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 skills/danielsalles/connector-platform-plugin/integration-buildernpx skills add danielsalles/connector-platform-plugin --skill integration-buildergit clone --depth 1 https://github.com/danielsalles/connector-platform-pluginWrote 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/danielsalles/connector-platform-plugin/integration-builder)<a href="https://agentmods.dev/skills/danielsalles/connector-platform-plugin/integration-builder"><img src="https://agentmods.dev/badge/skills/danielsalles/connector-platform-plugin/integration-builder.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00101 | $0.01298 |
| Opus 5 | $0.00051 | $0.00649 |
| Sonnet 5 | $0.00020 | $0.00260 |
| Haiku 4.5 | $0.00010 | $0.00130 |
Grade A, and why
integration-builder 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
integration-builder
The user is trying to add an integration to the project. The Connector Platform plugin already has the runtime — REST API + MCP server with 100+ pre-built connectors. Don't write integration code from scratch; route to the plugin.
How the platform models the user
Connector Platform has a builder ↔ end_user model. The token in .env.local
represents the builder (the dev / company). Each authorization happens for a
specific end_user identified by external_ref:
- Personal mode (solo dev, the default for plugin users): single
external_ref="__dev__"end_user. Connections show up immediately on the MCP alias/mcp/<builder_id>/self(auto-resolves to__dev__). The scaffolded handler defaultsuser_idto__dev__. - Multi-tenant (real SaaS with N customers): the dev replaces the
hardcoded
__dev__with their session/JWT lookup so each end_user gets their own connections. MCP path becomes/mcp/<builder_id>/<external_ref>.
The dev doesn't have to flip a switch — the platform UI adapts based on the end_user count. You don't need to mention this to the user unless they ask why their connections appear under "Personal mode".
OAuth credentials (shared vs BYO)
Connectors with auth.type === 'oauth2' (github, notion, slack, etc.) default
to the platform's shared OAuth app — fine for development, but in production
the user should register their own at the provider and configure it at:
<portal>/builder/oauth-apps/<connector_slug>
This gives dedicated rate limits and a consent screen branded as their company
instead of "Connector Platform". The /connector add command surfaces this
heads-up automatically when scaffolding an OAuth-typed connector.
Decision tree
- Detect the integration name from the user's message. Common ones:
- notion, slack, linear, github, gitlab, stripe, resend, hubspot, airtable, trello, asana, jira, intercom, zendesk, salesforce, mailchimp, sendgrid, dropbox, gmail, google-calendar, google-drive, openai, anthropic, etc.
- Normalize: lowercase, hyphenate spaces, strip "api" suffix.
"Google Calendar" →
google-calendar. "Notion API" →notion.
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.
- 3d ago First seen · 122 lines · 101 tokens per session scan A 4a0ac37951c7
integration-builder is a skill published in the GitHub repository danielsalles/connector-platform-plugin (0 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 1,298 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…