Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/brandcode-studio/brandsystem-mcp/agents-mdgit clone --depth 1 https://github.com/Brandcode-Studio/brandsystem-mcpWhat 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 | $0.02237 | $0.02237 |
| Opus 5 | $0.01118 | $0.01118 |
| Sonnet 5 | $0.00447 | $0.00447 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
brandsystem-mcp AGENTS.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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- brandsystem-mcp CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brandsystem-mcp
MCP server that extracts and manages brand identity (logo, colors, typography, voice, visual rules) for AI tools. Creates a .brand/ directory with structured YAML, DTCG tokens, and portable HTML reports.
Build and Test
npm install # Install dependencies
npm run build # Compile TypeScript to dist/
npm test # Run vitest tests
npm run lint # Type-check without emitting (tsc --noEmit)
npm run dev # Watch mode for development
npm start # Start the server (stdio transport)
Build must pass before committing. The entry point is src/index.ts (stdio transport) which creates the server from src/server.ts.
Branch and PR Workflow
main is protected by a ruleset (main-protection): no direct pushes, no force-pushes, PR required, and the CI matrix (build-and-test (20/22/24)) must pass before merge. Zero human approvals are required — CI is the gate. To land changes:
- Create a branch (
feat/...,fix/...) and commit there - Push and open a PR against
main - Enable auto-merge:
gh pr merge --auto --squash— the PR lands when CI is green - The branch is deleted automatically on merge
Do not attempt to push directly to main; the ruleset rejects it.
Architecture
src/
index.ts # Stdio transport entry point
server.ts # Creates McpServer, registers all 43 tools in priority order
tools/ # One file per tool, mostly (41 files, 43 tools — brand-feedback.ts registers 3). Each exports a register(server) function.
# Counts drift; verify via `ls src/tools/*.ts | wc -l` and `grep -rc 'server\.tool(' src/tools/*.ts`
lib/ # Shared utilities (brand-dir, css-parser, dtcg-compiler, content-scorer, etc.)
types/ # TypeScript type definitions
schemas/ # Zod schemas for validation
bin/
brandsystem-mcp.mjs # CLI entry point (npx @brandsystem/mcp)
Tool Registration Order (in server.ts)
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.
- 2d ago First seen · 195 lines · 2,237 tokens per session scan A 611835384dbd
brandsystem-mcp AGENTS.md is an instructions file published in the GitHub repository Brandcode-Studio/brandsystem-mcp (13 stars, last pushed 5d ago), licensed MIT. It adds 2,237 tokens to every session, about $0.0112 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 2026-08-30.
Other instructions, from other repositories
Brand-building-skills AGENTS.md
Instructions for arnabbagxd/Brand-building-skills, covering agents.md, repository overview, repository structure, build / lint / test commands and agent skills specification.
Brand-building-skills CLAUDE.md
Instructions for arnabbagxd/Brand-building-skills, a project described as: Brand building skills for Claude Code and AI agents. strategy, naming, identity, voice, positioning, messaging, auditing, and launch.
design-skills CLAUDE.md
Instructions for zstvns/design-skills, covering agents.md, repository overview, repository structure, the shared context documents and authoring rules.
marketing-cli AGENTS.md
Instructions for MoizIbnYousaf/marketing-cli, covering marketing agents, agent registry, how agents work, security posture and drop-in skill contract.
marketing-cli CLAUDE.md
Instructions for MoizIbnYousaf/marketing-cli, covering mktg: agent-native marketing playbook cli, what this is, repo layout, architecture and key principles.
brand-artisan CLAUDE.md
Instructions for roslove44/brand-artisan, covering claude.md, principes, 7. never change code you haven't read, charte par projet and toolchain de marque.