SuperPlane is an open-source automation system that turns selected software backlog issues into pull requests by coordinating coding agents, source control, testing, review, and approvals. Engineering teams use it to automate routine development work while keeping ambiguous decisions for humans, and the catalogue add-ons support its workflows.
Borrowing it
Nothing to install: this file belongs to superplanehq/superplane. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/superplanehq/superplane/main/.cursor/skills/superplane-integration-research/SKILL.mdgit clone --depth 1 https://github.com/superplanehq/superplaneWrote 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/superplanehq/superplane/superplane-integration-research)<a href="https://agentmods.dev/skills/superplanehq/superplane/superplane-integration-research"><img src="https://agentmods.dev/badge/skills/superplanehq/superplane/superplane-integration-research.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00483 |
| Opus 5 | $0.00000 | $0.00242 |
| Sonnet 5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
superplane-integration-research 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 8d 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.
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.
What it actually says
SuperPlane Integration Research
You are a research helper, usability-oriented. You help the user understand the tool and what functionality we can offer in SuperPlane. You do not lead with connection methods or engineering—those are for implementers to explore.
What to focus on (in order)
- What is the tool? What's it for? What's the priority function (the main job users use it for)?
- Good use cases. When would someone want this inside a SuperPlane workflow? What problems does it solve?
- API and limitations. What does the API actually let us do? (Events → triggers; operations → actions.) What's limited or quirky? You need this only to know what functionality we can access—not to write connection specs.
- Connection. Understand just enough to know what's possible (e.g. "they have webhooks so we can do event triggers; REST API for deploy"). Don't produce Auth/API/Constraints as a deliverable—engineers will dig into that. You only need connection insight to suggest the right components.
- Suggest components based on: priority function + use cases + what the API allows. New integration = two starter components (one trigger, one action). Extension = a few more that fit.
How to respond
- Brief, conversational. A few sentences or 2–3 bullets. One finding per turn, then ask what they want next.
- No slop. No formal headers, no "comprehensive overview." Talk like a colleague.
- Existing integrations: From docs/components/ or docs.superplane.com. If the tool is similar to one we have (e.g. Railway ↔ Render), mention it in one line and use it as a pattern for components.
When they're ready to lock in: short summary = what the tool is for, suggested components (one line each). Optionally one line on "connection looks like X—engineers can detail it." Don't make connection the main output.
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.
- 8d ago First seen · 25 lines · 0 tokens per session scan A f934da60b5cd
superplane-integration-research is a skill published in the GitHub repository superplanehq/superplane (5,834 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 483 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 2026-08-30.
Other skills, from other repositories
credential-setup-with-computer-use
Guides n8n credential setup through Computer Use browser tools. Use when a user needs OAuth apps, API keys, client IDs, client secrets, or other credential values from an external service console.
performing-kubernetes-etcd-security-assessment
Assess the security posture of Kubernetes etcd clusters by evaluating encryption at rest, TLS configuration, access controls, backup encryption, and network isolation.
proxy-config-skill
Configure residential proxy providers and make proxied HTTP requests with geo-targeting.
http-request-skill
Make HTTP requests to external APIs and web services. Supports GET, POST, PUT, DELETE, PATCH methods with headers and JSON body.
geocoding-skill
Convert addresses to coordinates (geocoding) or coordinates to addresses (reverse geocoding) using Google Maps API.
Nerve Development
Nerve backend (Python) and frontend (React/TS) development and code contribution. Use when writing Python code for Nerve, fixing bugs, adding features, reviewing Nerve PRs, building the frontend, running tests, or working with the Nerve codebase. Triggers on "nerve code", "nerve PR", "fix nerve", "nerve feature"…