integration

A coding agent for connecting an application to outside services such as GitHub, Sentry, webhooks, and sign-in providers. It handles common failures including temporary outages, expired login tokens, forged webhook requests, and request limits.

In plain words
What is it for?
Use it to build API clients, webhook handlers, OAuth sign-in flows, retry and backoff behavior, and request-limit handling.
Why use it?
Connections to outside services can fail in ways that simple requests do not handle. It adds the error handling and checks needed to avoid broken or unsafe integrations.

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/nxtg-ai/forge-plugin/integration
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,914 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 $0.00000 $0.01914
Opus 5 $0.00000 $0.00957
Sonnet 5 $0.00000 $0.00383
Haiku 4.5 $0.00000 $0.00191

Measured yesterday against content hash 77a5d6dc9c3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

docs/agents/integration.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integration

Connects your application to external services -- GitHub, Sentry, webhooks, OAuth providers -- with retry logic, signature verification, and rate limit awareness built in.

Level L1 Vibe Coder
Category Domain Specialist
Model Sonnet

What It Does

The Integration agent specializes in the fragile boundary between your application and the outside world. External APIs fail, webhooks arrive with forged signatures, OAuth tokens expire mid-session, and rate limits get hit at the worst possible time. The Integration agent writes the code that handles all of this gracefully -- HTTP clients with retry and exponential backoff, webhook handlers with cryptographic signature verification, OAuth flows with proper token storage, and rate limit tracking that slows requests before hitting 429 errors.

What separates this agent from "just use fetch" is its understanding of failure modes. Every external call it writes includes error handling for the specific ways that service can fail. GitHub returns 403 when rate-limited (track X-RateLimit-Remaining). Sentry webhooks include HMAC signatures that must be verified before processing. OAuth refresh tokens expire and need re-authentication flows. The Integration agent knows these patterns because they are encoded in its service-specific knowledge, not discovered at 3 AM when production breaks.

The agent also understands the architectural principle of decoupling. An integration failure should degrade the feature that depends on it, not crash the application. If the GitHub API is down, the PR status widget shows "unavailable" instead of throwing an unhandled error. The Integration agent builds this resilience into every service connection.

When to Use It

  • Adding a GitHub integration: When you need to fetch repos, PRs, issues, or Actions status from the GitHub API with proper authentication, pagination, and rate limit handling.
  • Implementing webhook handlers: When you need to receive and process events from external services with signature verification, event routing, and idempotent processing.
  • Setting up OAuth flows: When you need third-party authentication with token exchange, refresh handling, and secure storage.
  • Connecting to monitoring services: When you need to send errors to Sentry, metrics to Datadog, or alerts to PagerDuty with proper formatting and retry logic.

Read the full file on GitHub · 136 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. yesterday First seen · 136 lines · 0 tokens per session scan A 77a5d6dc9c3d

Subscribe to this mod's changes

integration is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,914 tokens. 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.