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 lobu-ai/lobu --skill crm-opsgit clone --depth 1 https://github.com/lobu-ai/lobuWrote 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/lobu-ai/lobu/crm-ops)<a href="https://agentmods.dev/skills/lobu-ai/lobu/crm-ops"><img src="https://agentmods.dev/badge/skills/lobu-ai/lobu/crm-ops/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/lobu-ai/lobu/crm-ops"><img src="https://agentmods.dev/badge/skills/lobu-ai/lobu/crm-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01013 |
| Opus 5 | $0.00022 | $0.00507 |
| Sonnet 5 | $0.00009 | $0.00203 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
crm-ops 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 11d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRM operations
The CRM lives in Lobu memory. Two entity types — lead and pilot — hold current state; events of type lead:* / pilot:* are the append-only history. The converted-to relationship links a lead to the pilot it became.
Funnel stages (the stage field on lead)
signal → trial → conversation → pilot → customer, plus cold (went quiet / not a fit). "Reach" (an impression, a passing tweet view) is not a stage — no lead record until there's a signal.
| Stage | Enter it when… |
|---|---|
signal |
starred the repo, followed on X, @-mentioned Lobu, commented on an issue |
trial |
cloned / ran lobu run / completed the quickstart / asked a real deployment question |
conversation |
DM'd, requested a demo, booked a call, said "we want to deploy this" |
pilot |
signed up for a paid pilot — open a pilot entity, link with converted-to |
customer |
converted from pilot to a paid contract |
cold |
three touches with no response, or explicitly not a fit |
Creating / enriching a lead
- Search first —
search_memory({query: "<github handle | x handle | email | company>"}). If aleadexists, enrich it; don't duplicate. - If new: create the
leadentity with metadata{name, company, source, stage, github_handle, x_handle, email, notes}. Setstageto the lowest stage the evidence supports. save_memory({content: "<who, company, source>", semantic_type: "lead:created", entity_ids: [<lead>, <source connector event>]}).
Logging an interaction
After any touchpoint (a meeting Burak had, a DM exchange, an issue reply you drafted):
save_memory({content: "{type, summary, next_action, date}", semantic_type: "lead:interaction", entity_ids: [<lead>]}). Update the lead's notes / stage if the touch moved it (see "advancing a stage").
Advancing a stage
save_memory({content: "{from, to, reason}", semantic_type: "lead:stage_changed", entity_ids: [<lead>]}).- Update the
leadentity'sstagefield. Never changestagewithout the matching event.
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.
- 11d ago First seen · 61 lines · 44 tokens per session scan A 861df908b261
crm-ops is a skill published in the GitHub repository lobu-ai/lobu (220 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 1,013 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 2026-08-30.
Other skills, from other repositories
trello
Manages Trello boards, lists, and cards via the Trello REST API. Use when the user wants to create cards, move tasks between lists, list boards, add comments, archive cards, or check what is on a Trello board. Handles authentication, pagination, and rate-limit awareness for all Trello REST endpoints.
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
status-report
Use when the user asks for a weekly / monthly status report, project update, individual or team progress summary. Produces a tight, scannable update with what shipped, what's in flight, what's blocked, and metrics.
wework-notifications
Send Wework in-app notifications when a user requests an alert, greeting, or automation notification. Works in ordinary conversations without a project or board, with optional project links and delivery to connected IM sessions.
wework-project-space
Read or update the Wework project space, current Issue, attachments, deliveries, members, or board items when a Wework project or Issue context is active.
dingtalk-ai-table
Read and manage DingTalk AI table records through the DingTalk AI Table MCP. Use this skill when the user explicitly refers to a DingTalk AI table, fields, or records.