What is brighty-agent-toolkit CLAUDE.md?

A repository instruction file for a Brighty toolkit, a monorepo containing related projects in one repository, including an MCP server and agent skills.

Use it when modifying the toolkit, its TypeScript banking server, its skills, or the surrounding plugin and repository configuration.

It gives coding agents the project context, rules, and workflows they need to make compatible changes and avoid breaking required conventions.

How razz-team/brighty-agent-toolkit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to razz-team/brighty-agent-toolkit. 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/razz-team/brighty-agent-toolkit/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/razz-team/brighty-agent-toolkit

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/razz-team/brighty-agent-toolkit/claude-md/github.svg)](https://agentmods.dev/instructions/razz-team/brighty-agent-toolkit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/razz-team/brighty-agent-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/razz-team/brighty-agent-toolkit/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/razz-team/brighty-agent-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/razz-team/brighty-agent-toolkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,219 This file is loaded in full into every session.

When invoked 2,219 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	$0.02219	$0.02219
Opus 5.5	$0.00888	$0.00888
Sonnet 5.5	$0.00444	$0.00444
Haiku 4.5	$0.00222	$0.00222

Measured 2mo ago against content hash 0202c21a6f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brighty-agent-toolkit 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 · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository context for Claude

This file is loaded automatically by Claude Code, Cursor, and similar tools when working in this repository. It captures the conventions and invariants that aren't obvious from the file tree alone.

What this repository is

brighty-agent-toolkit is a monorepo containing three things stitched together:

An Anthropic plugin (.claude-plugin/) — wraps everything below into a single installable unit
A TypeScript MCP server (packages/mcp-server/) — exposes the Brighty banking API as MCP tools (stdio in v0.1)
AgentSkills-spec skills (skills/) — teach AI agents how to use those tools effectively

Specialized agents (agents/) and slash commands (commands/) are planned for v0.1 — not present in v0.0.1, not declared in plugin.json. The server is stdio-only by design; there is no hosted/HTTP mode and one is not planned.

Skills follow the open AgentSkills standard (https://agentskills.io). The plugin wrapper is Anthropic-specific. Same skills work in Codex, Cursor, OpenClaw — the wrapper does not.

Critical invariants

These must hold across every change. CI enforces all of them:

Every tool name referenced in a SKILL.md exists in packages/mcp-server/src/tools/. Cross-checked by scripts/check-tool-references.mjs.
Every SKILL.md validates against the AgentSkills spec via skills-ref validate.
SKILL.md body stays under 500 lines. Detailed material lives in references/ and loads on demand.
Skill name in frontmatter matches the parent directory exactly (spec requirement).
No skill executes arbitrary code or fetches arbitrary URLs. Skills only orchestrate calls to MCP tools.

Workflows

Adding a new skill

Create skills/<skill-name>/SKILL.md with required frontmatter (name, description).
The description field is what the agent uses to decide when to activate the skill. Format: what the skill does + when to use it + 3-5 trigger keywords. Spec max is 1024 chars; aim for under 300.
Reference MCP tools by their actual snake_case name (e.g., brighty_create_payout).
Add the skill path to .claude-plugin/plugin.json under skills.
Run yarn validate and yarn check-tools.

Read the full file on GitHub · 146 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.

2mo ago First seen · 146 lines · 2,219 tokens per session scan A 0202c21a6f86

Subscribe to this mod's changes

brighty-agent-toolkit CLAUDE.md is an instructions file published in the GitHub repository razz-team/brighty-agent-toolkit (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,219 tokens to every session, about $0.0089 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.

brighty-agent-toolkit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
brighty-agent-toolkit CLAUDE.mdrazz-team/brighty-agent-toolkit	Instructions file	2	2mo ago	MIT	A	2,219	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

brighty-agent-toolkit: Instructions file for Claude Code