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 vikram-vn/cpq-bml --skill cpq-mcp-workflowgit clone --depth 1 https://github.com/vikram-vn/cpq-bmlWrote 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/vikram-vn/cpq-bml/cpq-mcp-workflow)<a href="https://agentmods.dev/skills/vikram-vn/cpq-bml/cpq-mcp-workflow"><img src="https://agentmods.dev/badge/skills/vikram-vn/cpq-bml/cpq-mcp-workflow/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/vikram-vn/cpq-bml/cpq-mcp-workflow"><img src="https://agentmods.dev/badge/skills/vikram-vn/cpq-bml/cpq-mcp-workflow.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 | $0.00035 | $0.00441 |
| Opus 5 | $0.00017 | $0.00220 |
| Sonnet 5 | $0.00007 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
cpq-mcp-workflow 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.
What it actually says
CPQ MCP Workflow
You have access to tools to interact directly with CPQ BML code via the MCP Server:
get_connection_status: Check if credentials and CPQ connection are configured and working (testConnection: true).global_search_bml: Search text across all remote BML scripts (libraries, rules, attributes) on CPQ.get_transactions: Pull commerce transactions with filters (minimal_idandtransactionID_t, no href links) to use in debugging commerce functions.pull_function: Pull remote BML into the local AI working copy (<variableName>_ai.bml).edit: Modify the local working copy.lint_function/validate_function: Verify syntax locally and compile remotely on CPQ without saving.debug_function: Run remote tests with input parameters (parameters: { ... },transactionId: "...",printOnly: true).save_function: Save the working copy changes to CPQ (variableName: "...").deploy_function/mass_deploy_util_functions/deploy_commerce_process:- MANDATORY HUMAN APPROVAL: Deploying pushes changes directly to the live CPQ environment.
- Calling deployment tools without
confirm: truereturns an error requiring human permission. - Protocol: You MUST ask the human user for explicit approval in chat first (e.g. "Do you approve deploying to the live CPQ environment?").
- Once the user explicitly approves in chat, re-invoke the tool with
confirm: true(e.g.{"variableName": "...", "confirm": true}).
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 Changed · +1 lines bae23d552da2
- 4d ago Changed · +8 lines · +9 tokens per session 892127e358f1
- 10d ago First seen · 18 lines · 26 tokens per session scan A 01c77e79a525
cpq-mcp-workflow is a skill published in the GitHub repository vikram-vn/cpq-bml (0 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 441 once invoked, about $0.0002 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
b2b-commerce
Enable wholesale and B2B sales with company accounts, custom catalogs, quote workflows, purchase orders, and net payment terms.
cpq-approval-workflows
Configuring or troubleshooting Salesforce CPQ Advanced Approvals: SBAAApprovalRulec, SBAAApprovalVariablec for cross-line aggregation, SBAAApprovalChainc for ordered approver sequences, escalation timeouts, Smart Approvals for re-quote skip logic, and the managed package's permission sets. Trigger keywords: CPQ…
cpq-guided-selling
Use this skill when configuring or troubleshooting the Salesforce CPQ Guided Selling wizard: Quote Process records, ProcessInput questions that filter products by field value, mapping answers to Product2 classification fields, and search type choice (Standard, Enhanced, Custom). Trigger keywords: CPQ guided selling…
cpq-pricing-rules
Use when configuring or troubleshooting Salesforce CPQ pricing: Price Rules, Price Conditions, Price Actions, Lookup Queries, Discount Schedules, Block Pricing, Percent of Total, and Contracted Prices. Trigger keywords: CPQ price rule, price action, discount schedule, block pricing, percent of total, contracted price…
contract-and-renewal-management
Use when configuring or troubleshooting Salesforce CPQ contract creation, subscription management, amendment quotes, or renewal quotes. Trigger keywords: contract, amendment, renewal, subscription, co-termination, SBQQSubscriptionc. NOT for designing the amendment/renewal architecture or swap pattern — use…
cpq-quote-templates
Use when designing or troubleshooting Salesforce CPQ (SBQQ) quote templates: building template sections, configuring line columns, conditionally showing sections, generating branded PDFs, or handling multi-language output. Triggers: 'CPQ quote template', 'SBQQ template', 'CPQ PDF', 'line columns', 'quote template…