coral_collective: Instructions file for Claude Code

CLAUDE.md

coral_collective CLAUDE.md is an instructions file for Claude Code from natesmalley/coral_collective. It costs 556 tokens per session, scanned A, original, MIT.

A project instruction file describing a collection of specialised coding agents and how they are organised. It lists agents for architecture, security, backend work, frontend work, testing, deployment, AI integration, compliance, and documentation.

In plain words
What is it for?
Guiding work in a multi-agent software project and identifying which specialist should handle architecture, code, security, testing, deployment, or documentation tasks.
Why use it?
It gives an agent a shared understanding of the project's available helpers and development conventions.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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 coral_collective CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/natesmalley/coral_collective/claude-md"><img src="https://agentmods.dev/badge/instructions/natesmalley/coral_collective/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 556 This file is loaded in full into every session.
When invoked 556 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 $0.00556 $0.00556
Opus 5 $0.00278 $0.00278
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00056 $0.00056

Measured 4d ago against content hash 4d8383e81e34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

coral_collective 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

CoralCollective is a curated collection of 10 specialized Claude Code subagents for software development. The agents live in .claude/agents/ and are automatically discovered by Claude Code's Task tool.

Subagents

Agent Model Purpose
architect Opus System architecture, technical specs, project planning
fullstack Sonnet Cross-cutting implementation, debugging, MVPs
security Opus Vulnerability audits, security hardening, auth systems
ai-engineer Opus LLM integration, vector DBs, RAG pipelines
backend Sonnet APIs, database schemas, server-side logic
frontend Sonnet UI components, accessibility, responsive design
qa Sonnet Test suites, edge cases, quality validation
devops Sonnet CI/CD, Docker, deployment, monitoring
compliance Sonnet Data governance, privacy, regulatory alignment
technical-writer Sonnet Documentation: specs, guides, API docs, ADRs

Design Principles

All agents follow these principles:

  • Tech-agnostic -- detect the project stack from config files (package.json, pyproject.toml, Cargo.toml, etc.) rather than assuming any specific language or framework
  • Read-first -- explore the codebase before making changes; understand existing patterns and conventions
  • Minimal-yet-sufficient -- do exactly what's needed without over-engineering or adding unnecessary abstractions
  • Structured output -- produce clear deliverables (code, docs, configs) rather than open-ended advice

Adding or Modifying Agents

Each agent is a single Markdown file in .claude/agents/. The file structure:

  1. Role declaration -- who the agent is and what it does
  2. Workflow -- step-by-step process the agent follows
  3. Principles -- constraints and quality standards
  4. Output format -- what the agent delivers

To add a new agent, create .claude/agents/<name>.md following the same structure as existing agents. Use model: opus for tasks requiring deep reasoning; use model: sonnet for implementation-focused work.

Read the full file on GitHub · 53 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. 4d ago First seen · 53 lines · 556 tokens per session scan A 4d8383e81e34

Subscribe to this mod's changes

coral_collective CLAUDE.md is an instructions file published in the GitHub repository natesmalley/coral_collective (9 stars, last pushed 4mo ago), licensed MIT. It adds 556 tokens to every session, about $0.0028 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 2026-09-04.

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