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 voicelogica/voice-logica-plugin --skill manage-crmgit clone --depth 1 https://github.com/voicelogica/voice-logica-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/voicelogica/voice-logica-plugin/manage-crm)<a href="https://agentmods.dev/skills/voicelogica/voice-logica-plugin/manage-crm"><img src="https://agentmods.dev/badge/skills/voicelogica/voice-logica-plugin/manage-crm/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/voicelogica/voice-logica-plugin/manage-crm"><img src="https://agentmods.dev/badge/skills/voicelogica/voice-logica-plugin/manage-crm.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 | $0.00044 | $0.00644 |
| Opus 5 | $0.00022 | $0.00322 |
| Sonnet 5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
manage-crm 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 12d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Voice Logica CRM
Self-serve CRMs: HubSpot, Zoho, Salesforce.
Monday.com is not self-serve. Do not try to add it from the customer UI. Point the user to Voice Logica if they need Monday.com.
3-layer rule
- Connect the CRM integration on the company (OAuth).
- Enable the CRM tool on the agent (
list_agent_tools/update_agent_tool). Read the live tool name — commonlyhubspot,zoho, orsalesforce. - Test with a Call ID and read
toolCalls.
If OAuth shows needsReconnect, disconnect and reconnect. Never edit the prompt to paper over a dead token. Never paste live API tokens into chat.
HubSpot
Setup: OAuth popup. Typical scopes: contacts, companies, deals, tickets, owners, schemas. Also used from workflow CRM nodes.
The HubSpot agent tool has three field groups. Enable only what the call flow needs:
readContactProperties— lookup / read contact fields during the callupdateContactProperties— write fields the caller actually providedcreateCallActivity— log the call on the HubSpot contact
A connected HubSpot account with the tool off will not run. A tool with no properties selected will run and do nothing useful.
After enabling, confirm the property names match HubSpot (internal names, not labels). Then test: find a contact, update one field, check the Call ID.
Zoho
OAuth redirect. Confirm the correct Zoho DC / region. Scopes typically include contacts, leads, notes create. Same 3-layer rule. Read the live tool config first. Change only the fields the user asked for.
Salesforce
Dialog: sandbox toggle, optional bring-your-own client id/secret, then OAuth + PKCE. Ask sandbox vs production — the host matters. Typical scopes: api, refresh_token, id. Do not ask for client secrets unless they are using BYO Salesforce. Same 3-layer rule.
Common jobs
"The agent did not update the CRM."
Get a Call ID. Check toolCalls for the CRM tool. If it never fired, check layer 2 and the prompt instruction to use it. If it fired and failed, check OAuth / needsReconnect and the property names. Do not start by rewriting the prompt.
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.
- 12d ago First seen · 56 lines · 44 tokens per session scan A 538f46467fed
manage-crm is a skill published in the GitHub repository voicelogica/voice-logica-plugin (0 stars, last pushed 20d ago), licensed MIT. It adds 44 tokens to every session and 644 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
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-gmail
Gmail: Send, read, and manage email.
gws-shared
The gws binary must be on $PATH. See the project README for install options.
gws-sheets
Google Sheets: Read and write spreadsheets.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
gws-docs
Read and write Google Docs.