agentmods.dev

prism-mcp: Instructions file for Claude Code

CLAUDE.md

prism-mcp CLAUDE.md is an instructions file for Claude Code from skyphusion-labs/prism-mcp. It costs 876 tokens per session, scanned B, original, MIT.

Repository instructions for Prism MCP, a server that lets coding agents call selected tools from the Prism playground API over the web.

In plain words
What is it for?
They guide work on the server, its tool catalogue, its connection to Prism, and its deployment settings.
Why use it?
They explain how this server fits with the wider Prism software and how it is configured and deployed.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is skyphusion-labs/prism-mcp's own configuration. It tells Claude Code how to work on prism-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 prism-mcp configures →

not rated 0repo 7d ago B scan 876 tokens original MIT
View source ↗ skyphusion-labs/prism-mcp play.skyphusion.org
Reuse

Borrowing it

Nothing to install: this file belongs to skyphusion-labs/prism-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/skyphusion-labs/prism-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/skyphusion-labs/prism-mcp

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.

agentmods badge for prism-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/skyphusion-labs/prism-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/skyphusion-labs/prism-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/skyphusion-labs/prism-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/skyphusion-labs/prism-mcp/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.

agentmods 80×15 button for prism-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/skyphusion-labs/prism-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/skyphusion-labs/prism-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 876 This file is loaded in full into every session.
When invoked 876 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00876 $0.00876
Opus 5 $0.00438 $0.00438
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00088 $0.00088

Measured 8d ago against content hash 3b2fdd077817, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

prism-mcp CLAUDE.md scanned grade B with 1 finding 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 8d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

identity via `sudo -u <member>`. Conventional Commits; SemVer on the package.
CLAUDE.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and the crew) working in this repo.

What this is

@skyphusion/prism-mcp: MCP door for the Prism playground API. Stateless Streamable-HTTP Worker that proxies curated tools to a prism host (PRISM_URL). Implementation lives here; deploy config is wrangler + secrets only.

Status: v1.0.0 (root package.json / tags / CHANGELOG.md). Estate peers prism, prism-control-plane, prism-ios, prism-android are also at 1.0.0 (2026-08-07).

  • Tool catalog: export const TOOLS in src/mcp-tools.ts (re-count from code if the number drifts).
  • License: MIT (client door). Prism remains AGPL.
  • Version: root package.json / release tags / CHANGELOG.md.

Relation to the stack

Repo Role
This package MCP server + tool catalog (npm + Worker entry) 1.0.0
prism Multimodal playground API (/api/*) 1.0.0
prism-control-plane Metered proxy; used when the prism user has a pcp_ key in prefs 1.0.0
prism-ios / prism-android Native clients 1.0.0

MCP talks to prism, not directly to the control plane. Control-plane spend is whatever the seeded prism session has configured under Account prefs.

Commands

npm run typecheck
npm test
npm run test:coverage
npm run build

Deploy model

  1. npm publish on tag prism-mcp-v* (.github/workflows/publish-npm.yml). Tag must match package.json and be an ancestor of main.
  2. Worker deploy is operator-side: pin the package, main → dist/mcp.js, secrets MCP_TOKEN + PRISM_SESSION, var PRISM_URL. See wrangler.mcp.toml.example and docs/mcp.md.

Architecture (load-bearing)

  • Two credentials. Agent presents MCP_TOKEN; Worker forwards prism session cookie. Prism cookie never leaves the Worker.
  • No prism bindings. Pure HTTP to PRISM_URL.
  • Stateless. Video/music/zip jobs: agent polls poll_job / poll_import.
  • One tool, one route (+ prism_request_read / prism_request_write escape hatch; prism_request is a write-only alias). Live WebSocket STT (/api/stt/stream) is out of scope for MCP tools.

Read the full file on GitHub · 82 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. 8d ago First seen · 82 lines · 876 tokens per session scan B 3b2fdd077817

Subscribe to this mod's changes

prism-mcp CLAUDE.md is an instructions file published in the GitHub repository skyphusion-labs/prism-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 876 tokens to every session, about $0.0044 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agentsai-agentscloudflare-workersmcpmit-licensemodel-context-protocol
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 · 5,153 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens