agentmods.dev

spliit-mcp-cloudflare: Instructions file for Codex

AGENTS.md

spliit-mcp-cloudflare AGENTS.md is an instructions file for Codex, OpenCode from kegelmeier/spliit-mcp-cloudflare. It costs 1,109 tokens per session, scanned A, original, MIT.

A set of instructions for coding agents working on a Cloudflare-based Spliit project. It defines rules for protecting private data, handling deployments, and approving changes.

In plain words
What is it for?
Use it when changing or deploying the specified Spliit MCP project. It covers reading required project documents, preparing write previews, authenticating deployments, protecting endpoints, and planning encryption-key rotations.
Why use it?
It reduces the risk of exposing tokens or private group data and sets boundaries around writes, authentication, and encryption changes.

Instructions file for CodexOpenCode

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

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

not rated 1repo 3d ago A scan 1,109 tokens original MIT
View source ↗ kegelmeier/spliit-mcp-cloudflare deploy.workers.cloudflare.com
Reuse

Borrowing it

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

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 spliit-mcp-cloudflare AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kegelmeier/spliit-mcp-cloudflare/agents-md.svg)](https://agentmods.dev/instructions/kegelmeier/spliit-mcp-cloudflare/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kegelmeier/spliit-mcp-cloudflare/agents-md"><img src="https://agentmods.dev/badge/instructions/kegelmeier/spliit-mcp-cloudflare/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,109 This file is loaded in full into every session.
When invoked 1,109 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 $0.01109 $0.01109
Opus 5 $0.00554 $0.00554
Sonnet 5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 6d ago against content hash 0af52f4d6633, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spliit-mcp-cloudflare 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 6d 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for coding agents

Read this file and docs/agentic-install.md completely before changing or deploying this project.

Non-negotiable boundaries

  1. Treat group URLs/IDs, participant IDs, bearer tokens, encryption keys, draft IDs, and returned private group data as sensitive.
  2. Never print them to agent output, logs, chat, screenshots, fixtures, command arguments, commits, pull requests, or issues.
  3. Never put secrets in wrangler.jsonc or another tracked file.
  4. Keep WRITES_ENABLED true by default. Set it to false only when the user explicitly requests a read-only deployment. Tool availability is not write approval: always present the prepared preview and obtain separate approval before commit_draft.
  5. Do not enable request tracing. Spliit tRPC URLs can contain group IDs.
  6. Deploy only after the user authenticates the intended Cloudflare account or explicitly supplies a scoped CI credential through a secure channel.
  7. Never expose /mcp without MCP_AUTH_TOKEN or /admin without a distinct ADMIN_TOKEN.
  8. Never rotate DATA_ENCRYPTION_KEY without an explicit data-migration plan.

If a secret appears in output, stop, identify only the class of exposed value, and tell the user how to rotate or replace it without repeating it.

add_group_from_link is an explicit user-opt-in path. When the user knowingly chooses it, accept the link only as that MCP tool's input and never repeat it in commentary, results, logs, commands, tests, commits, or issues. The default installation flow must still use /setup and must never ask for a link.

New installation contract

The user does not need to give the agent a Spliit group URL. Use this order:

  1. Confirm Git state and read the documentation.
  2. Verify Node.js 22+, run npm ci, and run npm run check.
  3. Run npx wrangler whoami; use interactive npx wrangler login if needed.
  4. Generate two different random 32-byte bearer tokens plus one 32-byte key encoded as 64 hexadecimal characters. Do not display any value.
  5. Put them in a mode-0600 file outside the repository, or ignored .dev.vars, with SPLIIT_GROUPS_JSON=[]. Never pass them as command arguments.
  6. Deploy using npx wrangler deploy --secrets-file <secure-file>.
  7. Remove the temporary file unless the user explicitly wants ignored local development configuration and has another recovery copy.
  8. Validate /healthz, missing-token rejection for /mcp and /admin, and the deployment metadata without showing secrets.
  9. Give the user https://WORKER_HOST/setup. The user enters the admin token and group links directly in the browser; the agent does not request them.
  10. Configure one Streamable HTTP MCP client with /mcp and an environment-backed MCP token.
  11. Confirm list_groups, select_group, and an active-group read. Never paste returned private contents into chat.
  12. Report URLs and validation status, never credentials.

Read the full file on GitHub · 96 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. 6d ago First seen · 96 lines · 1,109 tokens per session scan A 0af52f4d6633

Subscribe to this mod's changes

spliit-mcp-cloudflare AGENTS.md is an instructions file published in the GitHub repository kegelmeier/spliit-mcp-cloudflare (1 stars, last pushed 3d ago), licensed MIT. It adds 1,109 tokens to every session, about $0.0055 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 2026-08-31.

DevOps and cloudcloudflare-workersmcp-servermodel-context-protocolspliit
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 · 5,182 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens