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/membranehq/agent-skills/integration-developmentnpx skills add membranehq/agent-skills --skill integration-developmentgit clone --depth 1 https://github.com/membranehq/agent-skillsWrote 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/membranehq/agent-skills/integration-development)<a href="https://agentmods.dev/skills/membranehq/agent-skills/integration-development"><img src="https://agentmods.dev/badge/skills/membranehq/agent-skills/integration-development.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 5.1 | $0.00113 | $0.15331 |
| Opus 5 | $0.00056 | $0.07666 |
| Sonnet 5 | $0.00023 | $0.03066 |
| Haiku 4.5 | $0.00011 | $0.01533 |
Grade C, and why
integration-development scanned grade C with 2 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- served as GET / or GET /admin from your backend --> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST $API/integrations -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 1,819 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Development
How integrations work — the five-step mental model
Every Membrane-backed feature walks through the same linear spine. Steps 0–3 are the core path; step 4 is a capability upgrade you graduate into when your app isn't bound to one specific vendor.
Step 0: Authenticate yourself — you, the developer; via MCP or `membrane` CLI
Step 1: Authenticate your code — sign JWTs in your backend
↳ single-tenant vs multi-tenant decided HERE
Step 2: Create connections — `membrane.ui.connect()` in your app UI
Step 3: Use connections — call actions on the external app
↳ discover via intent search when you don't know what to call
↳ dispatch: inline api/code | catalog id | workspace key
Step 4 (advanced): Universal — app-agnostic code via universal actions + cross-connection logic
In an MCP session step 0 is already done — membrane status confirms.
The most consequential choice — whether your app serves one shared
external account (single-tenant: a team CRM, an internal Slack) or
many end users (multi-tenant: each user connects their own Gmail,
Linear, etc.) — lives in step 1. It determines what your backend puts
in the JWT it signs, which in turn scopes every connection and action
that follows. Everything downstream of step 1 is uniform: the same
membrane.ui.connect() call, the same /act dispatch.
Before you code — typical discovery flow
Four commands cover most starting points:
# 1. Populate env with real credentials.
membrane credentials --shell > .env.local
# 2. Find the app you're integrating with (returns externalAppId).
membrane external-app list --search <app-name>
# 3. List catalog actions for that app.
membrane action list --externalAppId <id>
# 4. Check existing connections in the current tenant.
membrane connection list
CLI quick reference.
- Mint a JWT:
membrane token(add--tenantKey <key>for per-user,--managerforPOST /actionsand other manager ops).membrane --helpormembrane <command> --helplists the full surface.
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 · 1,819 lines · 113 tokens per session scan C d2ab16280933
integration-development is a skill published in the GitHub repository membranehq/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 113 tokens to every session and 15,331 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…