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 skills add indranilbanerjee/neels-plugins --skill add-integrationgit clone --depth 1 https://github.com/indranilbanerjee/neels-pluginsWrote 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/indranilbanerjee/neels-plugins/add-integration)<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/add-integration"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/add-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/add-integration"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/add-integration.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00030 | $0.01297 |
| Opus 5.5 | $0.00012 | $0.00519 |
| Sonnet 5.5 | $0.00006 | $0.00259 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
add-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 2d 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.
This is a copy
88% identical to add-integration — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digital-marketing-pro:add-integration
Purpose
Guide users through adding a custom MCP server integration to the Digital Marketing Pro plugin. Search for existing MCP packages that provide the desired service connection, configure the server entry in .mcp.json with proper command, arguments, and environment variables, test connectivity to verify the integration works, and document the available tools. Supports both pre-built MCP servers from npm and custom implementations for proprietary APIs or internal tools.
Input Required
The user must provide (or will be prompted for):
- Service to integrate: The name and purpose of the service to connect — e.g., "Ahrefs for backlink analysis", "Stripe for payment data", "our internal analytics API for custom dashboards". This determines the MCP package search terms and configuration approach
- Integration type: Whether to use a pre-built npm MCP package (preferred — faster setup, community-maintained) or build a custom MCP server (necessary for proprietary APIs, internal tools, or services without existing MCP packages). If unsure, the system searches for pre-built options first
- Credentials available: API keys, access tokens, OAuth client IDs, or other authentication credentials required by the service. The user should have these ready — the system will specify which environment variable names to use and where to store them, but will never ask the user to paste secrets into the conversation
Process
- Load brand context: Read
~/.claude-marketing/brands/_active-brand.jsonfor the active slug, then load~/.claude-marketing/brands/{slug}/profile.json. Check for agency credential profiles at~/.claude-marketing/credentials/— if agency mode is active, the new integration may need to be mapped to specific client credential sets. Check for agency SOPs at~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults. - Search for existing MCP package: Query npm registry and known MCP server directories for packages matching the requested service — search by service name, API name, and common variations. Evaluate candidates by download count, last update date, GitHub stars, and compatibility with the plugin's MCP configuration format. Present the best match (or top 3 if multiple viable options) with package name, description, supported tools, and any known limitations.
- Generate configuration for pre-built package: If a suitable package is found, generate the complete
.mcp.jsonentry — server name (following the plugin's naming convention: lowercase with hyphens), command (npxfor npm packages), args array with the package name and any required flags, env object mapping environment variable names to credential references, and a description field summarizing what the integration provides. Show the user the exact JSON block to add. - Provide custom MCP guidance if needed: If no suitable pre-built package exists, provide a custom MCP server development template based on
skills/context-engine/custom-mcp-guide.md— project structure, required tool definitions, input/output schemas, authentication handling, and error response patterns. Include a starter implementation skeleton for the specific API the user wants to connect, with placeholder endpoints and authentication flow. - Configure environment variables: Guide the user on environment variable setup — specify the exact variable names to use (following the
SERVICE_API_KEYconvention), where to add them (.envfile in the project root or system environment variables for CI/CD), and how to reference them in the.mcp.jsonconfiguration. For agency setups, explain how to add the credentials to the appropriate credential profile at~/.claude-marketing/credentials/. - Test MCP connectivity: After the user confirms the configuration is in place, verify the integration works — check that the MCP server starts without errors, list the available tools it exposes, execute a basic read-only operation (e.g., fetching account info, listing resources, or a health check endpoint) to confirm authentication and connectivity. Report success or diagnose failure with specific error details and remediation steps.
- Map to agency credential profile (if applicable): For agency setups with multiple client brands, add the new integration's credential mapping to the appropriate profile — which environment variables are client-specific vs shared, how to switch credentials when switching brands, and how to verify the correct credentials are active.
- Document the integration: Record the new integration in the brand's configuration — service name, MCP server name, tools available, credential requirements, any rate limits or usage constraints discovered during testing, and example usage patterns for team reference.
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.
- 2d ago First seen · 46 lines · 30 tokens per session scan A 3f58b4465c35
add-integration is a skill published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 1,297 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to add-integration, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
continuous-improvement-loop
Run the Part 12 continuous improvement loop into a quarterly brief for leadership. "produce the quarterly improvement brief".
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
attribution-report
Run attribution on real conversion paths, comparing models. "which channels actually drive revenue".
validate-output
Validate content structure against a schema: sections, word counts. "scan for leftover placeholders".
add-integration
Add a custom MCP integration: scaffold the server, write .mcp.json, test it. "add a new MCP server".
client-proposal
Draft a client proposal or RFP response: scope, deliverables, KPIs, pricing tiers. "respond to this RFP".