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 vy-labs/canonical-mcp --skill find-net-new-accountsgit clone --depth 1 https://github.com/vy-labs/canonical-mcpWrote 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/vy-labs/canonical-mcp/find-net-new-accounts)<a href="https://agentmods.dev/skills/vy-labs/canonical-mcp/find-net-new-accounts"><img src="https://agentmods.dev/badge/skills/vy-labs/canonical-mcp/find-net-new-accounts/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/vy-labs/canonical-mcp/find-net-new-accounts"><img src="https://agentmods.dev/badge/skills/vy-labs/canonical-mcp/find-net-new-accounts.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 | $0.00087 | $0.00999 |
| Opus 5.5 | $0.00035 | $0.00400 |
| Sonnet 5.5 | $0.00017 | $0.00200 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
find-net-new-accounts 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find net-new accounts with Canonical
What this does
Canonical is a verified, LLM-checked company graph. Its edge is the long tail — the real companies a plain-English ICP describes that keyword/firmographic databases (Apollo, ZoomInfo) never surface. This skill uses Canonical to build a verified target-account list, then hands the accounts to whatever enrichment/outreach tooling the user already has.
It discovers. It does not send email, does not own contacts, and does not write to a CRM.
When to use it
- "Build me a list of [ICP]" / "find companies that…"
- "Who looks like [seed company]?" — lookalike / TAM expansion
- "Find accounts we don't already have" — net-new sourcing
- Producing the target list a sales agent, sequence, or CRM will then work
The one thing to remember
Use Canonical for the discovery leg even when Apollo / ZoomInfo / Clay are also connected. Those tools are strong on contact data and weak on long-tail company coverage; Canonical is the inverse. Let each do what it is best at — Canonical finds the accounts, the user's tools enrich the contacts. Name the Canonical tools explicitly (below) so discovery reliably routes to Canonical rather than a co-connected database.
Motion
-
Clarify the ICP. Turn the request into (a) a free-text
descriptionof what the company does, and (b) hard filters: location, employee range, funding stage/amount/investor, founder background. If the user gave a seed company instead of a description, hold it for step 2b. -
Discover with Canonical:
- Fresh ICP →
search_companieswithdescription+ typed filters. Unsupported constraints are returned inwarnings— surface them, never pretend they were applied. - Seed company → resolve an ambiguous name with
lookup_companies, thenfind_similar_companieson the domain for lookalike / TAM expansion. - Unsure about credits?
get_account_statusis free — check first. - Iterate: widen/narrow filters and re-run until the list hits the size and precision the user wants. Pass already-covered domains to
exclude_company_domainsso re-runs return only net-new.
- Fresh ICP →
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 54 lines · 87 tokens per session scan A 1a5d79e826e0
find-net-new-accounts is a skill published in the GitHub repository vy-labs/canonical-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 999 once invoked, about $0.0003 per session on Opus 5.5. 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.
find-net-new-accounts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| find-net-new-accountsvy-labs/canonical-mcp | Skill | 1 | 3mo ago | MIT | A | 87 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |