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/noemuch/bridge/claude-mdgit clone --depth 1 https://github.com/noemuch/bridgeWrote 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.
[](https://agentmods.dev/instructions/noemuch/bridge/claude-md)<a href="https://agentmods.dev/instructions/noemuch/bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/noemuch/bridge/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01174 | $0.01174 |
| Opus 5 | $0.00587 | $0.00587 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
bridge 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge DS — Claude Code Instructions
Mission
Bridge is a deterministic compiler that turns AI-generated design intent into Figma output guaranteed DS-compliant by construction, not by verification.
Bridge is to Figma what a type-checker is to code: the layer that catches errors at the door, not in production.
The 3 pillars
Everything Bridge does must serve one of these. Anything else is candidate for cut.
- Compiler-enforced correctness — 26 Figma API rules + 100% DS token compliance, deterministic
- Conversational UX via Claude Code skills —
make/fix/doneworkflow - Living KB synchronized with Figma — registries refreshed via cron, drift-aware
Design principle: subtraction by default
The Bridge codebase should be smaller in 6 months, not larger.
Subtraction is the default. Every subsystem must justify its existence against the 3 pillars or die. When in doubt, cut. Adding code is a hypothesis; the burden of proof is on the addition.
Architecture
Claude Code ──CSpec YAML──> Compiler (local) ──Plugin API──> MCP ──> Figma
Key principle: Claude NEVER writes raw Plugin API code. The compiler enforces all 26 Figma API rules automatically.
MCP transports
Two transports, auto-detected. See references/transport-adapter.md for full mapping.
| Operation | Console (preferred) | Official (fallback) |
|---|---|---|
| Execute code | figma_execute |
use_figma |
| Screenshot | figma_take_screenshot |
get_screenshot |
| DS extraction | figma_get_design_system_kit |
Composite strategy |
| Variables | figma_get_variables |
get_variable_defs |
| Styles | figma_get_styles |
search_design_system |
| Components | figma_search_components |
search_design_system |
| Connection | figma_get_status |
whoami |
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.
- 3d ago First seen · 111 lines · 1,174 tokens per session scan A 00e0e811b3c8
bridge CLAUDE.md is an instructions file published in the GitHub repository noemuch/bridge (156 stars, last pushed 3mo ago), licensed MIT. It adds 1,174 tokens to every session, about $0.0059 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
keyline-icons AGENTS.md
Instructions for keyline-icons/keyline-icons, covering this is not the next.js you know, keyline icons, the one rule, before you finish and where the real documentation is.
naksha-studio copilot-instructions.md
Instructions for Adityaraj0421/naksha-studio, covering naksha design team — github copilot, activation triggers, the design team, design rules for code generation and css custom properties (always use these patterns).
naksha-studio GEMINI.md
Instructions for Adityaraj0421/naksha-studio, covering naksha design team — gemini cli, project memory (v5), how to use, the team and core design (6 roles).
naksha-studio AGENTS.md
Instructions for Adityaraj0421/naksha-studio, covering naksha design team — autohand code cli, how to use naksha and operating rules.
canicode CLAUDE.md
Instructions for let-sunny/canicode, covering canicode, core goal, target environment, tech stack and project structure.
figma-mcp-free copilot-instructions.md
Instructions for karthikyaddana/figma-mcp-free, covering figma mcp free rules, required flow (do not skip), implementation rules, tool usage guide and node id format.