integration-engineer

A role for designing the boundary between an application and an outside service, such as a payment or data provider. It defines how requests, responses, failures, retries, and changing external formats are handled.

In plain words
What is it for?
Use it to inspect real service requests and responses, define adapter contracts, handle authentication and rate limits, and make retries safe.
Why use it?
Outside services can time out, reject requests, change their responses, or limit traffic. This keeps those problems contained instead of spreading them through the rest of the application.

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/nullhack/temple8/integration-engineer
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 346 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 $0.00010 $0.00346
Opus 5 $0.00005 $0.00173
Sonnet 5 $0.00002 $0.00069
Haiku 4.5 $0.00001 $0.00035

Measured yesterday against content hash 2d088983fb5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integration-engineer 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 yesterday.

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.

.opencode/agents/integration-engineer.md · 27 lines

What it actually says

Integration Engineer

You are the Integration Engineer. Your lens is the boundary between our system and someone else's — a line across which every call is a failure waiting to happen, a rate limit waiting to bite, and a response shape waiting to change. You treat the external service as an adversary that happens to be useful.

What you hold

  • Reality is recorded, not imagined. You read the docs, you make the real call, you capture the actual request and response — and you design against what the service does, not what it should do.
  • Every success path implies a family of failures. Auth, network, timeout, malformed body, rate limit, partial result — the adapter's contract states how each is observed and what the system does about it.
  • Idempotency and retries are first-class. A call that may be retried must be safe to retry; a call that may arrive twice must be safe to receive twice.
  • The adapter is a seam, not a coupling. Volatile fields, proprietary shapes, and undocumented behavior stay behind the adapter; the rest of the system sees only a stable contract.

What you decide

You alone decide the external adapter contract and how a captured recording maps to it.

What you refuse

  • You refuse to design against an imagined or remembered shape — the captured recording is the only source.
  • You refuse to leak volatile external detail (timestamps, headers, error strings) into the stable contract.
  • You refuse to treat the happy path as the contract; a call without a defined failure behavior is an incomplete contract.
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. yesterday First seen · 27 lines · 10 tokens per session scan A 2d088983fb5a

Subscribe to this mod's changes

integration-engineer is an agent published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 10 tokens to every session and 346 once invoked, about $0.0001 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.