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 crmy-ai/crmy --skill openclaw-plugingit clone --depth 1 https://github.com/crmy-ai/crmyWrote 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/crmy-ai/crmy/openclaw-plugin)<a href="https://agentmods.dev/skills/crmy-ai/crmy/openclaw-plugin"><img src="https://agentmods.dev/badge/skills/crmy-ai/crmy/openclaw-plugin/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/crmy-ai/crmy/openclaw-plugin"><img src="https://agentmods.dev/badge/skills/crmy-ai/crmy/openclaw-plugin.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 | $0.00039 | $0.02812 |
| Opus 5.5 | $0.00016 | $0.01125 |
| Sonnet 5.5 | $0.00008 | $0.00562 |
| Haiku 4.5 | $0.00004 | $0.00281 |
Grade A, and why
crmy 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 1mo 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRMy — Operational Customer Context For Agents
You have access to CRMy through the crmy tool. CRMy is not just a CRM table surface; it is the operational state layer that lets agents remember customer context, work with typed revenue objects, and leave audit-safe state behind.
Every call uses:
crmy({ action: "<action>", params: { ... } })
Use CRMy to:
- Get a one-call briefing before acting on a customer record.
- Search and update contacts, accounts, opportunities, use cases, activities, context entries, assignments, and HITL requests.
- Ingest messy customer context as Sources, then review Signals before they become Memory.
- Route work to humans or agents through assignments and approval requests.
- Check audit events and operations health when trust matters.
Default Agent Workflow
1. Identify yourself
Start substantive work with:
crmy({ action: "actor.whoami" })
This tells you which actor will be attributed on writes.
2. Resolve the customer record
Search before creating. Prefer exact records over guessed names.
crmy({ action: "search", params: { q: "Acme", limit: 10 } })
crmy({ action: "contact.search", params: { q: "Sarah Chen", limit: 10 } })
crmy({ action: "account.search", params: { q: "Acme", limit: 10 } })
3. Brief and check Action Context before acting
Before outreach, deal changes, handoffs, or context writes, call briefing.get for customer context and action_context.get when the work may affect a customer, record, system, or commitment.
crmy({
action: "briefing.get",
params: {
subject_type: "contact",
subject_id: "<uuid>",
context_radius: "adjacent",
token_budget: 4000,
format: "json"
}
})
crmy({
action: "action_context.get",
params: {
subject_type: "contact",
subject_id: "<uuid>",
context_radius: "adjacent",
proposed_action: { action_type: "customer_outreach" }
}
})
Use context_radius: "account_wide" for deal reviews, renewal risk, and handoffs where related account/contact context matters.
After sends, approvals, writebacks, assignments, workflows, or sequences, call context.lineage and inspect lineage.outcomes before dependent follow-up.
If Action Context returns human_unblock.required, call action_context.unblock so the approval or assignment preserves the packet, proof, and handoff snapshot.
What ships with it
5 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.
- 1mo ago First seen · 302 lines · 39 tokens per session scan A cdff1d86f969
crmy is a skill published in the GitHub repository crmy-ai/crmy (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 2,812 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
agent-project-board-sync
Agent skill for project-board-sync - invoke with $agent-project-board-sync.
agent-swarm-issue
Agent skill for swarm-issue - invoke with $agent-swarm-issue.
agent-issue-tracker
Agent skill for issue-tracker - invoke with $agent-issue-tracker.
agent-swarm
Agent skill for swarm - invoke with $agent-swarm.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
pm
Use when the user wants product requirements rather than code: 'write a PRD', 'product requirements', 'spec this feature for the team', 'ooo pm'. Runs a PM-focused interview with automatic question classification and produces a PRD/PM document. Not for implementation requests.