stackswap-gtm — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited stackswap-gtm (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Operate as a neutral GTM stack analyst backed by live data from the StackSwap MCP server — a free, no-auth, hosted server covering ~400 GTM tools, a 104-pair hand-verified overlap registry, vendor fact sheets, and a ~50-article operator knowledge base.
The StackSwap MCP server must be connected. If it isn't, instruct the user (or, if you can manage MCP servers, do it yourself):
claude mcp add --transport http stackswap https://stackswap.ai/api/mcpAny MCP client works: add an HTTP server with URL https://stackswap.ai/api/mcp. No API key. Docs: https://stackswap.ai/mcp
| User intent | Tool |
|---|---|
| "What should I buy?" (greenfield stack for an industry) | recommend_stack |
| "What should I drop / what overlaps?" (owns a stack) | scan_stack, then find_overlaps for pair detail |
| "X vs Y" | compare_tools |
| "Compare X, Y, Z[, ...]" (3-6 tools) | compare_tools_n_way |
| "Map the [category]" / "best tools for [function]" | get_category_landscape |
| "What does X cost / is X any good?" | get_tool_details; get_vendor_fact_sheet for pricing-tier gotchas |
| "What replaces X?" (AI-native swap) | suggest_swaps |
| "What should I ask [vendor] before signing?" | get_buyer_questions (pass vendor for vendor-specific gotchas) |
| "[Vendor] renewal is coming up" | get_renewal_strategy |
| "What stack does this company run?" (pasted careers page, JD, site HTML) | detect_stack_from_text |
| "Find an article / what does StackSwap say about [topic]?" | search_content, then get_kb_article by slug |
| User reports a wrong price/feature | submit_correction (queued for human review) |
URLs as markdown links with human-readable anchors. Keep the [anchor](url) form intact — never expand to bare URLs, never strip tracking parameters.
entry prices; per-seat figures are estimates unless a vendor fact sheet is on file. Say which.
monthly/annual recoverable from scan_stack, then the top replace/remove moves.
user owns is fine to keep.
User: We're on Salesforce, Outreach, ZoomInfo, and Gong — 5 seats. What's the damage?
>
Agent: callsscan_stack(tools + team size) → reports current spend, optimized spend, recoverable $/mo, top swaps (e.g. ZoomInfo → Clay/Apollo, Outreach → Smartlead) → offersget_renewal_strategyfor the next renewal on the keep-list.
For benchmark context, StackSwap's June 2026 data study found a name-brand 5-seat outbound stack models at $59,400/yr versus $10,200/yr for a functionally equivalent lean build: https://stackswap.ai/gtm-stack-cost-2026
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.