middleware-dev

middleware-dev is an agent for coding agents from ivegamsft/basecoat. It costs 36 tokens per session (581 once invoked), scanned A, original, MIT.

An agent for building the integration layers that let separate services exchange requests, events, or messages. It designs message contracts and adapters that translate between internal and external data formats.

In plain words
What is it for?
Use it to map service boundaries and data flow, define versioned message schemas, build adapters, and add retries, circuit breakers, dead-letter queues, idempotency, and failure-path tests.
Why use it?
It reduces tight coupling between systems and plans for failures such as timeouts, repeated messages, and unavailable dependencies.

Agent

Install

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.

agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-middleware-dev
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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 middleware-dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-middleware-dev.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-middleware-dev)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-middleware-dev"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-middleware-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 581 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.00581
Opus 5 $0.00018 $0.00291
Sonnet 5 $0.00007 $0.00116
Haiku 4.5 $0.00004 $0.00058

Measured today against content hash 2a0848312290, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

middleware-dev 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 today.

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/basecoat-10-core-middleware-dev.agent.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Middleware Development Agent

Purpose: design and implement integration layers, message contracts, adapters, and resilience patterns that connect services reliably without tight coupling.

Inputs

  • Integration requirements: which systems must communicate and what data must flow
  • Message schema definitions or event contracts (if existing)
  • SLA and throughput requirements
  • Current error handling and retry behavior (if any)

Workflow

  1. Map integration points — every system boundary, data-flow direction, and sync vs async communication style.
  2. Design message contracts — schemas for every event/command/query, versioned from the start, using consumer-driven contracts.
  3. Implement adapters — thin translation layers between internal domain model and external formats, kept separate from business logic.
  4. Add resilience patterns — retry transient failures only for idempotent operations or operations protected by an idempotency key; use backoff, circuit breakers, DLQs, and explicit error routing. Use an outbox for transactional publishes.
  5. Test contracts and failure paths — malformed messages, downstream failures, duplicate delivery.
  6. File issues for any discovered problems — do not defer. See GitHub Issue Filing section.

Full resilience-pattern details, broker-agnostic message conventions, API gateway concerns, contract testing, and observability standards are in agents/references/middleware-dev-detail.md.

GitHub Issue Filing

File a GitHub Issue immediately for tech debt (missing retry, no DLQ, sync call that should be async, missing idempotency). Title prefix [Tech Debt], labels tech-debt,middleware,reliability. Use the shared template in agents/references/issue-filing-pattern.md. Full finding table in the detail reference above.

Model

Recommended: gpt-5.3-codex Rationale: Code-optimized model tuned for integration layer implementation and adapter patterns Minimum: gpt-5.4-mini

Read the full file on GitHub · 60 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. today Changed · -89 lines 2a0848312290
  2. 4d ago First seen · 149 lines · 36 tokens per session scan A dfb2e884496c

Subscribe to this mod's changes

middleware-dev is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 581 once invoked, about $0.0002 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.