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 skills/mobilereality/mdma/mdma-integrationnpx skills add MobileReality/mdma --skill mdma-integrationgit clone --depth 1 https://github.com/MobileReality/mdmaWrote 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/skills/mobilereality/mdma/mdma-integration)<a href="https://agentmods.dev/skills/mobilereality/mdma/mdma-integration"><img src="https://agentmods.dev/badge/skills/mobilereality/mdma/mdma-integration.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 | $0.00111 | $0.03022 |
| Opus 5 | $0.00056 | $0.01511 |
| Sonnet 5 | $0.00022 | $0.00604 |
| Haiku 4.5 | $0.00011 | $0.00302 |
Grade A, and why
mdma-integration 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 5d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill guides integration of MDMA (Markdown Document with Mounted Applications) into real applications. MDMA is published as a set of composable npm packages under the @mobile-reality org — mdma-spec, mdma-parser, mdma-runtime, mdma-renderer-react, mdma-attachables-core, mdma-prompt-pack, mdma-validator, mdma-cli, mdma-mcp. A good integration picks the narrowest set of packages for the task, follows the parse → store → render contract, and uses the authoring and validation tooling rather than rolling its own. The goal is to make it obvious to a developer — or an agent — how to plug MDMA into their stack with minimum ceremony and maximum correctness.
The user provides an integration task: "add MDMA to this React chat app", "stream MDMA from the LLM and re-render as chunks arrive", "write a domain prompt for a clinical intake", "validate our MDMA docs in CI", "register a custom chart renderer", "expose MDMA to our agent via MCP", or "migrate our form rendering to MDMA". They may specify framework (React is first-class), LLM provider, validation rules, or PII constraints.
Integration Thinking
Before editing code, establish what "integrate MDMA" actually means for this request:
- Shape of the integration: One of — static document rendering (ship pre-written MDMA, parse+render once), LLM-streamed chat (assistant streams MDMA, reparse as chunks arrive, preserve store state across reparses), CI validation (lint
*.mdfiles against the spec), custom prompt authoring (build a domain-specificcustomPromptthat feedsbuildSystemPrompt), MCP exposure (let an agent callget-spec/build-system-prompt/validate-prompt), or custom component (register a Zod schema + renderer for a non-builtin type). Each has a different package footprint. - Package footprint: Install only what the integration needs. A chat app needs
mdma-parser+mdma-runtime+mdma-renderer-react+mdma-prompt-pack. A CI validator needs onlymdma-validator. An agent harness may need onlymdma-mcp. Don't install the full matrix "just in case" — the dependency graph is structured so you never have to. - Constraints: Which components are in scope? Which fields must be
sensitive? Which environment policies apply (allow/deny actions, redaction mode)? Which LLM provider is streaming? Does the host app already own state management, or willcreateDocumentStorebe the source of truth for document state? - Where prompts live: A domain prompt is a maintained artifact, not a one-off string. Decide where it lives (a
prompts/directory, exported from a package, generated via the CLI prompt builder) and how it's versioned, before writing it.
CRITICAL: Integrate with the smallest valid surface area. Prefer the provided MdmaDocument + createDocumentStore pairing over hand-rolled rendering. Prefer buildSystemPrompt({ customPrompt }) over concatenating strings yourself. Prefer the validator package over ad-hoc regex. The packages encode invariants (binding graph, PII redaction, audit log, policy) that are painful to re-derive.
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.
- 5d ago First seen · 168 lines · 111 tokens per session scan A aea8e3e87781
mdma-integration is a skill published in the GitHub repository MobileReality/mdma (66 stars, last pushed 25d ago), licensed MIT. It adds 111 tokens to every session and 3,022 once invoked, about $0.0006 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 skills, from other repositories
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. Use when building or reviewing React or Next.js components, state, or render performance.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
react-testing
React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…