fireboard-mcp: Instructions file for Codex

AGENTS.md

fireboard-mcp AGENTS.md is an instructions file for Codex, OpenCode from benhodgson87/fireboard-mcp. It costs 1,142 tokens per session, scanned A, original, MIT.

Repository instructions for fireboard-mcp, a TypeScript server that connects agents to FireBoard devices and data through tools.

In plain words
What is it for?
Use them when developing, testing, formatting, or adding tools and FireBoard API handling in this repository.
Why use it?
They define the project's commands, file structure, module conventions, API boundaries, caching, and testing approach.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is benhodgson87/fireboard-mcp's own configuration. It tells Codex and OpenCode how to work on fireboard-mcp 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 fireboard-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to benhodgson87/fireboard-mcp. 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/benhodgson87/fireboard-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/benhodgson87/fireboard-mcp

Made for: Codex, OpenCode.

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 fireboard-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/benhodgson87/fireboard-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/benhodgson87/fireboard-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/benhodgson87/fireboard-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/benhodgson87/fireboard-mcp/agents-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 fireboard-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/benhodgson87/fireboard-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/benhodgson87/fireboard-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,142 This file is loaded in full into every session.
When invoked 1,142 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 $0.01142 $0.01142
Opus 5.5 $0.00457 $0.00457
Sonnet 5.5 $0.00228 $0.00228
Haiku 4.5 $0.00114 $0.00114

Measured 24d ago against content hash c5b58f0fb593, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fireboard-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 24d 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.

AGENTS.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fireboard MCP — Agent Instructions

Commands

  • Type check: npm run build
  • Test: npm test
  • Lint: npm run lint
  • Format: npm run format
  • Dev server: npm run dev
  • Docs build: npm run docs:build (install website dependencies with npm ci --prefix website)
  • Docs dev server: npm run docs:dev

Language and modules

TypeScript, ESM ("type": "module"), moduleResolution: "Bundler". Internal relative imports use no file extension. Third-party imports keep whatever extension their package exports map requires (e.g. @modelcontextprotocol/sdk/server/mcp.js). tsx runs TypeScript directly in both dev (tsx watch) and production — no compilation step.

Structure

  • fireboard-api-client — Published package owning Fireboard transport, response validation, raw types, and device caching.
  • src/fireboard/client.ts — MCP adapter retaining a client per token, passing configuration, logging errors, and mapping empty Drive responses to null.
  • src/transformers/index.ts — Pure functions mapping raw API shapes to MCP response shapes. Keeps MCP response formatting separate from the client package.
  • src/tools/ — One file per tool group. Each exports a register*Tools(server, token) function. Token is injected via closure — never a tool parameter.
  • src/tools/outputSchemas.ts — Zod shapes for all tool outputSchema declarations. Shared across tool files.
  • src/oauth/provider.ts — FireboardOAuthProvider implementing OAuthServerProvider. Handles dynamic client registration, authorization code flow, and token verification. Client registrations and token mappings use the existing Container Durable Object in Cloudflare via a private outbound bridge (src/oauth/state.ts and cloudflare/oauth-state.js); local development defaults to memory. Login transactions and pending codes remain in memory.
  • src/views/login.html — OAuth login form.
  • website/ — Astro Starlight documentation. Tool pages are generated from MCP definitions by website/scripts/generate-tools.ts; editable guides live in website/src/content/docs/. Static output is built into website/dist/ and served by Express.
  • public/ — Static assets served at /. Lives at the repo root (not inside src/).
  • src/server.ts — Creates McpServer, calls all register functions.
  • src/index.ts — Express entry point: OAuth routes via mcpAuthRouter, POST /oauth/login (Fireboard credential exchange), POST /mcp (token-gated MCP handler), static documentation at /, and public asset serving.

Read the full file on GitHub · 72 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. 24d ago Changed · +19 tokens per session c5b58f0fb593
  2. 26d ago Changed · +10 lines · +298 tokens per session c37975a0901c
  3. 2mo ago First seen · 62 lines · 825 tokens per session scan A 2016675217ad

Subscribe to this mod's changes

fireboard-mcp AGENTS.md is an instructions file published in the GitHub repository benhodgson87/fireboard-mcp (1 stars, last pushed 25d ago), licensed MIT. It adds 1,142 tokens to every session, about $0.0046 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.

Related

fireboard-mcp AGENTS.md compared with instructions from other repositories

fireboard-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fireboard-mcp AGENTS.mdbenhodgson87/fireboard-mcpInstructions file125d agoMITA1,142Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode