --help)
2 bad usage/arguments (argparse-style)
3 missing optional dependency (message names the binary + install hint)
4 input file not found / unreadable / unsupported type
5 operation produced no result (e.g., search with no hits when --fail-empty)

Read the full file on GitHub · 49 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.

4d ago Changed · +4 lines · +208 tokens per session 8b2d6c2d9f8d
7d ago First seen · 45 lines · 692 tokens per session scan A 748f7baf1790

Subscribe to this mod's changes

carrel CLAUDE.md is an instructions file published in the GitHub repository coltonbearden/carrel (1 stars, last pushed 4d ago), licensed MIT. It adds 900 tokens to every session, about $0.0045 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.

Claude Code claude-code-plugins cli file-management mcp ocr

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

carrel: Instructions file for Claude Code