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 agents/nxtg-ai/forge-plugin/integrationgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01914 |
| Opus 5 | $0.00000 | $0.00957 |
| Sonnet 5 | $0.00000 | $0.00383 |
| Haiku 4.5 | $0.00000 | $0.00191 |
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.
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.
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.
- yesterday First seen · 136 lines · 0 tokens per session scan A 77a5d6dc9c3d
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.
Other agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.